Nothing Special   »   [go: up one dir, main page]

WO2018147653A1 - Method, device and computer program for generating survival rate prediction model - Google Patents

Method, device and computer program for generating survival rate prediction model Download PDF

Info

Publication number
WO2018147653A1
WO2018147653A1 PCT/KR2018/001692 KR2018001692W WO2018147653A1 WO 2018147653 A1 WO2018147653 A1 WO 2018147653A1 KR 2018001692 W KR2018001692 W KR 2018001692W WO 2018147653 A1 WO2018147653 A1 WO 2018147653A1
Authority
WO
WIPO (PCT)
Prior art keywords
prediction model
survival rate
survival
data
section
Prior art date
Application number
PCT/KR2018/001692
Other languages
French (fr)
Korean (ko)
Inventor
서성욱
Original Assignee
사회복지법인 삼성생명공익재단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 사회복지법인 삼성생명공익재단 filed Critical 사회복지법인 삼성생명공익재단
Publication of WO2018147653A1 publication Critical patent/WO2018147653A1/en

Links

Images

Classifications

    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/18Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/22Social work or social welfare, e.g. community support activities or counselling services

Definitions

  • Embodiments of the present invention relate to a method, apparatus and computer program for generating a survival prediction model.
  • Cancer 5-year survival rate is a representative indicator of the effectiveness of medical technology and the performance of the medical system.
  • Cancer 5-year survival rate refers to the probability that a cancer patient diagnosed with cancer and started treatment will not die from cancer that has occurred for at least 5 years.
  • the high five-year survival rate indicates that cancer treatment is progressing relatively smoothly, and that the medical system is suitable for managing severe diseases such as cancer.
  • the OECD compares international 5-year survival rates for colorectal cancer, uterine cancer and breast cancer. OECD cancer survival statistics are inconsistent with domestic cancer survival statistics due to differences in calculations. On a OECD basis, Korea's five-year survival rate for colorectal cancer was 70.9% in 2008-2013, the highest among the major OECD countries, followed by Sweden (65.4%). The 5-year survival rate for breast cancer is 85.9% in Korea, slightly higher than the OECD average (84.9%) and about 5 percentage points lower than Sweden (89.4%), which has the highest survival rate.
  • Embodiments of the present invention provide a method, apparatus, and computer program for generating a survival prediction model capable of predicting annual survival rates from medical data of a patient.
  • a first step of generating an N-th section survival prediction model using clinical data and N-th section survival rate data of a subject who provided the clinical data And a second step of generating an N + 1th interval survival prediction model using the Nth interval survival rate data, the Nth interval survival prediction model, and the N + 1st interval survival rate data.
  • a prognostic prediction model generation method for generating a prediction model is disclosed.
  • the score discloses a method for generating a prognostic prediction model that is proportional to the survival period.
  • the survival period discloses a method for generating a prognostic prediction model divided at least monthly.
  • the N + 1 th section survival prediction model discloses a method for generating a prognostic prediction model, which is an input / output function for inputting the clinical data and the N th section survival rate data and outputting the N + 1 th section survival rate data.
  • the generating step discloses a prognostic prediction model generation method using a Recurrent Neural Network (RNN) algorithm.
  • RNN Recurrent Neural Network
  • Another embodiment of the present invention comprises a clinical data acquisition unit for obtaining clinical data; A survival rate data acquisition unit for obtaining survival rate data; And generating the N-th section survival rate prediction model using the clinical data and the N-th section survival rate data of the subject who provided the clinical data, and the N-th section survival rate data, the N-th section survival rate prediction model, and the N + 1st And a prediction model generator configured to generate an N + 1th interval survival prediction model using interval survival data.
  • Survival data processing unit for giving a score according to the survival period for each of the N-th section survival rate data; further comprising, wherein the prediction model generator, N + using the scores assigned to each of the N-th section survival rate data
  • a prognostic prediction model generating device for generating a 1 year survival prediction model.
  • the score discloses an apparatus for generating a prognostic prediction model that is proportional to the survival period.
  • the survival period discloses a prognostic prediction model generating device divided at least monthly.
  • the N + 1th section survival rate prediction model discloses a prognostic prediction model generating device which is an input / output function for inputting the clinical data and the Nth section survival rate data and outputting the N + 1th section survival rate data.
  • the generating step discloses a prognostic prediction model generation device using a Recurrent Neural Network (RNN) algorithm.
  • RNN Recurrent Neural Network
  • Another embodiment of the present invention discloses a computer program stored in a medium for executing the above-described prognostic prediction model generation method using a computer.
  • Survival prediction model generation method, apparatus and computer program according to embodiments of the present invention can predict the annual survival rate from the medical data of the patient.
  • the method, apparatus and computer program for generating a survival prediction model generate a prediction model with high accuracy by generating a survival prediction model this year using survival data of a previous year's patient.
  • Survival prediction model generation method, apparatus and computer program can obtain a large number of significant data by assigning a ranked score in using the survival data of the previous year patient, and thus accuracy Produces a high prediction model.
  • FIG. 1 schematically illustrates a configuration of an apparatus for generating a predictive model according to an embodiment of the present invention.
  • FIG. 2 is a flowchart illustrating a method of generating a prediction model according to an embodiment of the present invention.
  • FIG. 3 is a flowchart illustrating a method of generating a prediction model according to another embodiment of the present invention.
  • FIG. 4 is a view for explaining a prediction model according to an embodiment of the present invention.
  • FIG. 5 is another example of a diagram for describing a prediction model according to an embodiment of the present invention.
  • FIG. 6 is a graph illustrating a prediction model according to an embodiment of the present invention.
  • FIG. 1 schematically illustrates a configuration of an apparatus for generating a predictive model according to an embodiment of the present invention.
  • the predictive model generating apparatus 10 shown in FIG. 1 shows only the components related to the present embodiment in order to prevent the features of the present embodiment from being blurred. Accordingly, it will be understood by those skilled in the art that other general purpose components may be further included in addition to the components shown in FIG. 1.
  • the prediction model generating apparatus 10 may correspond to at least one processor or may include at least one processor. Accordingly, the predictive model generating device 10 may be driven in a form included in another hardware device such as a microprocessor or a general purpose computer system.
  • the invention can be represented by functional block configurations and various processing steps. Such functional blocks may be implemented in various numbers of hardware or / and software configurations that perform particular functions.
  • the present invention is an integrated circuit configuration such as memory, processing, logic, look-up table, etc., capable of executing various functions by the control of one or more microprocessors or other control devices. You can employ them.
  • the present invention includes various algorithms implemented in data structures, processes, routines or other combinations of programming constructs, including C, C ++ It may be implemented in a programming or scripting language such as Java, an assembler, or the like.
  • the functional aspects may be implemented with an algorithm running on one or more processors.
  • the present invention may employ the prior art for electronic environment setting, signal processing, and / or data processing.
  • Terms such as “mechanism”, “element”, “means”, “configuration” may be used widely, and the components of the present invention are not limited to mechanical and physical configurations.
  • the term may include the meaning of a series of routines of software in conjunction with a processor or the like.
  • the prediction model generating device 10 includes a clinical data acquisition unit 11, a survival rate data acquisition unit 12, a survival rate data processing unit 14, and a prediction model generation unit 13.
  • the clinical data acquisition unit 11 acquires medical data of a patient, for example, clinical data.
  • Clinical data may be obtained from a medical image of a patient or may be obtained from a patient's specimen test result, but is not limited thereto.
  • the survival rate data acquisition unit 12 acquires survival rate data of a subject (patient) who provided clinical data.
  • Survival data is data showing survival or not. Survival data may include only survival, but may further include information about survival.
  • the prediction model generator 13 generates a survival prediction model that can predict the survival rate for each section of the patient from the clinical data of the patient.
  • the interval may be a year.
  • the prediction model generator 13 may generate a survival prediction model that predicts annual survival rate of gastric cancer patients from clinical data of gastric cancer patients.
  • the prediction model generator 13 may generate a survival prediction model that may predict annual survival rates of gastric cancer patients from 1 year to 5 years from the first year clinical data of gastric cancer patients.
  • the prediction model generator 13 may generate a survival prediction model based on clinical data and actual survival data of patients using a machine learning technique.
  • the prediction model generator 13 may use a deep learning algorithm among machine learning techniques, and among them, may use a recurrent neural network (RNN) algorithm.
  • RNN recurrent neural network
  • the RNN algorithm refers to a neural network in which a connection between units constituting an artificial neural network constitutes a directed cycle.
  • the prediction model generator 13 generates the N-th section survival prediction model using the clinical data and the N-th section survival rate data of the patient who provided the clinical data.
  • the prediction model generator 13 generates the N + 1st section survival prediction model using the clinical data and the N + 1st section survival rate data of the patient who provided the clinical data.
  • the prediction model generator 13 may be based on the Nth interval survival prediction model using the RNN algorithm to generate the N + 1th interval survival prediction model.
  • the prediction model generator 13 further uses the N-th section survival rate data to generate the N + 1-th section survival rate prediction model. That is, the N + 1th section survival rate prediction model may be an input / output function that inputs clinical data and Nth section survival rate data and outputs N + 1th section survival rate. As such, when the N-th section survival rate data is further used as an input value of the N + 1 th section survival prediction model, an accurate prediction model may be generated.
  • the prediction model generator 13 In relation to generating the N-th section survival prediction model using the N-th section survival rate data, the prediction model generator 13 according to an embodiment generates the aforementioned N + 1-th section survival prediction model when N is 2 or more. The method applies equally. For example, when N is 2 or more, the prediction model generator 13 may be based on the N-1th interval survival prediction model using the RNN algorithm to generate the Nth interval survival prediction model, and N-1 Second interval survival data may be further used.
  • the prediction model generator 13 does not use the N-1th section survival rate prediction model, and uses the clinical data and the Nth section survival rate data of the patient who provided the clinical data.
  • a survival prediction model may be generated, and a predetermined initial survival rate P_0 may be further used. Details related to this will be described later with reference to FIG. 5.
  • the prediction model generator 13 may use the processed data in using the N-th section survival rate data.
  • the survival rate data processor 14 processes the survival rate data. For example, each survival data is scored over survival.
  • the prediction model generator 13 generates a N + 1 year survival prediction model using scores assigned to each of the N-th section survival data.
  • the survival rate data processing unit 14 may assign a score to the survival rate data in proportion to the survival period. Survival periods may be divided at least monthly. According to this, the survival rate of the deceased patient is not counted as 0, but the ranked score is given as much as the survival period, thereby increasing the number of significant data used to generate the model, and consequently contributing to the generation of a highly accurate model. .
  • the prediction model generator 13 generates a survival rate prediction model for each section, for example, annually. For example, in the case of a model for predicting the survival rate of a cancer patient, a 1 year survival prediction model, a 2 year survival prediction model, a 3 year survival prediction model, a 4 year survival prediction model and a 5 year survival prediction model may be generated. Each annual model predicts the patient's corresponding annual survival rate from the patient's clinical data.
  • Each annual model may include a multi-layered matrix that connects i nodes corresponding to clinical data of the patient to two survival nodes.
  • Each annual model generated by the predictive model generator 13 may connect two nodes corresponding to i nodes corresponding to clinical data of a patient and two nodes corresponding to a previous year survival rate to two survival rate nodes. It may include a matrix of multiple layers, that is, a matrix of multiple layers connecting i + 2 input nodes to two output nodes.
  • the input node contains nodes corresponding to previous year's survival rate data.
  • the previous year's survival rate data nodes may be two, each of which may be a survival node and a death node.
  • the survival rate data may be [0, 1] when the patient dies or [1, 0] when the patient survives.
  • a treatment method capable of giving a score by ranking it is proposed without treating the survival rate data when the patient dies with [0, 1].
  • Survival data of patients who died in this example may be [p, 1-p], where p is assigned a non-zero score value.
  • the score may be given in proportion to the survival of the deceased patient.
  • Table 1 below is an example of N-year survival rate scores by N-year survival period.
  • Table 1 described an example in which survival periods are divided into monthly units, but the present invention is not limited thereto, and the survival periods may be divided into various units such as semi-annual, quarterly, monthly, and day depending on the design.
  • FIG. 2 is a flowchart illustrating a method of generating a prediction model according to an embodiment of the present invention.
  • the prediction model generator 13 of FIG. 1 generates the N-th section survival prediction model using the clinical data of the patient and the N-th section survival rate data.
  • the prediction model generator 13 of FIG. 1 generates the N + 1th section survival prediction model using the Nth section survival rate data, the Nth section survival rate prediction model, and the N + 1st section survival rate data.
  • FIG. 3 is a flowchart illustrating a method of generating a prediction model according to another embodiment of the present invention.
  • the prediction model generator 13 of FIG. 1 generates the N-th section survival prediction model using the clinical data of the patient and the N-th section survival rate data.
  • step 32 the survival rate data processing unit 14 of FIG. 1 assigns a score according to the survival period to the Nth section survival rate data.
  • the prediction model generator 13 of FIG. 1 generates the N + 1th section survival prediction model using the score of the Nth section survival rate data, the Nth section survival prediction model, and the N + 1st section survival rate data. .
  • the method of generating a predictive model according to an embodiment of the present invention shown in FIGS. 2 and 3 may be written as a program that can be executed in a computer, and the general purpose of operating the program using a computer-readable recording medium. It can be implemented in a digital computer.
  • the computer-readable recording medium may include a storage medium such as a magnetic storage medium (eg, a ROM, a floppy disk, a hard disk, etc.) and an optical reading medium (eg, a CD-ROM, a DVD, etc.).
  • FIG. 4 is a view for explaining a prediction model according to an embodiment of the present invention.
  • the N-1 year survival rate prediction model PM_N-1 and the N year survival rate prediction model PM_N are illustrated.
  • the N-1 year survival rate prediction model PM_N-1 predicts the N-1 year survival rate P_N-1 from clinical data (X).
  • the N-1 year survival rate prediction model PM_N-1 is an input / output function capable of outputting the N-1 year survival rate P_N-1 when clinical data X is input.
  • the N-1 year survival rate prediction model PM_N-1 may be generated by machine learning techniques based on clinical data (X) and N-1 year survival rate (P_N-1) data for a plurality of patients.
  • the N-year survival rate prediction model PM_N may be generated based on the N-year survival rate prediction model PM_N-1.
  • the N year survival prediction model PM_N is generated based on the N-1 year prediction model PM_N-1 to generate a survival rate P_N from the clinical data X.
  • the N-year survival rate prediction model PM_N not only the N-1 year survival rate prediction model PM_N-1, but also the N-1 year survival rate P_N-1 is used.
  • the N-1 year survival rate (P_N-1) is the actual data for each patient case, it is used to generate the N-1 year survival rate prediction model (PM_N-1). Survival prediction models can be generated from year 1 to year 5.
  • the clinical data X input to each model may be first year clinical data, which are all initial values.
  • an annual survival rate prediction model may be generated using the annual clinical data and the annual survival rate (P) for a plurality of patients, and inputting the first year clinical data of any patient into the generated model, The annual survival rate of the patient can be predicted.
  • FIG. 5 is another example of a diagram for describing a prediction model according to an embodiment of the present invention.
  • the first year survival rate prediction model PM_1 and the subsequent N year year survival rate prediction model PM_N are illustrated.
  • the first-year survival rate prediction model PM_1 which is an input / output function capable of outputting the first-year survival rate P_1 when the clinical data X and the initial survival rate P_0 is inputted, is machine-learned. Is generated.
  • a second year survival rate prediction model (PM_2) which is an input / output function capable of outputting the second year survival rate (P_2), is generated by the machine learning technique.
  • the first year survival rate prediction model PM_1 is used to generate the second year survival rate prediction model PM_2.
  • the annual survival rate prediction model PM_N is generated by the machine learning technique.
  • the N-1 year survival rate prediction model PM_N-1 is used to generate the N year survival rate prediction model PM_N.
  • the N-year survival rate prediction model (PM_N) is generated by the machine learning method based on the input and output of the N-year survival rate prediction model (PM_N)
  • the N-1 year survival rate prediction model (PM_N ⁇ ) is used as an initial model. 1) can be used.
  • the first year survival rate prediction model PM_1 is used for the second year survival rate prediction model PM_2, and the second year survival rate prediction model PM_2 is the basis for generation of the third year survival rate prediction model PM_3.
  • the survival rate initial value P_0 may be set to [0, 1].
  • the first year survival rate P_1 may include values of two nodes, such as [1-p, p].
  • FIG. 6 is a graph illustrating a prediction model according to an embodiment of the present invention.
  • the vertical axis of the heatmaps shown in FIG. 6 is the serial number of the subject, and the vertical axis corresponds to the node.
  • the value corresponding to each node is represented by the intensity of the color.
  • graphs 611, 612, and 613 show a 1-year survival rate prediction model.
  • Graph 611 shows clinical data for a plurality of subjects at concentrations corresponding to each of 30 nodes, with initial values of survival expressed as 2 nodes.
  • Graph 613 shows the first year survival rate for a plurality of subjects as two nodes. That is, the 1-year survival prediction model converges a total of 32 node values (shown in graph 611) into a total of 2 node values (shown in graph 613).
  • the present invention is not limited thereto.
  • graphs 621, 622, and 623 show a second year survival rate prediction model.
  • the graph 621 shows clinical data for a plurality of subjects at concentrations corresponding to each of 30 nodes, and 1 year survival rate as 2 nodes.
  • Graph 623 shows the second year survival rate for two subjects as two nodes.
  • the second year survival prediction model converges a total of 32 node values (shown in graph 621) into a total of two node values (shown in graph 613).
  • the second year survival prediction model is generated by the first year survival prediction model, clinical data, the first year survival rate, and the second year survival rate.
  • graphs 651, 652, and 653 show a five-year survival rate prediction model.
  • Graph 651 shows clinical data for a plurality of subjects at concentrations corresponding to each of 30 nodes, with 4 year survival rates as 2 nodes.
  • Graph 653 shows five-year survival rates for two subjects as two nodes. In other words, the 5 year survival prediction model converges a total of 32 node values (shown in graph 651) into a total of 2 node values (shown in graph 653).
  • Embodiments of the present invention can be applied to a method, apparatus and computer program for generating a survival prediction model capable of predicting annual survival rate from medical data of a patient.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • General Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Primary Health Care (AREA)
  • Theoretical Computer Science (AREA)
  • Pure & Applied Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Strategic Management (AREA)
  • Evolutionary Biology (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Economics (AREA)
  • Algebra (AREA)
  • Child & Adolescent Psychology (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

An embodiment of the present invention provides a method for generating a survival rate prediction model comprising: a first step of generating a Nth interval survival rate prediction model using clinical data and Nth interval survival rate data of a subject providing the clinical data; and a second step of generating an (N+1)th interval survival rate prediction model using the Nth interval survival rate data, the Nth interval survival rate prediction model, and (N+1)th interval survival rate data.

Description

생존율 예측 모델 생성 방법, 장치 및 컴퓨터 프로그램Methods, devices, and computer programs for generating survival prediction models
본 발명의 실시예들은 생존율 예측 모델 생성 방법, 장치 및 컴퓨터 프로그램에 관한 것이다.Embodiments of the present invention relate to a method, apparatus and computer program for generating a survival prediction model.
암 5년 생존율은 암 5년 생존율은 의료기술의 효과와 의료체계의 성과를 드러내는 대표적인 지표이다. 암 5년 생존율은 암에 걸린 것으로 진단받고 치료를 시작한 암 환자가 최소한 5년 동안 발병한 암으로 사망하지 않을 확률을 의미한다. 5년 생존율이 높다는 것은 곧 암 치료가 상대적으로 순탄하게 잘 진행되고 있음을 나타내며 의료체계가 암과 같은 중증질환을 관리하기에 적합하다는 것을 보여준다고 할 수 있다.Five-year cancer survival rate is a representative indicator of the effectiveness of medical technology and the performance of the medical system. Cancer 5-year survival rate refers to the probability that a cancer patient diagnosed with cancer and started treatment will not die from cancer that has occurred for at least 5 years. The high five-year survival rate indicates that cancer treatment is progressing relatively smoothly, and that the medical system is suitable for managing severe diseases such as cancer.
OECD에서는 대장암, 자궁암, 유방암의 5년 생존율을 국제적으로 비교하고 있다. OECD의 암 생존율 통계는 계산방식의 차이로 인하여 국내의 암 생존율 통계와 일치하지 않는다. OECD 기준으로 볼 때 한국의 대장암 5년 생존율은 2008-2013년 기간에 70.9%로 OECD 주요 국가들 중에서 가장 높으며, 스웨덴(65.4%)이 그 다음으로 높다. 유방암 5년 생존율의 경우 한국은 85.9%로 OECD 국가들의 평균(84.9%)보다 조금 더 높은 수준이며 생존율이 가장 높은 스웨덴(89.4%)보다는 약 5% 포인트 정도 낮다.The OECD compares international 5-year survival rates for colorectal cancer, uterine cancer and breast cancer. OECD cancer survival statistics are inconsistent with domestic cancer survival statistics due to differences in calculations. On a OECD basis, Korea's five-year survival rate for colorectal cancer was 70.9% in 2008-2013, the highest among the major OECD countries, followed by Sweden (65.4%). The 5-year survival rate for breast cancer is 85.9% in Korea, slightly higher than the OECD average (84.9%) and about 5 percentage points lower than Sweden (89.4%), which has the highest survival rate.
본 발명의 실시예들은 환자의 의료 데이터로부터 연차별 생존율을 예측할 수 있는 생존율 예측 모델 생성 방법, 장치 및 컴퓨터 프로그램을 제공한다.Embodiments of the present invention provide a method, apparatus, and computer program for generating a survival prediction model capable of predicting annual survival rates from medical data of a patient.
본 발명의 일 실시예는 임상 데이터 및 상기 임상 데이터를 제공한 대상자의 N번째 구간 생존율 데이터를 이용하여 N번째 구간 생존율 예측 모델을 생성하는 제1 단계; 상기 N번째 구간 생존율 데이터, 상기 N번째 구간 생존율 예측 모델 및 N+1번째 구간 생존율 데이터를 이용하여 N+1번째 구간 생존율 예측 모델을 생성하는 제2 단계;를 포함하는 생존율 예측 모델 생성 방법을 개시한다.According to an embodiment of the present invention, a first step of generating an N-th section survival prediction model using clinical data and N-th section survival rate data of a subject who provided the clinical data; And a second step of generating an N + 1th interval survival prediction model using the Nth interval survival rate data, the Nth interval survival prediction model, and the N + 1st interval survival rate data. do.
상기 N번째 구간 생존율 데이터 각각에 대하여, 생존 기간에 따른 스코어를 부여하는 단계;를 더 포함하고, 상기 제2 단계는, 상기 N번째 구간 생존율 데이터 각각에 부여된 스코어를 이용하여 N+1년차 생존율 예측 모델을 생성하는 예후 예측 모델 생성 방법을 개시한다.And assigning a score according to the survival period to each of the N-th section survival rate data, wherein the second step comprises: N + 1 year survival rate by using a score assigned to each of the N-th section survival rate data A prognostic prediction model generation method for generating a prediction model is disclosed.
상기 스코어는 상기 생존 기간에 비례하는 예후 예측 모델 생성 방법을 개시한다.The score discloses a method for generating a prognostic prediction model that is proportional to the survival period.
상기 생존 기간은 적어도 월 단위로 구분되는 예후 예측 모델 생성 방법을 개시한다.The survival period discloses a method for generating a prognostic prediction model divided at least monthly.
상기 N+1번째 구간 생존율 예측 모델은 상기 임상 데이터 및 N번째 구간 생존율 데이터를 입력으로 하고 N+1번째 구간 생존율 데이터를 출력으로 하는 입출력함수인 예후 예측 모델 생성 방법을 개시한다.The N + 1 th section survival prediction model discloses a method for generating a prognostic prediction model, which is an input / output function for inputting the clinical data and the N th section survival rate data and outputting the N + 1 th section survival rate data.
상기 생성하는 단계는, RNN(Recurrent Neural Network) 알고리즘을 이용하는 예후 예측 모델 생성 방법을 개시한다.The generating step discloses a prognostic prediction model generation method using a Recurrent Neural Network (RNN) algorithm.
본 발명의 다른 실시예는 임상 데이터를 획득하는 임상 데이터 획득부; 생존율 데이터를 획득하는 생존율 데이터 획득부; 및 상기 임상 데이터 및 상기 임상 데이터를 제공한 대상자의 N번째 구간 생존율 데이터를 이용하여 N번째 구간 생존율 예측 모델을 생성하고, 상기 N번째 구간 생존율 데이터, 상기 N번째 구간 생존율 예측 모델 및 N+1번째 구간 생존율 데이터를 이용하여 N+1번째 구간 생존율 예측 모델을 생성하는 예측 모델 생성부;를 포함하는 생존율 예측 모델 생성 장치를 개시한다.Another embodiment of the present invention comprises a clinical data acquisition unit for obtaining clinical data; A survival rate data acquisition unit for obtaining survival rate data; And generating the N-th section survival rate prediction model using the clinical data and the N-th section survival rate data of the subject who provided the clinical data, and the N-th section survival rate data, the N-th section survival rate prediction model, and the N + 1st And a prediction model generator configured to generate an N + 1th interval survival prediction model using interval survival data.
상기 N번째 구간 생존율 데이터 각각에 대하여, 생존 기간에 따른 스코어를 부여하는 생존율 데이터 가공부;를 더 포함하고, 상기 예측 모델 생성부는, 상기 N번째 구간 생존율 데이터 각각에 부여된 스코어를 이용하여 N+1년차 생존율 예측 모델을 생성하는 예후 예측 모델 생성 장치를 개시한다.Survival data processing unit for giving a score according to the survival period for each of the N-th section survival rate data; further comprising, wherein the prediction model generator, N + using the scores assigned to each of the N-th section survival rate data Disclosed is a prognostic prediction model generating device for generating a 1 year survival prediction model.
상기 스코어는 상기 생존 기간에 비례하는 예후 예측 모델 생성 장치를 개시한다.The score discloses an apparatus for generating a prognostic prediction model that is proportional to the survival period.
상기 생존 기간은 적어도 월 단위로 구분되는 예후 예측 모델 생성 장치를 개시한다.The survival period discloses a prognostic prediction model generating device divided at least monthly.
상기 N+1번째 구간 생존율 예측 모델은 상기 임상 데이터 및 N번째 구간 생존율 데이터를 입력으로 하고 N+1번째 구간 생존율 데이터를 출력으로 하는 입출력함수인 예후 예측 모델 생성 장치를 개시한다.The N + 1th section survival rate prediction model discloses a prognostic prediction model generating device which is an input / output function for inputting the clinical data and the Nth section survival rate data and outputting the N + 1th section survival rate data.
상기 생성하는 단계는, RNN(Recurrent Neural Network) 알고리즘을 이용하는 예후 예측 모델 생성 장치를 개시한다.The generating step discloses a prognostic prediction model generation device using a Recurrent Neural Network (RNN) algorithm.
본 발명의 다른 실시예는 컴퓨터를 이용하여 전술한 예후 예측 모델 생성 방법을 실행하기 위하여 매체에 저장된 컴퓨터 프로그램을 개시한다.Another embodiment of the present invention discloses a computer program stored in a medium for executing the above-described prognostic prediction model generation method using a computer.
전술한 것 외의 다른 측면, 특징, 이점이 이하의 도면, 특허청구범위 및 발명의 상세한 설명으로부터 명확해질 것이다. Other aspects, features, and advantages other than those described above will become apparent from the following drawings, claims, and detailed description of the invention.
본 발명의 실시예들에 관한 생존율 예측 모델 생성 방법, 장치 및 컴퓨터 프로그램은 환자의 의료 데이터로부터 연차별 생존율을 예측할 수 있다.Survival prediction model generation method, apparatus and computer program according to embodiments of the present invention can predict the annual survival rate from the medical data of the patient.
본 발명의 실시예들에 관한 생존율 예측 모델 생성 방법, 장치 및 컴퓨터 프로그램은 전년도 환자의 생존율 데이터를 이용하여 금년도 생존율 예측 모델을 생성함으로써, 정확도가 높은 예측 모델을 생성한다.The method, apparatus and computer program for generating a survival prediction model according to embodiments of the present invention generate a prediction model with high accuracy by generating a survival prediction model this year using survival data of a previous year's patient.
본 발명의 실시예들에 관한 생존율 예측 모델 생성 방법, 장치 및 컴퓨터 프로그램은 전년도 환자의 생존율 데이터를 이용함에 있어서 랭킹화된 스코어를 부여함으로써, 많은 수의 유의미한 데이터를 확보할 수 있고, 이에 따라 정확도가 높은 예측 모델을 생성한다.Survival prediction model generation method, apparatus and computer program according to embodiments of the present invention can obtain a large number of significant data by assigning a ranked score in using the survival data of the previous year patient, and thus accuracy Produces a high prediction model.
도 1은 본 발명의 일 실시예에 따른 예측 모델 생성 장치의 구성을 개략적으로 도시한 것이다.1 schematically illustrates a configuration of an apparatus for generating a predictive model according to an embodiment of the present invention.
도 2는 본 발명의 일 실시예에 따른 예측 모델 생성 방법을 도시한 흐름도이다.2 is a flowchart illustrating a method of generating a prediction model according to an embodiment of the present invention.
도 3은 본 발명의 다른 실시예에 따른 예측 모델 생성 방법을 도시한 흐름도이다.3 is a flowchart illustrating a method of generating a prediction model according to another embodiment of the present invention.
도 4는 본 발명의 일 실시예에 따른 예측 모델을 설명하기 위한 도면이다.4 is a view for explaining a prediction model according to an embodiment of the present invention.
도 5는 본 발명의 일 실시예에 따른 예측 모델을 설명하기 위한 도면의 다른 예이다.5 is another example of a diagram for describing a prediction model according to an embodiment of the present invention.
도 6은 본 발명의 일 실시예에 따른 예측 모델을 설명하기 위한 그래프이다. 6 is a graph illustrating a prediction model according to an embodiment of the present invention.
본 발명은 다양한 변환을 가할 수 있고 여러 가지 실시예를 가질 수 있는 바, 특정 실시예들을 도면에 예시하고 상세한 설명에 상세하게 설명하고자 한다. 본 발명의 효과 및 특징, 그리고 그것들을 달성하는 방법은 도면과 함께 상세하게 후술되어 있는 실시예들을 참조하면 명확해질 것이다. 그러나 본 발명은 이하에서 개시되는 실시예들에 한정되는 것이 아니라 다양한 형태로 구현될 수 있다. As the invention allows for various changes and numerous embodiments, particular embodiments will be illustrated in the drawings and described in detail in the written description. Effects and features of the present invention, and methods of achieving them will be apparent with reference to the embodiments described below in detail together with the drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various forms.
이하, 첨부된 도면을 참조하여 본 발명의 실시예들을 상세히 설명하기로 하며, 도면을 참조하여 설명할 때 동일하거나 대응하는 구성 요소는 동일한 도면부호를 부여하고 이에 대한 중복되는 설명은 생략하기로 한다.Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, and the same or corresponding components will be denoted by the same reference numerals, and redundant description thereof will be omitted. .
이하의 실시예에서, 단수의 표현은 문맥상 명백하게 다르게 뜻하지 않는 한, 복수의 표현을 포함한다. 이하의 실시예에서, 포함하다 또는 가지다 등의 용어는 명세서상에 기재된 특징, 또는 구성요소가 존재함을 의미하는 것이고, 하나 이상의 다른 특징들 또는 구성요소가 부가될 가능성을 미리 배제하는 것은 아니다. In the following examples, the singular forms "a", "an" and "the" include plural forms unless the context clearly indicates otherwise. In the following examples, the terms including or having have meant that there is a feature or component described in the specification and does not preclude the possibility of adding one or more other features or components.
이하, 첨부된 도면들에 도시된 본 발명의 바람직한 실시예를 참조하여 본 발명을 보다 상세히 설명한다.Hereinafter, with reference to the preferred embodiment of the present invention shown in the accompanying drawings will be described in detail the present invention.
도 1은 본 발명의 일 실시예에 따른 예측 모델 생성 장치의 구성을 개략적으로 도시한 것이다.1 schematically illustrates a configuration of an apparatus for generating a predictive model according to an embodiment of the present invention.
도 1에 도시된 예측 모델 생성 장치(10)는 본 실시예의 특징이 흐려지는 것을 방지하기 위하여 본 실시예와 관련된 구성요소들만을 도시한 것이다. 따라서, 도 1에 도시된 구성요소들 외에 다른 범용적인 구성요소들이 더 포함될 수 있음을 본 실시예와 관련된 기술분야에서 통상의 지식을 가진 자라면 이해할 수 있다.The predictive model generating apparatus 10 shown in FIG. 1 shows only the components related to the present embodiment in order to prevent the features of the present embodiment from being blurred. Accordingly, it will be understood by those skilled in the art that other general purpose components may be further included in addition to the components shown in FIG. 1.
본 실시예에 따른 예측 모델 생성 장치(10)는 적어도 하나 이상의 프로세서(processor)에 해당하거나, 적어도 하나 이상의 프로세서를 포함할 수 있다. 이에 따라, 예측 모델 생성 장치(10)는 마이크로 프로세서나 범용 컴퓨터 시스템과 같은 다른 하드웨어 장치에 포함된 형태로 구동될 수 있다.The prediction model generating apparatus 10 according to the present embodiment may correspond to at least one processor or may include at least one processor. Accordingly, the predictive model generating device 10 may be driven in a form included in another hardware device such as a microprocessor or a general purpose computer system.
본 발명은 기능적인 블록 구성들 및 다양한 처리 단계들로 나타내어질 수 있다. 이러한 기능 블록들은 특정 기능들을 실행하는 다양한 개수의 하드웨어 또는/및 소프트웨어 구성들로 구현될 수 있다. 예를 들어, 본 발명은 하나 이상의 마이크로프로세서들의 제어 또는 다른 제어 장치들에 의해서 다양한 기능들을 실행할 수 있는, 메모리, 프로세싱, 로직(logic), 룩 업 테이블(look-up table) 등과 같은 직접 회로 구성들을 채용할 수 있다. 본 발명에의 구성 요소들이 소프트웨어 프로그래밍 또는 소프트웨어 요소들로 실행될 수 있는 것과 유사하게, 본 발명은 데이터 구조, 프로세스들, 루틴들 또는 다른 프로그래밍 구성들의 조합으로 구현되는 다양한 알고리즘을 포함하여, C, C++, 자바(Java), 어셈블러(assembler) 등과 같은 프로그래밍 또는 스크립팅 언어로 구현될 수 있다. 기능적인 측면들은 하나 이상의 프로세서들에서 실행되는 알고리즘으로 구현될 수 있다. 또한, 본 발명은 전자적인 환경 설정, 신호 처리, 및/또는 데이터 처리 등을 위하여 종래 기술을 채용할 수 있다. "매커니즘", "요소", "수단", "구성"과 같은 용어는 넓게 사용될 수 있으며, 본 발명의 구성요소들이 기계적이고 물리적인 구성들로서 한정되는 것은 아니다. 상기 용어는 프로세서 등과 연계하여 소프트웨어의 일련의 처리들(routines)의 의미를 포함할 수 있다.The invention can be represented by functional block configurations and various processing steps. Such functional blocks may be implemented in various numbers of hardware or / and software configurations that perform particular functions. For example, the present invention is an integrated circuit configuration such as memory, processing, logic, look-up table, etc., capable of executing various functions by the control of one or more microprocessors or other control devices. You can employ them. Similar to the components in the present invention may be implemented in software programming or software elements, the present invention includes various algorithms implemented in data structures, processes, routines or other combinations of programming constructs, including C, C ++ It may be implemented in a programming or scripting language such as Java, an assembler, or the like. The functional aspects may be implemented with an algorithm running on one or more processors. In addition, the present invention may employ the prior art for electronic environment setting, signal processing, and / or data processing. Terms such as "mechanism", "element", "means", "configuration" may be used widely, and the components of the present invention are not limited to mechanical and physical configurations. The term may include the meaning of a series of routines of software in conjunction with a processor or the like.
도 1을 참조하면, 예측 모델 생성 장치(10)는 임상 데이터 획득부(11), 생존율 데이터 획득부(12), 생존율 데이터 가공부(14) 및 예측 모델 생성부(13)를 포함한다.Referring to FIG. 1, the prediction model generating device 10 includes a clinical data acquisition unit 11, a survival rate data acquisition unit 12, a survival rate data processing unit 14, and a prediction model generation unit 13.
일 실시예에 따른 임상 데이터 획득부(11)는 환자의 의료 데이터, 예컨대 임상 데이터를 획득한다. 임상 데이터는 환자의 의료 영상으로부터 획득되거나, 환자의 검체 검사 결과로부터 획득될 수 있고, 이에 한정하지 않는다.According to an embodiment, the clinical data acquisition unit 11 acquires medical data of a patient, for example, clinical data. Clinical data may be obtained from a medical image of a patient or may be obtained from a patient's specimen test result, but is not limited thereto.
일 실시예에 따른 생존율 데이터 획득부(12)는 임상 데이터를 제공한 대상자(환자)의 생존율 데이터를 획득한다. 생존율 데이터는, 생존 여부를 나타내는 데이터이다. 생존율 데이터는 생존 여부만을 포함할 수도 있으나, 생존 기간에 대한 정보를 더 포함할 수 있다. The survival rate data acquisition unit 12 according to an embodiment acquires survival rate data of a subject (patient) who provided clinical data. Survival data is data showing survival or not. Survival data may include only survival, but may further include information about survival.
일 실시예에 따른 예측 모델 생성부(13)는 환자의 임상 데이터로부터 환자의 구간 별 생존율을 예측할 수 있는 생존율 예측 모델을 생성한다. 구간은 연(year)일 수 있다. 예를 들어, 예측 모델 생성부(13)는 위암 환자의 임상 데이터로부터 위암 환자의 연차 별 생존율을 예측하는 생존율 예측 모델을 생성할 수 있다. 상세히, 예측 모델 생성부(13)는 위암 환자의 첫 해 임상 데이터로부터, 위암 환자의 1년차부터 5년차까지의 연차 별 생존율을 예측할 수 있는 생존율 예측 모델을 생성할 수 있다. The prediction model generator 13 generates a survival prediction model that can predict the survival rate for each section of the patient from the clinical data of the patient. The interval may be a year. For example, the prediction model generator 13 may generate a survival prediction model that predicts annual survival rate of gastric cancer patients from clinical data of gastric cancer patients. In detail, the prediction model generator 13 may generate a survival prediction model that may predict annual survival rates of gastric cancer patients from 1 year to 5 years from the first year clinical data of gastric cancer patients.
일 실시예에 따른 예측 모델 생성부(13)는 머신러닝 기법을 이용하여, 환자들의 임상 데이터 및 실제 생존율 데이터를 기반으로 생존율 예측 모델을 생성할 수 있다. 일 실시예에 따른 예측 모델 생성부(13)는 머신러닝 기법 중에서도 딥 러닝 알고리즘을 사용할 수 있고, 그 중에서도 RNN(Recurrent Neural Network) 알고리즘을 사용할 수 있다. RNN 알고리즘은, 인공신경망을 구성하는 유닛 사이의 연결이 다이렉티드 싸이클(directed cycle)을 구성하는 신경망을 말한다. According to an embodiment, the prediction model generator 13 may generate a survival prediction model based on clinical data and actual survival data of patients using a machine learning technique. The prediction model generator 13 may use a deep learning algorithm among machine learning techniques, and among them, may use a recurrent neural network (RNN) algorithm. The RNN algorithm refers to a neural network in which a connection between units constituting an artificial neural network constitutes a directed cycle.
일 실시예에 따른 예측 모델 생성부(13)는 임상 데이터 및 상기 임상 데이터를 제공한 환자의 N번째 구간 생존율 데이터를 이용하여 N번째 구간 생존율 예측 모델을 생성한다. 예측 모델 생성부(13)는 임상 데이터 및 상기 임상 데이터를 제공한 환자의 N+1번째 구간 생존율 데이터를 이용하여, N+1번째 구간 생존율 예측 모델을 생성한다. 예측 모델 생성부(13)는 N+1번째 구간 생존율 예측 모델을 생성하기 위해 RNN 알고리즘을 이용하여 N번째 구간 생존율 예측 모델을 기반으로 할 수 있다. The prediction model generator 13 generates the N-th section survival prediction model using the clinical data and the N-th section survival rate data of the patient who provided the clinical data. The prediction model generator 13 generates the N + 1st section survival prediction model using the clinical data and the N + 1st section survival rate data of the patient who provided the clinical data. The prediction model generator 13 may be based on the Nth interval survival prediction model using the RNN algorithm to generate the N + 1th interval survival prediction model.
일 실시예에 따른 예측 모델 생성부(13)는 N+1번째 구간 생존율 예측 모델을 생성하기 위해 N번째 구간 생존율 데이터를 더 이용한다. 즉, N+1번째 구간 생존율 예측 모델은, 임상 데이터와 N번째 구간 생존율 데이터를 입력으로 하고 N+1번째 구간 생존율을 출력으로 하는 입출력함수일 수 있다. 이와 같이 N+1번째 구간 생존율 예측 모델의 입력 값으로 N번째 구간 생존율 데이터를 더 이용하게 되면, 정확도 높은 예측 모델을 생성할 수 있다. The prediction model generator 13 according to an embodiment further uses the N-th section survival rate data to generate the N + 1-th section survival rate prediction model. That is, the N + 1th section survival rate prediction model may be an input / output function that inputs clinical data and Nth section survival rate data and outputs N + 1th section survival rate. As such, when the N-th section survival rate data is further used as an input value of the N + 1 th section survival prediction model, an accurate prediction model may be generated.
일 실시예에 따른 예측 모델 생성부(13)가 N번째 구간 생존율 데이터를 이용하여 N번째 구간 생존율 예측 모델을 생성하는 것과 관련하여, N이 2 이상인 경우 전술한 N+1번째 구간 생존율 예측 모델 생성 방법이 동일하게 적용된다. 예를 들어, N이 2 이상인 경우 예측 모델 생성부(13)는 N번째 구간 생존율 예측 모델을 생성하기 위해 RNN 알고리즘을 이용하여 N-1번째 구간 생존율 예측 모델을 기반으로 할 수 있고, N-1번째 구간 생존율 데이터를 더 이용할 수 있다. In relation to generating the N-th section survival prediction model using the N-th section survival rate data, the prediction model generator 13 according to an embodiment generates the aforementioned N + 1-th section survival prediction model when N is 2 or more. The method applies equally. For example, when N is 2 or more, the prediction model generator 13 may be based on the N-1th interval survival prediction model using the RNN algorithm to generate the Nth interval survival prediction model, and N-1 Second interval survival data may be further used.
한편, N이 1인 경우 예측 모델 생성부(13)는 N-1번째 구간 생존율 예측 모델을 이용하지 않으며, 임상 데이터 및 상기 임상 데이터를 제공한 환자의 N번째 구간 생존율 데이터를 이용하여 N번째 구간 생존율 예측 모델을 생성하고, 기설정된 생존율 초기값(P_0)을 더 이용할 수 있다. 이와 관련한 상세한 내용은 도 5를 참조하여 후술한다.On the other hand, when N is 1, the prediction model generator 13 does not use the N-1th section survival rate prediction model, and uses the clinical data and the Nth section survival rate data of the patient who provided the clinical data. A survival prediction model may be generated, and a predetermined initial survival rate P_0 may be further used. Details related to this will be described later with reference to FIG. 5.
일 실시예에 따른 예측 모델 생성부(13)는 N번째 구간 생존율 데이터를 이용함에 있어, 가공된 상태의 데이터를 이용할 수 있다.The prediction model generator 13 may use the processed data in using the N-th section survival rate data.
일 실시예에 따른 생존율 데이터 가공부(14)는 생존율 데이터를 가공한다. 예를 들어, 생존율 데이터 각각에 대하여 생존 기간에 따른 스코어를 부여한다. 예측 모델 생성부(13)는 N번째 구간 생존율 데이터 각각에 부여된 스코어를 이용하여 N+1년차 생존율 예측 모델을 생성한다. 일 실시예에 따른 생존율 데이터 가공부(14)는 생존 기간에 비례하여 생존율 데이터에 스코어를 부여할 수 있다. 생존 기간은 적어도 월 단위로 구분될 수 있다. 이에 따르면, 사망한 환자의 생존율이 0으로 카운트되지 않고 생존 기간 만큼의 랭킹화된 스코어가 부여됨으로써, 모델 생성에 사용되는 유의미한 데이터 수를 늘릴 수 있고, 결과적으로 정확도 높은 모델의 생성에 기여하게 된다.The survival rate data processor 14 according to an embodiment processes the survival rate data. For example, each survival data is scored over survival. The prediction model generator 13 generates a N + 1 year survival prediction model using scores assigned to each of the N-th section survival data. The survival rate data processing unit 14 may assign a score to the survival rate data in proportion to the survival period. Survival periods may be divided at least monthly. According to this, the survival rate of the deceased patient is not counted as 0, but the ranked score is given as much as the survival period, thereby increasing the number of significant data used to generate the model, and consequently contributing to the generation of a highly accurate model. .
일 실시예에 따른 예측 모델 생성부(13)는 구간 별로, 예컨대 연차별로 생존율 예측 모델을 생성된다. 예를 들어, 암 환자의 생존율을 예측하는 모델의 경우, 1년차 생존율 예측 모델, 2년차 생존율 예측 모델, 3년차 생존율 예측 모델, 4년차 생존율 예측 모델 및 5년차 생존율 예측 모델이 생성될 수 있다. 각 연차 별 모델은, 환자의 임상 데이터로부터 환자의 해당 연차 생존율을 예측한다. The prediction model generator 13 generates a survival rate prediction model for each section, for example, annually. For example, in the case of a model for predicting the survival rate of a cancer patient, a 1 year survival prediction model, a 2 year survival prediction model, a 3 year survival prediction model, a 4 year survival prediction model and a 5 year survival prediction model may be generated. Each annual model predicts the patient's corresponding annual survival rate from the patient's clinical data.
각 연차 별 모델은, 환자의 임상 데이터에 해당하는 i개의 노드를 2개의 생존율 노드로 연결시키는 복수 레이어의 매트릭스를 포함할 수 있다. 일 실시예에 따른 예측 모델 생성부(13)에 의해 생성되는 각 연차 별 모델은, 환자의 임상 데이터에 해당하는 i개의 노드 및 전년차 생존율에 해당하는 2개의 노드를 2개의 생존율 노드로 연결시키는 복수 레이어의 매트릭스, 즉 i+2개의 입력 노드를 2개 출력 노드로 연결시키는 복수 레이어의 매트릭스를 포함할 수 있다. Each annual model may include a multi-layered matrix that connects i nodes corresponding to clinical data of the patient to two survival nodes. Each annual model generated by the predictive model generator 13 according to an embodiment may connect two nodes corresponding to i nodes corresponding to clinical data of a patient and two nodes corresponding to a previous year survival rate to two survival rate nodes. It may include a matrix of multiple layers, that is, a matrix of multiple layers connecting i + 2 input nodes to two output nodes.
입력 노드에는 전년도 생존율 데이터에 해당하는 노드가 포함된다. 전년도 생존율 데이터 노드는 2개일 수 있고, 각각 생존노드와 사망노드일 수 있다. 생존율 데이터에 해당하는 2개 노드가 [생존노드, 사망노드]인 경우에는, 생존율 데이터는 환자가 사망한 경우 [0, 1] 또는 환자가 생존한 경우 [1, 0]일 수 있다. The input node contains nodes corresponding to previous year's survival rate data. The previous year's survival rate data nodes may be two, each of which may be a survival node and a death node. When the two nodes corresponding to the survival rate data are [survival node and death node], the survival rate data may be [0, 1] when the patient dies or [1, 0] when the patient survives.
다만 본 발명의 일 실시예에 따르면, 환자가 사망한 경우의 생존율 데이터를 [0, 1]로 처리하지 않고, 랭킹화하여 스코어를 부여할 수 있는 처리 방법이 제안된다. 본 실시예에서 사망한 환자의 생존율 데이터는 [p, 1-p]일 수 있고, 여기서 p에는 0이 아닌 스코어 값이 부여된다. 일 예에 따르면, 스코어는 사망한 환자의 생존 기간에 비례하도록 부여될 수 있다. 여기서 생존 기간은, 적어도 월 단위로 구분될 수 있다. 예컨대, N년차에 3개월 생존한 환자의 경우 N년차 생존율 스코어는 3/12이고, 생존율 데이터는 [3/12, 1-3/12]=[0.25, 0.75]일 수 있다. 다음의 표 1은 N년차 생존 기간 별 N년차 생존율 스코어의 예이다.However, according to one embodiment of the present invention, a treatment method capable of giving a score by ranking it is proposed without treating the survival rate data when the patient dies with [0, 1]. Survival data of patients who died in this example may be [p, 1-p], where p is assigned a non-zero score value. According to one example, the score may be given in proportion to the survival of the deceased patient. In this case, the survival period may be divided into at least monthly units. For example, for patients who survived for 3 months at N years, the N year survival score may be 3/12, and the survival data may be [3/12, 1-3 / 12] = [0.25, 0.75]. Table 1 below is an example of N-year survival rate scores by N-year survival period.
생존기간(month)Survival 스코어Score
1One 1/12=0.081/12 = 0.08
22 2/12=0.172/12 = 0.17
33 3/12=0.253/12 = 0.25
44 4/12=0.334/12 = 0.33
55 5/12=0.425/12 = 0.42
66 6/12=0.56/12 = 0.5
77 7/12=0.587/12 = 0.58
88 8/12=0.678/12 = 0.67
99 9/12=0.759/12 = 0.75
1010 10/12=0.8310/12 = 0.83
1111 11/12=0.9211/12 = 0.92
1212 12/12=112/12 = 1
표 1에서는 생존기간이 월 단위로 구분된 예를 설명하였으나, 본 발명은 이에 한정하지 않으며, 설계에 따라 반기, 분기, 월, 일 등 다양한 단위로 생존기간의 구분이 가능하다.Table 1 described an example in which survival periods are divided into monthly units, but the present invention is not limited thereto, and the survival periods may be divided into various units such as semi-annual, quarterly, monthly, and day depending on the design.
도 2는 본 발명의 일 실시예에 따른 예측 모델 생성 방법을 도시한 흐름도이다.2 is a flowchart illustrating a method of generating a prediction model according to an embodiment of the present invention.
도 2를 참조하면, 단계 21에서 도 1의 예측 모델 생성부(13)는 환자의 임상 데이터 및 N번째 구간 생존율 데이터를 이용하여 N번째 구간 생존율 예측 모델을 생성한다.Referring to FIG. 2, in step 21, the prediction model generator 13 of FIG. 1 generates the N-th section survival prediction model using the clinical data of the patient and the N-th section survival rate data.
단계 22에서 도 1의 예측 모델 생성부(13)는 N번째 구간 생존율 데이터, N번째 구간 생존율 예측 모델 및 N+1번째 구간 생존율 데이터를 이용하여 N+1번째 구간 생존율 예측 모델을 생성한다.In operation 22, the prediction model generator 13 of FIG. 1 generates the N + 1th section survival prediction model using the Nth section survival rate data, the Nth section survival rate prediction model, and the N + 1st section survival rate data.
도 3은 본 발명의 다른 실시예에 따른 예측 모델 생성 방법을 도시한 흐름도이다.3 is a flowchart illustrating a method of generating a prediction model according to another embodiment of the present invention.
도 3을 참조하면, 단계 31에서 도 1의 예측 모델 생성부(13)는 환자의 임상 데이터 및 N번째 구간 생존율 데이터를 이용하여 N번째 구간 생존율 예측 모델을 생성한다.Referring to FIG. 3, in step 31, the prediction model generator 13 of FIG. 1 generates the N-th section survival prediction model using the clinical data of the patient and the N-th section survival rate data.
단계 32에서 도 1의 생존율 데이터 가공부(14)는 N번째 구간 생존율 데이터에 생존 기간에 따른 스코어를 부여한다.In step 32, the survival rate data processing unit 14 of FIG. 1 assigns a score according to the survival period to the Nth section survival rate data.
단계 33에서 도 1의 예측 모델 생성부(13)는 N번째 구간 생존율 데이터의 스코어, N번째 구간 생존율 예측 모델 및 N+1번째 구간 생존율 데이터를 이용하여 N+1번째 구간 생존율 예측 모델을 생성한다.In operation 33, the prediction model generator 13 of FIG. 1 generates the N + 1th section survival prediction model using the score of the Nth section survival rate data, the Nth section survival prediction model, and the N + 1st section survival rate data. .
한편, 도 2 및 도 3에 도시된 흐름도는, 도 1에 도시된 예측 모델 생성 장치(10)에서 시계열적으로 처리되는 단계들로 구성된다. 따라서, 이하에서 생략된 내용이라 하더라도, 도 1에서 도시된 구성들에 관하여 이상에서 기술된 내용은 도 2 및 도 3에 도시된 흐름도에도 적용됨을 알 수 있다.On the other hand, the flow chart shown in Figures 2 and 3 is composed of steps that are processed in time series in the predictive model generating device 10 shown in FIG. Therefore, even if omitted below, it can be seen that the above description of the components shown in FIG. 1 also applies to the flowcharts shown in FIGS. 2 and 3.
한편, 도 2 및 도 3에 도시된 본 발명의 일 실시예에 따른 예측 모델 생성 방법은 컴퓨터에서 실행될 수 있는 프로그램으로 작성 가능하고, 컴퓨터로 읽을 수 있는 기록매체를 이용하여 상기 프로그램을 동작시키는 범용 디지털 컴퓨터에서 구현될 수 있다. 상기 컴퓨터로 읽을 수 있는 기록매체는 마그네틱 저장매체(예를 들면, 롬, 플로피 디스크, 하드 디스크 등), 광학적 판독 매체(예를 들면, 시디롬, 디브이디 등)와 같은 저장매체를 포함한다.Meanwhile, the method of generating a predictive model according to an embodiment of the present invention shown in FIGS. 2 and 3 may be written as a program that can be executed in a computer, and the general purpose of operating the program using a computer-readable recording medium. It can be implemented in a digital computer. The computer-readable recording medium may include a storage medium such as a magnetic storage medium (eg, a ROM, a floppy disk, a hard disk, etc.) and an optical reading medium (eg, a CD-ROM, a DVD, etc.).
도 4는 본 발명의 일 실시예에 따른 예측 모델을 설명하기 위한 도면이다.4 is a view for explaining a prediction model according to an embodiment of the present invention.
도 4를 참조하면, N-1년차 생존율 예측 모델(PM_N-1)과 N년차 생존율 예측 모델(PM_N)이 도시되었다. 도 4를 참조하면, N-1년차 생존율 예측 모델(PM_N-1)은 임상 데이터(X)로부터 N-1년차 생존율(P_N-1)을 예측한다. 예를 들어, N-1년차 생존율 예측 모델(PM_N-1)은 임상 데이터(X)를 입력하였을 때 N-1년차 생존율(P_N-1)을 출력할 수 있는 입출력함수이다. N-1년차 생존율 예측 모델(PM_N-1)은 복수의 환자에 대한 임상 데이터(X) 및 N-1년차 생존율(P_N-1) 데이터에 기초하여 머신러닝 기법에 의해 생성될 수 있다. 한편, N-1년차 생존율 예측 모델(PM_N-1)을 기반으로 하여 N년차 생존율 예측 모델(PM_N)이 생성될 수 있다. Referring to FIG. 4, the N-1 year survival rate prediction model PM_N-1 and the N year survival rate prediction model PM_N are illustrated. Referring to FIG. 4, the N-1 year survival rate prediction model PM_N-1 predicts the N-1 year survival rate P_N-1 from clinical data (X). For example, the N-1 year survival rate prediction model PM_N-1 is an input / output function capable of outputting the N-1 year survival rate P_N-1 when clinical data X is input. The N-1 year survival rate prediction model PM_N-1 may be generated by machine learning techniques based on clinical data (X) and N-1 year survival rate (P_N-1) data for a plurality of patients. Meanwhile, the N-year survival rate prediction model PM_N may be generated based on the N-year survival rate prediction model PM_N-1.
도 4를 참조하면, N년차 생존율 예측 모델(PM_N)은 N-1년차 예측 모델(PM_N-1)을 기반으로 하여, 임상 데이터(X)로부터 생존율(P_N)을 예측할 수 있도록 생성된다. 본 발명의 일 실시예에 따르면, N년차 생존율 예측 모델(PM_N)을 생성함에 있어, N-1년차 생존율 예측 모델(PM_N-1)뿐 아니라, N-1년차 생존율(P_N-1)이 이용된다. 한편, N-1년차 생존율(P_N-1)은 각 환자의 케이스에 대한 실제 데이터로써, N-1년차 생존율 예측 모델(PM_N-1)을 생성하는 데에 이용된다. 생존율 예측 모델은 1년차부터 5년차까지 생성될 수 있다. Referring to FIG. 4, the N year survival prediction model PM_N is generated based on the N-1 year prediction model PM_N-1 to generate a survival rate P_N from the clinical data X. Referring to FIG. According to an embodiment of the present invention, in generating the N-year survival rate prediction model PM_N, not only the N-1 year survival rate prediction model PM_N-1, but also the N-1 year survival rate P_N-1 is used. . On the other hand, the N-1 year survival rate (P_N-1) is the actual data for each patient case, it is used to generate the N-1 year survival rate prediction model (PM_N-1). Survival prediction models can be generated from year 1 to year 5.
도 4에서 각 모델의 입력이 되는 임상 데이터(X)는 모두 초기값인 1년차 임상 데이터일 수 있다. 이에 따르면, 복수의 환자에 대한 1년차 임상 데이터 및 연차별 생존율(P)을 이용하여, 연차별 생존율 예측 모델을 생성할 수 있고, 생성된 모델에 임의의 환자의 1년차 임상 데이터를 입력하면, 해당 환자의 연차별 생존율(P)을 예측 수 있게 된다.In FIG. 4, the clinical data X input to each model may be first year clinical data, which are all initial values. According to this, an annual survival rate prediction model may be generated using the annual clinical data and the annual survival rate (P) for a plurality of patients, and inputting the first year clinical data of any patient into the generated model, The annual survival rate of the patient can be predicted.
도 5는 본 발명의 일 실시예에 따른 예측 모델을 설명하기 위한 도면의 다른 예이다.5 is another example of a diagram for describing a prediction model according to an embodiment of the present invention.
도 5를 참조하면, 1년차 생존율 예측 모델(PM_1)과, 그 이후의 N년차 생존율 예측 모델(PM_N)이 도시되었다. 도 4를 참조하면, 임상 데이터(X) 및 생존율 초기값(P_0)을 입력하였을 때 1년차 생존율(P_1)을 출력할 수 있는 입출력함수인 1년차 생존율 예측 모델(PM_1)이 머신러닝 기법에 의해 생성된다. 다음으로, 임상 데이터(X) 및 1년차 생존율(P_1)을 입력하였을 때 2년차 생존율(P_2)을 출력할 수 있는 입출력함수인 2년차 생존율 예측 모델(PM_2)이 머신러닝 기법에 의해 생성된다. 이 때 1년차 생존율 예측 모델(PM_1)이 2년차 생존율 예측 모델(PM_2) 생성에 이용된다. 이와 같은 과정이 반복됨에 따라(N=N+1), 임상 데이터(X) 및 N-1년차 생존율(P_N-1)을 입력하였을 때 N년차 생존율(P_N)을 출력할 수 있는 입출력함수인 N년차 생존율 예측 모델(PM_N)이 머신러닝 기법에 의해 생성된다. N-1년차 생존율 예측 모델(PM_N-1)은 N년차 생존율 예측 모델(PM_N)의 생성에 이용된다. 예를 들어, N년차 생존율 예측 모델(PM_N)의 입력과 출력을 기반으로 머신 러닝 기법에 의해 N년차 생존율 예측 모델(PM_N)을 생성할 때, 초기모델로 N-1년차 생존율 예측 모델(PM_N-1)을 사용할 수 있다. 1년차 생존율 예측 모델(PM_1)은 2년차 생존율 예측 모델(PM_2)에 이용되고, 2년차 생존율 예측 모델(PM_2)은 3년차 생존율 예측 모델(PM_3) 생성의 기반이 된다. Referring to FIG. 5, the first year survival rate prediction model PM_1 and the subsequent N year year survival rate prediction model PM_N are illustrated. Referring to FIG. 4, the first-year survival rate prediction model PM_1, which is an input / output function capable of outputting the first-year survival rate P_1 when the clinical data X and the initial survival rate P_0 is inputted, is machine-learned. Is generated. Next, when the clinical data (X) and the first year survival rate (P_1) are input, a second year survival rate prediction model (PM_2), which is an input / output function capable of outputting the second year survival rate (P_2), is generated by the machine learning technique. At this time, the first year survival rate prediction model PM_1 is used to generate the second year survival rate prediction model PM_2. As this process is repeated (N = N + 1), when the clinical data (X) and the N-1 year survival rate (P_N-1) are input, N, the input / output function that can output the N year survival rate (P_N) The annual survival rate prediction model PM_N is generated by the machine learning technique. The N-1 year survival rate prediction model PM_N-1 is used to generate the N year survival rate prediction model PM_N. For example, when the N-year survival rate prediction model (PM_N) is generated by the machine learning method based on the input and output of the N-year survival rate prediction model (PM_N), the N-1 year survival rate prediction model (PM_N−) is used as an initial model. 1) can be used. The first year survival rate prediction model PM_1 is used for the second year survival rate prediction model PM_2, and the second year survival rate prediction model PM_2 is the basis for generation of the third year survival rate prediction model PM_3.
생존율 초기값(P_0)은 [0, 1]로 설정될 수 있다. 1년차 생존율(P_1)은 [1-p, p]와 같이 2개 노드의 값을 포함할 수 있다.The survival rate initial value P_0 may be set to [0, 1]. The first year survival rate P_1 may include values of two nodes, such as [1-p, p].
도 6은 본 발명의 일 실시예에 따른 예측 모델을 설명하기 위한 그래프이다. 6 is a graph illustrating a prediction model according to an embodiment of the present invention.
도 6에 도시된 히트맵(heatmap)들의 세로축은 대상자의 일련번호이고, 세로축은 노드에 해당한다. 각 노드에 해당하는 값은 색상의 농도로 표시되었다. 도 6을 참고하면, 그래프(611, 612, 613)는 1년차 생존율 예측 모델을 보여준다. 그래프(611)는 복수의 대상자들에 대한 임상 데이터가 각 30개 노드에 해당하는 농도로 표시되었고, 여기에 생존율의 초기값이 2개 노드로 표시되었다. 그래프(613)는 복수의 대상자들에 대한 1년차 생존율이 2개 노드로 표시되었다. 즉, 1년차 생존율 예측 모델은 총 32개의 노드값(그래프 611에 도시)을 총 2개의 노드값(그래프 613에 도시)으로 수렴시킨다. 다만, 구체적인 노드의 개수는 예시에 불과하므로, 본 발명이 이에 한정되지 않는다.The vertical axis of the heatmaps shown in FIG. 6 is the serial number of the subject, and the vertical axis corresponds to the node. The value corresponding to each node is represented by the intensity of the color. Referring to FIG. 6, graphs 611, 612, and 613 show a 1-year survival rate prediction model. Graph 611 shows clinical data for a plurality of subjects at concentrations corresponding to each of 30 nodes, with initial values of survival expressed as 2 nodes. Graph 613 shows the first year survival rate for a plurality of subjects as two nodes. That is, the 1-year survival prediction model converges a total of 32 node values (shown in graph 611) into a total of 2 node values (shown in graph 613). However, since the number of specific nodes is only an example, the present invention is not limited thereto.
마찬가지로, 그래프(621, 622, 623)는 2년차 생존율 예측 모델을 보여준다. 그래프(621)는 복수의 대상자들에 대한 임상 데이터가 각 30개 노드에 해당하는 농도로 표시되었고, 1년차 생존율이 2개 노드로 표시되었다. 그래프(623)는 복수의 대상자들에 대한 2년차 생존율이 2개 노드로 표시되었다. 즉, 2년차 생존율 예측 모델은 총 32개의 노드값(그래프 621에 도시)을 총 2개의 노드값(그래프 613에 도시)으로 수렴시킨다. 2년차 생존율 예측 모델은 1년차 생존율 예측 모델, 임상 데이터, 1년차 생존율, 2년차 생존율에 의해 생성된다.Similarly, graphs 621, 622, and 623 show a second year survival rate prediction model. The graph 621 shows clinical data for a plurality of subjects at concentrations corresponding to each of 30 nodes, and 1 year survival rate as 2 nodes. Graph 623 shows the second year survival rate for two subjects as two nodes. In other words, the second year survival prediction model converges a total of 32 node values (shown in graph 621) into a total of two node values (shown in graph 613). The second year survival prediction model is generated by the first year survival prediction model, clinical data, the first year survival rate, and the second year survival rate.
마찬가지로, 그래프(651, 652, 653)는 5년차 생존율 예측 모델을 보여준다. 그래프(651)는 복수의 대상자들에 대한 임상 데이터가 각 30개 노드에 해당하는 농도로 표시되었고, 4년차 생존율이 2개 노드로 표시되었다. 그래프(653)는 복수의 대상자들에 대한 5년차 생존율이 2개 노드로 표시되었다. 즉, 5년차 생존율 예측 모델은 총 32개의 노드값(그래프 651에 도시)을 총 2개의 노드값(그래프 653에 도시)으로 수렴시킨다.Similarly, graphs 651, 652, and 653 show a five-year survival rate prediction model. Graph 651 shows clinical data for a plurality of subjects at concentrations corresponding to each of 30 nodes, with 4 year survival rates as 2 nodes. Graph 653 shows five-year survival rates for two subjects as two nodes. In other words, the 5 year survival prediction model converges a total of 32 node values (shown in graph 651) into a total of 2 node values (shown in graph 653).
이제까지 본 발명에 대하여 그 바람직한 실시예들을 중심으로 살펴보았다. 본 발명은 도면에 도시된 실시예를 참고로 설명되었으나 이는 예시적인 것에 불과하며, 본 발명이 속하는 기술 분야에서 통상의 지식을 가진 자라면 본 발명이 본 발명의 본질적인 특성에서 벗어나지 않는 범위에서 변형된 형태로 구현될 수 있으며, 균등한 다른 실시 예가 가능함을 이해할 수 있을 것이다. 그러므로 개시된 실시예들은 한정적인 관점이 아니라 설명적인 관점에서 고려되어야 한다. 본 발명의 범위는 전술한 설명이 아니라 특허청구범위에 나타나 있으며, 그와 동등한 범위 내에 있는 모든 차이점은 본 발명에 포함된 것으로 해석되어야 할 것이다.So far I looked at the center of the preferred embodiment for the present invention. Although the present invention has been described with reference to the embodiments illustrated in the drawings, this is merely exemplary, and a person skilled in the art to which the present invention pertains may modify the present invention without departing from the essential characteristics of the present invention. It may be implemented in the form, it will be understood that other equivalent embodiments are possible. Therefore, the disclosed embodiments should be considered in descriptive sense only and not for purposes of limitation. The scope of the present invention is shown in the claims rather than the foregoing description, and all differences within the scope will be construed as being included in the present invention.
본 발명의 실시예들은 환자의 의료 데이터로부터 연차별 생존율을 예측할 수 있는 생존율 예측 모델 생성 방법, 장치 및 컴퓨터 프로그램에 적용될 수 있다.Embodiments of the present invention can be applied to a method, apparatus and computer program for generating a survival prediction model capable of predicting annual survival rate from medical data of a patient.
이상에서는 본 발명의 예시적인 실시예들을 참조하여 설명하였지만, 해당 기술 분야에서 통상의 지식을 가진 자라면 하기의 특허 청구의 범위에 기재된 본 발명의 사상 및 영역으로부터 벗어나지 않는 범위 내에서 본 발명을 다양하게 수정 및 변경시킬 수 있음을 이해할 수 있을 것이다.Although the above has been described with reference to exemplary embodiments of the present invention, those skilled in the art may vary the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. It will be understood that modifications and changes can be made.

Claims (13)

  1. 임상 데이터 및 상기 임상 데이터를 제공한 대상자의 N번째 구간 생존율 데이터를 이용하여 N번째 구간 생존율 예측 모델을 생성하는 제1 단계;A first step of generating an N-th section survival prediction model using clinical data and N-th section survival rate data of the subject who provided the clinical data;
    상기 N번째 구간 생존율 데이터, 상기 N번째 구간 생존율 예측 모델 및 N+1번째 구간 생존율 데이터를 이용하여 N+1번째 구간 생존율 예측 모델을 생성하는 제2 단계;를 포함하는 A second step of generating an N + 1th interval survival prediction model using the Nth interval survival rate data, the Nth interval survival prediction model, and the N + 1th interval survival rate data;
    생존율 예측 모델 생성 방법.How to generate a survival prediction model.
  2. 제1 항에 있어서,According to claim 1,
    상기 N번째 구간 생존율 데이터 각각에 대하여, 생존 기간에 따른 스코어를 부여하는 단계;를 더 포함하고,For each of the N-th section survival rate data, assigning a score according to the survival period;
    상기 제2 단계는, 상기 N번째 구간 생존율 데이터 각각에 부여된 스코어를 이용하여 N+1년차 생존율 예측 모델을 생성하는In the second step, the N + 1 year survival rate prediction model is generated using the scores assigned to each of the Nth interval survival rate data.
    예후 예측 모델 생성 방법.How to create a prognostic prediction model.
  3. 제2 항에 있어서,The method of claim 2,
    상기 스코어는 상기 생존 기간에 비례하는The score is proportional to the survival
    예후 예측 모델 생성 방법.How to create a prognostic prediction model.
  4. 제2 항에 있어서,The method of claim 2,
    상기 생존 기간은 적어도 월 단위로 구분되는 The survival period is divided at least monthly
    예후 예측 모델 생성 방법.How to create a prognostic prediction model.
  5. 제1 항에 있어서,According to claim 1,
    상기 N+1번째 구간 생존율 예측 모델은 상기 임상 데이터 및 N번째 구간 생존율 데이터를 입력으로 하고 N+1번째 구간 생존율 데이터를 출력으로 하는 입출력함수인The N + 1th section survival rate prediction model is an input / output function that inputs the clinical data and the Nth section survival rate data and outputs the N + 1th section survival rate data.
    예후 예측 모델 생성 방법.How to create a prognostic prediction model.
  6. 제1 항에 있어서,According to claim 1,
    상기 생성하는 단계는, RNN(Recurrent Neural Network) 알고리즘을 이용하는The generating step using a Recurrent Neural Network (RNN) algorithm
    예후 예측 모델 생성 방법.How to create a prognostic prediction model.
  7. 임상 데이터를 획득하는 임상 데이터 획득부;Clinical data acquisition unit for acquiring clinical data;
    생존율 데이터를 획득하는 생존율 데이터 획득부; 및A survival rate data acquisition unit for obtaining survival rate data; And
    상기 임상 데이터 및 상기 임상 데이터를 제공한 대상자의 N번째 구간 생존율 데이터를 이용하여 N번째 구간 생존율 예측 모델을 생성하고, 상기 N번째 구간 생존율 데이터, 상기 N번째 구간 생존율 예측 모델 및 N+1번째 구간 생존율 데이터를 이용하여 N+1번째 구간 생존율 예측 모델을 생성하는 예측 모델 생성부;를 포함하는The Nth section survival rate prediction model is generated using the clinical data and the Nth section survival rate data of the subject who provided the clinical data, and the Nth section survival rate data, the Nth section survival rate prediction model, and the N + 1st section A prediction model generator configured to generate an N + 1th interval survival prediction model using survival data;
    생존율 예측 모델 생성 장치.Survival prediction model generation device.
  8. 제7 항에 있어서,The method of claim 7, wherein
    상기 N번째 구간 생존율 데이터 각각에 대하여, 생존 기간에 따른 스코어를 부여하는 생존율 데이터 가공부;를 더 포함하고,And a survival rate data processing unit for giving a score according to the survival period for each of the N-th section survival rate data.
    상기 예측 모델 생성부는, 상기 N번째 구간 생존율 데이터 각각에 부여된 스코어를 이용하여 N+1년차 생존율 예측 모델을 생성하는The prediction model generator generates an N + 1 year survival prediction model using scores assigned to each of the Nth interval survival data.
    예후 예측 모델 생성 장치.Prognostic prediction model generator.
  9. 제8 항에 있어서,The method of claim 8,
    상기 스코어는 상기 생존 기간에 비례하는The score is proportional to the survival
    예후 예측 모델 생성 장치.Prognostic prediction model generator.
  10. 제8 항에 있어서,The method of claim 8,
    상기 생존 기간은 적어도 월 단위로 구분되는 The survival period is divided at least monthly
    예후 예측 모델 생성 장치.Prognostic prediction model generator.
  11. 제7 항에 있어서,The method of claim 7, wherein
    상기 N+1번째 구간 생존율 예측 모델은 상기 임상 데이터 및 N번째 구간 생존율 데이터를 입력으로 하고 N+1번째 구간 생존율 데이터를 출력으로 하는 입출력함수인The N + 1th section survival rate prediction model is an input / output function that inputs the clinical data and the Nth section survival rate data and outputs the N + 1th section survival rate data.
    예후 예측 모델 생성 장치.Prognostic prediction model generator.
  12. 제7 항에 있어서,The method of claim 7, wherein
    상기 생성하는 단계는, RNN(Recurrent Neural Network) 알고리즘을 이용하는The generating step using a Recurrent Neural Network (RNN) algorithm
    예후 예측 모델 생성 장치.Prognostic prediction model generator.
  13. 컴퓨터를 이용하여 제1항 내지 제6항 중 어느 한 항의 방법을 실행하기 위하여 매체에 저장된 컴퓨터 프로그램. A computer program stored in a medium for carrying out the method of any one of claims 1 to 6 using a computer.
PCT/KR2018/001692 2017-02-08 2018-02-08 Method, device and computer program for generating survival rate prediction model WO2018147653A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020170017642A KR102127449B1 (en) 2017-02-08 2017-02-08 Apparatus, method, and computer program for generating survival rate prediction model
KR10-2017-0017642 2017-02-08

Publications (1)

Publication Number Publication Date
WO2018147653A1 true WO2018147653A1 (en) 2018-08-16

Family

ID=63107726

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2018/001692 WO2018147653A1 (en) 2017-02-08 2018-02-08 Method, device and computer program for generating survival rate prediction model

Country Status (2)

Country Link
KR (1) KR102127449B1 (en)
WO (1) WO2018147653A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110276068A (en) * 2019-05-08 2019-09-24 清华大学 Law merit analysis method and device
US20210090732A1 (en) * 2017-04-28 2021-03-25 University Of Southern California System and method for predicting survival time

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102174608B1 (en) * 2018-11-27 2020-11-05 공주대학교 산학협력단 Apparatus for predicting loan defaults based on machine learning and method thereof

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050019798A1 (en) * 2003-05-30 2005-01-27 Michael Kattan Methods to predict death from breast cancer
JP2009533782A (en) * 2006-04-17 2009-09-17 シーメンス メディカル ソリューションズ ユーエスエー インコーポレイテッド Personal prognostic modeling in medical planning
US20090234627A1 (en) * 2008-03-13 2009-09-17 Siemens Medical Solutions Usa, Inc. Modeling lung cancer survival probability after or side-effects from therapy
US20100057651A1 (en) * 2008-09-03 2010-03-04 Siemens Medicals Solutions USA, Inc. Knowledge-Based Interpretable Predictive Model for Survival Analysis
KR101501826B1 (en) * 2013-04-05 2015-03-13 연세대학교 산학협력단 Method for preparing prognosis prediction model of gastric cancer

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050019798A1 (en) * 2003-05-30 2005-01-27 Michael Kattan Methods to predict death from breast cancer
JP2009533782A (en) * 2006-04-17 2009-09-17 シーメンス メディカル ソリューションズ ユーエスエー インコーポレイテッド Personal prognostic modeling in medical planning
US20090234627A1 (en) * 2008-03-13 2009-09-17 Siemens Medical Solutions Usa, Inc. Modeling lung cancer survival probability after or side-effects from therapy
US20100057651A1 (en) * 2008-09-03 2010-03-04 Siemens Medicals Solutions USA, Inc. Knowledge-Based Interpretable Predictive Model for Survival Analysis
KR101501826B1 (en) * 2013-04-05 2015-03-13 연세대학교 산학협력단 Method for preparing prognosis prediction model of gastric cancer

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210090732A1 (en) * 2017-04-28 2021-03-25 University Of Southern California System and method for predicting survival time
US11515039B2 (en) * 2017-04-28 2022-11-29 University Of Southern California System and method for predicting survival time
CN110276068A (en) * 2019-05-08 2019-09-24 清华大学 Law merit analysis method and device

Also Published As

Publication number Publication date
KR102127449B1 (en) 2020-06-26
KR102127449B9 (en) 2021-07-26
KR20180092189A (en) 2018-08-17

Similar Documents

Publication Publication Date Title
Poongodi et al. Diagnosis and combating COVID-19 using wearable Oura smart ring with deep learning methods
WO2018147653A1 (en) Method, device and computer program for generating survival rate prediction model
WO2018106005A1 (en) System for diagnosing disease using neural network and method therefor
Osuch et al. Complexity in mood disorder diagnosis: fMRI connectivity networks predicted medication‐class of response in complex patients
WO2017051943A1 (en) Method and apparatus for generating image, and image analysis method
WO2019172498A1 (en) Computer-aided diagnosis system for providing tumor malignancy and basis of malignancy inference and method therefor
WO2020111754A9 (en) Method for providing diagnostic system using semi-supervised learning, and diagnostic system using same
WO2021040327A1 (en) Apparatus and method for predicting cardiovascular risk factor
Tsai et al. Optimal paramedic numbers in resuscitation of patients with out-of-hospital cardiac arrest: a randomized controlled study in a simulation setting
WO2018169121A1 (en) Method, device, and program for predicting prognosis of synovial sarcoma by using artificial neural network
WO2024162595A1 (en) Method and device for generating three-dimensional tooth model
Dong et al. How brain structure–function decoupling supports individual cognition and its molecular mechanism
WO2023136417A1 (en) Method and device for constructing transformer model for video story question answering
WO2015060486A1 (en) Apparatus and method for diagnosing image
WO2022055158A1 (en) Method for converting part of dental image and apparatus therefor
WO2023096034A1 (en) Electronic device for predicting drug-drug interactions and control method therefor
WO2019225799A1 (en) Method and device for deleting user information using deep learning generative model
Kadari et al. A Pathway to Real-Time Wellness Digital Twins for Precision Wellness Monitoring
WO2021242073A1 (en) Electronic device and control method therefor
WO2022215764A1 (en) Digital apparatus and application for treatment of mild cognitive impairment and dementia
US20190180000A1 (en) Patient diagnosis and treatment based on genomic tensor motifs
WO2022019514A1 (en) Apparatus, method, and computer-readable recording medium for decision-making in hospital
Mirarchi et al. Data mining techniques for vestibular data classification
WO2021015490A2 (en) Method and device for analyzing specific area of image
Lin et al. Control strategies against COVID-19 in China: Significance of effective testing in the long run

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18751357

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18751357

Country of ref document: EP

Kind code of ref document: A1