diagnostics

Review
Enhancing the Evidence with Algorithms: How Artificial
Intelligence Is Transforming Forensic Medicine
Alin-Ionut Piraianu † , Ana Fulga *, Carmina Liana Musat † , Oana-Roxana Ciobotaru, Diana Gina Poalelungi,
Elena Stamate *, Octavian Ciobotaru † and Iuliu Fulga

Faculty of Medicine and Pharmacy, Dunarea de Jos University of Galati, 35 AI Cuza St., 800010 Galati, Romania;
alin.piraianu@gmail.com (A.-I.P.); carmina.musat@ugal.ro (C.L.M.); roxana_hag@yahoo.com (O.-R.C.);
dianapoalelungi10@gmail.com (D.G.P.); coctavian72@gmail.com (O.C.); fulgaiuliu@yahoo.com (I.F.)
* Correspondence: ana.fulgaa@gmail.com (A.F.); elena.stamate94@yahoo.com (E.S.)
† These authors contributed equally to this work.

Abstract: Background: The integration of artificial intelligence (AI) into various fields has ushered in
a new era of multidisciplinary progress. Defined as the ability of a system to interpret external data,
learn from it, and adapt to specific tasks, AI is poised to revolutionize the world. In forensic medicine
and pathology, algorithms play a crucial role in data analysis, pattern recognition, anomaly identifica-
tion, and decision making. This review explores the diverse applications of AI in forensic medicine,
encompassing fields such as forensic identification, ballistics, traumatic injuries, postmortem interval
estimation, forensic toxicology, and more. Results: A thorough review of 113 articles revealed a subset
of 32 papers directly relevant to the research, covering a wide range of applications. These included
forensic identification, ballistics and additional factors of shooting, traumatic injuries, post-mortem
interval estimation, forensic toxicology, sexual assaults/rape, crime scene reconstruction, virtual
autopsy, and medical act quality evaluation. The studies demonstrated the feasibility and advantages
of employing AI technology in various facets of forensic medicine and pathology. Conclusions:
Citation: Piraianu, A.-I.; Fulga, A.; The integration of AI in forensic medicine and pathology offers promising prospects for improving
Musat, C.L.; Ciobotaru, O.-R.; accuracy and efficiency in medico-legal practices. From forensic identification to post-mortem interval
Poalelungi, D.G.; Stamate, E.; estimation, AI algorithms have shown the potential to reduce human subjectivity, mitigate errors, and
Ciobotaru, O.; Fulga, I. Enhancing the provide cost-effective solutions. While challenges surrounding ethical considerations, data security,
Evidence with Algorithms: How and algorithmic correctness persist, continued research and technological advancements hold the key
Artificial Intelligence Is Transforming to realizing the full potential of AI in forensic applications. As the field of AI continues to evolve, it is
Forensic Medicine. Diagnostics 2023, poised to play an increasingly pivotal role in the future of forensic medicine and pathology.
13, 2992. https://doi.org/10.3390/
diagnostics13182992
Keywords: artificial intelligence; medicine; forensic science; forensic medicine; pathology
Academic Editors: Miguel
Mascarenhas Saraiva and
Guilherme Macedo
1. Introduction
Received: 20 August 2023
Revised: 13 September 2023 The next revolution from an IT and industrial point of view will be the use of artificial
Accepted: 14 September 2023 intelligence for multidisciplinary progress. Kaplan and Haenlein define AI as “the ability
Published: 19 September 2023 of a system to correctly interpret external data, learn from such data, and use it to achieve
specific goals and tasks through flexible adaptation” [1]. The term “artificial intelligence” is
used colloquially to describe machines that mimic the “cognitive” functions that humans
associate with other human minds, such as “learning” and “problem solving” [2]. We
Copyright: © 2023 by the authors. are currently at the point of implementation of the fourth industrial revolution, with AI
Licensee MDPI, Basel, Switzerland. becoming a cornerstone for all digital transformation initiatives [3].
This article is an open access article Algorithms are well-defined sets of instructions or steps that a computer follows to
distributed under the terms and
solve a particular problem or perform a particular task. These instructions are defined
conditions of the Creative Commons
logically and sequentially so that they can be followed by the computer to achieve a
Attribution (CC BY) license (https://
particular result. In the context of the use of artificial intelligence in forensics, algorithms
creativecommons.org/licenses/by/
can be programmed to analyze data, recognize patterns, identify anomalies, or provide
4.0/).

Diagnostics 2023, 13, 2992. https://doi.org/10.3390/diagnostics13182992 https://www.mdpi.com/journal/diagnostics

Diagnostics 2023, 13, 2992 2 of 11

suggestions and decisions based on the data provided. These sets of instructions and
mathematical operations can be used by artificial intelligence to perform specific tasks
within the field of forensics.
In medicine, AI is already used as an assistant to doctors, to establish a correct diag-
nosis, detect and monitor vital signs, and even detect skin cancer [4]. Forensic medicine
is a medical discipline that aims to prepare scientific medical-biological evidence for the
application of judicial rules. Medical science, implicitly forensic medicine and pathology,
cannot ignore the new expertise techniques. The classic way of performing an autopsy
and drawing up an expert report has many limitations, but these can be reduced with the
help of artificial intelligence. Forensic medicine and pathology changes in “the big data
era”, and the development is a full expansion in 2023 artificial intelligence, bringing new
opportunities. In recent years, numerous studies based on artificial intelligence technology
have been carried out, such as face recognition, age and sex estimates, DNA analysis, post-
mortem interval estimation, and injury and cause of death identification, demonstrating the
feasibility and advantages of using artificial intelligence technology in forensic medicine
and pathology [5]. Thus, a new worldwide direction has been launched, which includes
technology adaptability challenges with the potential of integration into the well-known
medico-legal practice until now.

1.1. Definitions of Terms Related to AI and Medicine

1.1.1. Artificial Intelligence
Alan Turing, the founding father of artificial intelligence gave the first definition
of artificial intelligence as the science and engineering of making intelligent machines,
especially intelligent computer programs [6]. According to Salto-Tellez M. et al. [7], AI is
an advanced technological range of machines that can extract meaning and understanding
from extended data inputs in ways that mimic human capabilities. Currently, a specific
definition can be the ability of a system to interpret external data correctly and to learn
from it to achieve specific goals and tasks through flexible adaptation [1].

1.1.2. Machine Learning (ML)

Machine learning is a statistical technique of fitting models to data and, learning
by training models using data [8]. In medicine, the most widely used application of
machine learning is precision medicine (predicting the treatment that is likely to have the
best effect on the patient) [9]. For precision medicine to work, a set of training data is
required for which the outcome variable (e.g., disease onset) is known, which is called
supervised learning.

1.1.3. Deep Learning (DL)

Deep Learning, a subcategory of machine learning, is a deep neural network that has
a specific configuration in which neurons are organized in several successive layers, which
can independently learn representations of the data and progressively extract complex
features to perform tasks such as computer vision and natural language processing (NPL)
and is used in medicine to detect diseases from medical imaging [10].

1.1.4. Natural Language Processing (NPL)

Natural language processing is a theoretically motivated range of computational
techniques for analyzing and representing naturally occurring texts at one or more levels
of linguistic analysis to achieve human-like language processing for a range of tasks or
applications, being used in medicine to structure information in healthcare systems and
extract relevant information from narrative texts to provide data for decision making [11].

1.1.5. Robotics
The robot has been defined as “a reprogrammable multifunctional manipulator de-
signed to move material, parts, tools, or specialized devices through variable programmed
Diagnostics 2023, 13, 2992 3 of 11

motions for the performance of a variety of tasks” by the Robot Institute of America; in
medicine, they are used for their precision, especially in surgical specialties [12].

1.1.6. Artificial Neural Network (ANN)

Artificial neural networks are a class of artificial intelligence algorithms that emerged
in the 1980s as a result of developments in cognitive and computer science research. Like
other artificial intelligence algorithms, ANNs have been motivated to address different
aspects or elements of learning, such as learning mode, induction mode, and inference
mode [13].

1.1.7. Convolutional Neural Networks (CNNs)

Convolutional neural networks are neural networks similar to regular neural networks
because they are also composed of neurons with learnable weights. CNNs make the explicit
assumption that inputs have specific structures like images. This allows for encoding of
this property into the architecture by sharing the weights for each location in the image
and having neurons respond only locally [14].

2. Literature Review
2.1. Methodology
We conducted a review of current literature including original articles and reviews
that studied various clinical applications of AI in forensic medicine and pathology. We
performed extensive searches on Google Scholar, PubMed, and ScienceDirect databases
to identify relevant manuscripts. As keywords, we used “artificial intelligence”, “deep
learning”, and “machine learning”, combined with “forensic medicine”, “legal medicine”,
“forensic pathology” and, medicine”. We restricted our search to papers published in
English and found more than 100 relevant manuscripts. The inclusion criteria focused on
studies that examined the application of artificial intelligence in forensic medicine and
pathology and various medical specialties.

2.2. Results
After a thorough review and assessment of the 113 articles, we identified and included
a subset of 32 papers that were directly relevant to our research, including seven in forensic
identification, one in Ballistics and additional factors of shooting, one in traumatic injuries,
three in establishing the post-mortem interval, two in forensic toxicology, one in sexual
assaults/rape, one in crime scene reconstruction, one in virtual autopsy, and fourteen in
medical act quality evaluation, listed in Table 1. These selected studies provided valuable
insights into the use and impact of AI in forensic medicine and pathology and various
medical specialties, forming the basis of our review.

2.2.1. Forensic Identification

Forensic odontostomatological identification by visual or clinical methods can some-
times be difficult. The expertise allows for the determination of ABO antigens, serum
proteins (Gm, Km, Gc), enzyme markers, the genetic fingerprint, and the Y chromosome
by analyzing the root pulp. Age and sex can be estimated by analyzing the dentin. Some
authors have identified drugs, proteins, lipids, and carbohydrates in the tartar collected
from corpses or from a living person, which can point to a certain population group
through information related to socio-economic status, occupation, diet, dental, or systemic
diseases [15,16]. However, the existing technique can be exhausting and complicated in
a larger scale expertise, which requires a much larger number of forensic odontostom-
atological identifications. Mohammad N et al. state in the review carried out that the
potential application of artificial intelligence in forensic odontology can be classified into
four categories: (1) human bite marks, (2) sex estimate, (3) age estimation, and (4) dental
comparison [1]. AI can provide a set of data, and a correctly assigned analysis algorithm in
Diagnostics 2023, 13, 2992 4 of 11

the case of hyperparameters, which allows for the creation of a predictive model at a very
high level of performance.

Table 1. Scientific articles that analyze the use of artificial intelligence in forensic medicine.

Year of Study Author Application

2022 Mohammad N. [17] Forensic Odontology
2020 Khanagar S.B. [18] Forensic Odontology
2021 Thurzo A. [19] The AI impact on forensic anthropology
Forensic Identification
2017 Nino-Sandoval T. [20] Mandibular reconstruction
2022 Matsuda S. [21] Personal identification
2016 Nguyen D.T [22] Sex estimates
2021 Massimo L. [23] Visual semiotics and digital forensics
Ballistics and additional Establishing the class of the weapon
2020 Bobbili R. [24]
factors of shooting and the bullet caliber
Estimating the ecchymosis age by color
Traumatic injuries 2005 Georgieva L. [25]
analysis
Prediction of PM interval through
Post-mortem interval 2019 Hachem M. [26]
blood biomarkers
2020 Zou Y. [27] Post Mortem interval and AI
2022 Wang Z. [28] AI and microbiome for PM interval
Forensic toxicology 2020 Gasteiger J. [29] Chemistry and AI
2000 Helma C. [30] Toxicology and AI
Sperm identification under an optical
Sexual assaults/rape 2021 Golomingi R. [31]
microscope using AI
Making animations regarding the
Crime Scene Reconstruction 2020 Siddhant G. [32]
circumstances of the death
O’Sullivan S. [33];
Virtual autopsy 2017 AI assistance in necropsy expertise
Gerke S. [34]
Medical Act Quality
2019 Santin M. [35] AI assistance in imaging investigations
Evaluation
2020 Qui S. [36] AI assistance in psychiatry
2023 Salazar L. [37]
2019 Attia Z.I [38] AI assistance in cardiology
2018 Alsharqi M. [39]
2020 Zhang Y.H. [40] Cancer management using AI
2022 Rajpurkar P. [41] AI assistance in pathology
2020 Young A.T [42]
AI in dermatology
2019 Dick V. [43]
2020 Pedersen M. [44] AI in neurology
2017 Rathi S. [45] AI in ophthalmology
2021 Kroner P.T. [46] AI in gastroenterology
2015 Idowu I.O. [47]
AI in obstetrics and gynecology
2021 Sone K. [48].
Diagnostics 2023, 13, 2992 5 of 11

In Khanagar S.B. et al.’s review, we found the perspective of using AI for the re-
construction of the mandible [18]. These AI models are based either on artificial neural
networks (ANN) or on convolutional neural networks (CNN). The results being promising,
these models show accuracy and precision equivalent to those of experts in the field, useful
especially in the case of the need to identify victims of mass disasters [17]. CNN is a
deep learning algorithm that can apply different properties/aspects to an input image and
differentiate it from others. Convolutional neural networks work like the human brain
by trying to identify blurred images. Recognition improves when more slices are added,
which provides a 3D feature [19,20]. A forensic anthropologist has the difficult task of
storing and processing a huge amount of anthropometric information, and sometimes
fatigue, subjectivism, methodological difficulties, and interpretation can lead to errors.
The incidence of these errors can be reduced by processing data with the help of AI with
automatic learning that imitates human neural networks which can solve even the most
complex problems, without getting tired, without using emotions, and without particu-
larizing cases through subjective judgment. During COVID-19, person identification (PI)
with the help of AI would have been extremely useful, considering the number of deaths
worldwide and the existence of unknown bodies that needed to be identified. Matsuda S.
and Yoshimura H. carried out a scientific paper in 2022 in which they show that conven-
tional anthropological methods that follow the description of facial features (hair, eye color,
nose, lips, scars, tattoos, particular signs) or fingerprints and DNA analysis can be replaced
with modern, new methods, with the involvement of artificial intelligence, already used for
the identification of some bodily parameters, the retina model and fingerprints, especially
in institutions where data security takes precedence, even proposing the use of artificial
intelligence on all living people, ethically questionable methods, but which could help
identify people [21]. Currently, out of all the identification methods used, facial recognition
is in second place, after the fingerprint [22]. Although progress exists, and the replacement
of fingerprint-based methods with AI identification devices requires training/learning with
images of people, the human factor remains decisive in the formation of these systems, and
the challenges related to the infrastructure and biometric resources of a population will
exist [23].

2.2.2. Ballistic Expertise and Additional Factors of the Shooting

When a bullet leaves a weapon, it carries microscopic traces, which are like ballistic
fingerprints. Artificial intelligence can guide experts to the place where they need to
look for gunpowder and cartridge tubes and compare the traces with a database through
image processing, without human involvement. Currently, some algorithms allow for the
highlighting the residues resulting from firing with firearms, allowing for the detection of
the explosion inside the barrel, changes due to shock waves, as well as the provision of
data that allow for the establishment of the class and caliber [24].

2.2.3. Traumatic Injuries—Bruise Color’s Recognition

Ecchymoses undergo color changes in their evolution towards healing, through the
degradation of hemoglobin: initially reddish, then violet-blue, on the third day it becomes
greenish due to biliverdin, then after 4–5 days it turns brown due to bilirubin, and later
turns yellow due to the accumulation of hemosiderin pigment, disappearing in 10–14 days.
Forensic medicine assesses the age of the bruises initially macroscopically, passing the
color change through this mind filter. The techniques for detecting bruise colors by AI are
much more accurate than the human factor, which can be subjective in some cases, and
through the created algorithm, a time interval of the production of traumatic injuries [25]
is generated.
Diagnostics 2023, 13, 2992 6 of 11

2.2.4. Determination of the Postmortem Interval

Postmortem interval estimation (PMI) is part of the current, almost daily practice
of forensics, being a very important expertise in some cases. An important step in the
evolution of forensic investigations is the introduction of AI in PMI research. The field
of biochemical technologies has begun to identify biomarkers in various biological fluids,
such as blood and urine, for the estimation of PMI. It is suggested that the blood from
the femoral vein should be collected for the measurement of biochemical components
such as lactate dehydrogenase—LDH, aspartate aminotransferase—AST, triglycerides,
and cholesterols, as well as the measurement of pH. These biochemical markers analyzed
by artificial intelligence can provide information on the time of death [26]. After death,
through the decomposition of the body, the level of these biomarkers changes and is directly
proportional to the time elapsed since death. Zou Y et al. state that AI technology is in
full development for data processing and is already being used by some researchers as a
conventional method for PMI estimation [27]. By applying next-generation sequencing
(NGS) and AI techniques, the forensic pathologist can enhance the dataset of microbial
communities and obtain detailed information on the inventory of specific ecosystems,
quantifications of community diversity, descriptions of their ecological function, and even
their application in forensic medicine and pathology through post-mortem sequencing of
the cadaveric microbiome [28].

2.2.5. Forensic Toxicology

Artificial intelligence use prospects in forensic toxicology come from the idea of ex-
panding the search field and creating links with millions of data to identify toxic substances,
drugs, and different metabolites. Automated toxicological analysis through AI allowed for
quantitative and qualitative identification, which by 2020 reached more than 160 million or-
ganic and inorganic substances found in the Chemical Abstract Service (CAS) database [29].
Helma C. et al. revealed in a scientific paper that there can be human errors by using the
spectrophotometer, neutron, and high-performance liquid chromatography (HPLC), and
in this sense, AI can play an essential role by providing a data set as a sample which will
increase the precision of the method, the efficiency, and even the reduction in the costs of
investigations [30].

2.2.6. Sperm Identification

Sperm detection is an investigation that proves rape. In some cases, the samples
contain no sperm or contain only small amounts of sperm. Therefore, the biological
material is transferred to a glass slide and must be manually scanned using an optical
microscope. This work can be very time-consuming, especially when no sperm are present.
Convolutional neural networks trained by the VGG19 network and a variation of VGG19
with 1942 can fulfill this task, they can reduce the scanning time by locating the sperm on
the microscope images [31].

2.2.7. Crime Scene Reconstruction

The manual process of data collection, on-site research, and reconstruction often
involves the forensic pathologist. Artificial intelligence can extract and analyze every
aspect after it is given “some input data”, such as the corpse itself or any object next to it
that could bring data on the death circumstances, by creating video animations [32].

2.2.8. Virtual Autopsy

Artificial intelligence combined with virtual autopsy represents the latest trend in the
field of forensic medicine and pathology. By teaching the machine to take images of the
body through CT or MRI scans, the AI will identify the pathology of an organ, fractures,
deep injuries, and types of inflammation and compare it to the database. The AI will also
process these organic changes and form its own opinion regarding the anatomopathological
diagnosis and the conclusions regarding the cause of death. This technique can also provide
Diagnostics 2023, 13, 2992 7 of 11

information on the injuries produced by firearms, measuring the entrance hole at the level
of the flat bones, and comparing it with different models, thus allowing for the estimation
of the caliber of the bullet. All this, together with the possibility of collecting biological
samples through this method, can assist the forensic pathologist in issuing diagnoses and
formulating more correct conclusions [33].

3. Discussion
3.1. Perspectives and Directions for the Application of Artificial Intelligence in Forensic Medicine
and Pathology
The scientific palette in the field of artificial intelligence is still at the beginning and will
certainly undergo changes to improve and assist the human factor in medicine. Forensic
medicine is no exception to progress, and as we have shown through the review carried
out, various methods are already being implemented worldwide, which we can subdivide
into a few essential aspects: (1) assistance to the forensic pathologist regarding the accuracy
of both the anatomopathological diagnosis macroscopically, as well as all complementary
exams; (2) reducing subjective judgment and fatigue, all the factors that define human
nature through its vulnerability; (3) reducing the costs that involve all the forensic activity
by eliminating some investigations, sometimes necessary for the human with the help of AI
that can express an earlier and more solid opinion, but also by eliminate the risk of repeating
certain complementary examinations which can cause of human errors; (4) the contribution
of artificial intelligence to the creation of an electronic data archiving environment, thus
eliminating files and devices for storing and memorizing data, which are becoming more
and more difficult to manage due to the volume they occupy and the fragility of USB drives
and hard disk, as well as through the possibility of destroying these data.
Although artificial intelligence is renovating the world, its legal value in front of a
court is still not accepted. The human factor, although showing professional sensitivity,
should have the last word to say in a forensic medical report. AI is still a technology in its
teenage years, but it is already proving that its algorithms are more objective and smarter
than humans, basically speculating on human weaknesses. From a scientific point of view,
it is possible that the opinion formed by artificial intelligence will not be accepted as an
individual conclusive proof, but probably with time and with the implementation of AI
in our daily life, it will evolve and be unanimously accepted. Gerke S. et al. state that the
challenges of artificial intelligence also include the ethical characteristics regarding the use
of data, transparency and cyber security, algorithmic correctness, and the confidentiality of
medical data [34].

3.2. Evaluation of Medical Malpractice Cases

The last topic we would like to touch on is the evaluation of medical malpractice with
the help of artificial intelligence. Can we decrease the number of medical malpractice cases
by using artificial intelligence in current practice? In the literature, we found numerous
works that discuss the usefulness of AI in diagnosis accuracy, the prediction of some
complications, as well as the establishment of the degree of effectiveness of the treatment,
alongside works that outline this direction of research [35–48].

3.2.1. Medical Diagnosis

AI can be trained to analyze medical images, such as X-rays, computed tomography
(CT) scans, and magnetic resonance images (MRI), etc., (Figure 1) to detect and diagnose
various pathologies [35,49–52].
Diagnostics
Diagnostics2023,
2023,13,
13,x2992
FOR PEER REVIEW 8 of 11 8 of 1

Figure 1. Distribution of published papers for disease diagnosis using artificial intelligence tech-
Figure 1. Distribution of published papers for disease diagnosis using artificial intelligenc
niques [4]. Adapted from Kumar, Y., Koul, A., Singla, R. et al. Artificial intelligence in disease
techniques [4]. Adapted from Kumar, Y., Koul, A., Singla, R. et al. Artificial intelligence in diseas
diagnosis: a systematic literature review, synthesizing framework, and future research agenda. J
diagnosis: a systematic literature review, synthesizing framework, and future research agenda.
Ambient Intell Human Comput 14, 8459–8486 (2023).
Ambient Intell Human Comput 14, 8459–8486 (2023).
3.2.2. Personalized Treatment
3.2.2. Personalized
Artificial Treatment
intelligence and pharmacogenomics can help identify the right drugs for a
patientArtificial
based on intelligence
their genes and
andpotential drug–drug interactions;
pharmacogenomics can helpAI can analyze
identify medical
the right drugs for
data, and history, to develop a predictive treatment plan [53].
patient based on their genes and potential drug–drug interactions; AI can analyze medica
data,Disease
3.2.3. and history, to develop
Monitoring a predictive treatment plan [53].
and Management
Monitoring systems can collect data about a patient’s condition (heart rate, glucose
3.2.3. Disease Monitoring and Management
level, blood pressure, etc.) and artificial intelligence can analyze this data to detect early
Monitoring
signs of systems
complications. can conducted
In a study collect data aboutby
in China a patient’s
Weng S.F. condition (heart
et al. between 2005rate,
and glucos
2015, using routine clinical data of over 350,000 patients, machine learning significantly
level, blood pressure, etc.) and artificial intelligence can analyze this data to detect earl
improved the accuracy of In
signs of complications. cardiovascular risk prediction,
a study conducted in Chinacorrectly
by Weng predicting 355
S.F. et al. (an
between 200
additional 7.6%) more patients who developed cardiovascular disease compared
and 2015, using routine clinical data of over 350,000 patients, machine learnin with the
established algorithm [54].
significantly improved the accuracy of cardiovascular risk prediction, correctly predictin
In health data management, AI can help analyze and interpret massive amounts of
355 (an additional 7.6%) more patients who developed cardiovascular disease compared
healthcare data, providing healthcare professionals with relevant information and insights
with
to makethe established
more informedalgorithm
decisions. [54].
In health data management, AI can help analyze and interpret massive amounts o
3.2.4. Robot-Assisted
healthcare Surgery
data, providing healthcare professionals with relevant information and
insights to make
According moreX.Y
to Zhou informed decisions.
et al., artificial intelligence has revolutionized surgery, pro-
longing the life and survival limit of patients by managing acute and chronic diseases [55].
Current robots already Surgery
3.2.4. Robot-Assisted can automatically perform some tasks related to basic surgery,
such as suturing and knot tying [56,57]. In the literature, it has already described that a
skilledAccording
surgical robotto was
Zhou
ableX.Y et al., artificial
to completely intelligence
suture the hasofrevolutionized
small intestines a pig on its own, surgery
prolonging the life and survival limit of patients by managing
surpassing the human manual dexterity of experienced surgeons who performed acute and the
chronic
same disease
[55]. Current
suture at the samerobots already can automatically perform some tasks related to basi
time [58].
surgery, such as suturing and knot tying [56,57]. In the literature, it has already described
3.2.5.
that aDrug Discovery
skilled surgical robot was able to completely suture the small intestines of a pig o
With surpassing
its own, all the current progress,
the humanartificial
manualintelligence could
dexterity of accelerate the
experienced processwho
surgeons of new
performed
drug discovery, as its ability to model
the same suture at the same time [58]. molecular interactions and identify compounds
with potential therapeutic properties is already known. For example, in toxicology, deep
learning might automatically identify high-level drug use patterns by combining data from
3.2.5. Drug Discovery
social media, poison control logs, published reports, and national surveys [59].
With all the current progress, artificial intelligence could accelerate the process o
new drug discovery, as its ability to model molecular interactions and identif
compounds with potential therapeutic properties is already known. For example, in
toxicology, deep learning might automatically identify high-level drug use patterns b
Diagnostics 2023, 13, 2992 9 of 11

All that remains is to deepen this perspective and the limits of AI, in the hope that it will
provide us with useful data comparable to a complementary forensic medical examination,
helping human nature to reduce its errors, all of which will be reflected in the benefit of
patients and the whole society.

4. Conclusions
Advancements in artificial intelligence (AI) have marked a turning point in the field
of forensic medicine and pathology. In recent years, these technologies have demonstrated
significant potential in optimizing the processes of data analysis and interpretation. How-
ever, it is important to emphasize that human expertise remains essential in making critical
decisions. One of the major challenges in using AI in this context is ensuring the quality of
scientific data. The process of collecting and cleaning data is of fundamental importance to
ensure the performance and accuracy of AI algorithms. Only by providing reliable data can
we reach the maximum potential of this technology in forensic medicine and pathology.
The benefits brought by AI within the justice system are evident. These include
accelerating the analysis of evidence and interpreting clues, which can lead to a more
efficient and precise legal process. However, it is crucial to recognize that the transition to
fully automated AI use will take time and continuous adjustments. Fundamentally, AI is
not a substitute for human expertise, but rather a valuable partner. Human discernment and
knowledge remain indispensable for interpreting context and making informed decisions.
By balancing technology with human expertise, we can maintain a fair and ethical justice
system in an ever-evolving modern world.
Thus, the progressive integration of AI in forensic medicine and pathology represents
a significant step towards improved well-being and security for society. Through the col-
laboration between technology and human expertise, we can fully harness the advantages
offered by this innovation in the fields of justice and forensic medicine.

Author Contributions: Methodology, data curation, writing—original draft preparation, A.-I.P., A.F.
and E.S.; writing—review and editing, C.L.M., O.-R.C., O.C., A.F., E.S. and D.G.P.; supervision,
conceptualization and funding, I.F. All authors have read and agreed to the published version of
the manuscript.
Funding: This research was funded by the “Dunărea de Jos” University of Galati, VAT 27232142, and
The APC was paid by the “Dunărea de Jos” University of Galati, VAT 27232142.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: Not applicable.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Kaplan, A.; Haenlein, M. Siri, Siri, in My Hand: Who’s the Fairest in the Land? On the Interpretations, Illustrations, and
Implications of Artificial Intelligence. Bus. Horiz. 2019, 62, 15–25. [CrossRef]
2. Russell, S.J.; Norvig, P. Artificial Intelligence: A Modern Approach (d), 3rd ed.; Prentice Hall: Upper Saddle River, NJ, USA, 2009.
3. Narasimhan, G.; Krishnan, R.; Krishnan, A. Fourth Industrial Revolution and Business Dynamics: Issues and Implications; Palgrave
Macmillan: Singapore, 2021.
4. Kumar, Y.; Koul, A.; Singla, R.; Ijaz, M.F. Artificial Intelligence in Disease Diagnosis: A Systematic Literature Review, Synthesizing
Framework and Future Research Agenda. J. Ambient Intell. Humaniz. Comput. 2023, 14, 8459–8486. [CrossRef] [PubMed]
5. Fang, Y.T.; Lan, Q.; Xie, T.; Liu, Y.F.; Mei, S.Y.; Zhu, B.F. New Opportunities and Challenges for Forensic Medicine in the Era of
Artificial Intelligence Technology. Fa Yi Xue Za Zhi 2020, 36, 77–85. [CrossRef] [PubMed]
6. Turing, A.M.I. Computing machinery and intelligence. Mind 1950, 236, 433–460. [CrossRef]
7. Salto-Tellez, M.; Maxwell, P.; Hamilton, P. Artificial intelligence-the third revolution in pathology. Histopathology 2019, 74, 372–376.
[CrossRef] [PubMed]
8. Deloitte Insights State of AI in the Enterprise. Deloitte. 2018. Available online: www2.deloitte.com/content/dam/insights/us/
articles/4780_State-of-AI-in-the-enterprise/AICognitiveSurvey2018_Infographic.pdf (accessed on 1 July 2023).
Diagnostics 2023, 13, 2992 10 of 11

9. Lee, S.I.; Celik, S.; Logsdon, B.A.; Lundberg, S.M.; Martins, T.J.; Oehler, V.G. A machine learning approach to integrate big data
for precision medicine in acute myeloid leukemia. Nat. Commun. 2018, 9, 42. [CrossRef] [PubMed]
10. LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436–444. [CrossRef] [PubMed]
11. Liddy, E.D. Natural Language Processing. In Encyclopedia of Library and Information Science, 2nd ed.; Marcel Decker, Inc.:
New York, NY, USA, 2001.
12. Bann, S.; Khan, M.; Hernandez, J.; Munz, Y.; Moorthy, K.; Datta, V.; Rockall, T.; Darzi, A. Robotics in Surgery. J. Am. Coll. Surg.
2003, 196, 784–795. [CrossRef] [PubMed]
13. Yang, Z.R.; Yang, Z. Comprehensive Biomedical Physics; Karolinska Institute Stockholm, Sweden; Elsevier: Amsterdam, The Netherlands,
2014; p. 1.
14. Teuwen, J.; Moriakov, N. Handbook of Medical Image Computing and Computer Assisted Intervention; Academic Press:
Cambridge, MA, USA, 2020.
15. Sørensen, L.K.; Hasselstrøm, J.B.; Larsen, L.S.; Bindslev, D.A. Entrapment of Drugs in Dental Calculus—Detection Validation
Based on Test Results from Post-Mortem Investigations. Forensic Sci. Int. 2021, 319, 110647. [CrossRef]
16. Setiawan, I.; Lesmana, D.; Marhaeni Diah Herawati, D.; Sufiawati, I.; Widyaputra, S. Correlation between the Macronutrient
Content of Dental Calculus and the FFQ-Based Nutritional Intake of Obese and Normal-Weight Individuals. Int. J. Dent. 2021,
2021, 5579208. [CrossRef]
17. Mohammad, N.; Ahmad, R.; Kurniawan, A.; Mohd Yusof, M.Y.P. Applications of Contemporary Artificial Intelligence Technology
in Forensic Odontology as Primary Forensic Identifier: A Scoping Review. Front. Artif. Intell. 2022, 5, 1049584. [CrossRef]
[PubMed]
18. Khanagar, S.B.; Vishwanathaiah, S.; Naik, S.; Al-Kheraif, A.; Devang Divakar, D.; Sarode, S.C.; Bhandi, S.; Patil, S. Application
and Performance of Artificial Intelligence Technology in Forensic Odontology—A Systematic Review. Leg. Med. 2021, 48, 101826.
[CrossRef]
19. Thurzo, A.; Kosnáčová, H.S.; Kurilová, V.; Kosmel’, S.; Beňuš, R.; Moravanský, N.; Kováč, P.; Kuracinová, K.M.; Palkovič, M.;
Varga, I. Use of Advanced Artificial Intelligence in Forensic Medicine, Forensic Anthropology and Clinical Anatomy. Healthcare
2021, 9, 1545. [CrossRef] [PubMed]
20. Niño-Sandoval, T.C.; Guevara Pérez, S.V.; González, F.A.; Jaque, R.A.; Infante-Contreras, C. Use of Automated Learning
Techniques for Predicting Mandibular Morphology in Skeletal Class I, II and III. Forensic Sci. Int. 2017, 281, 187.e1–187.e7.
[CrossRef]
21. Matsuda, S.; Yoshimura, H. Personal Identification with Artificial Intelligence under COVID-19 Crisis: A Scoping Review. Syst.
Rev. 2022, 11, 7. [CrossRef] [PubMed]
22. Nguyen, D.; Park, K. Body-Based Gender Recognition Using Images from Visible and Thermal Cameras. Sensors 2016, 16, 156.
[CrossRef]
23. Massimo, L. From Fingers to Faces: Visual Semiotics and Digital Forensics. Int. J. Semiot. Law 2021, 34, 579–599.
24. Bobbili, R.; Ramakrishna, B.; Madhu, V. An Artificial Intelligence Model for Ballistic Performance of Thin Plates. Mech. Based Des.
Struct. Mach. 2023, 51, 327–338. [CrossRef]
25. Georgieva, L.; Dimitrova, T.; Stoyanov, I. Computer-Aided System for the Bruise Color’s Recognition; Bulgarian Chapter:
Sofia, Bulgaria, 2005; pp. 1–6.
26. Hachem, M.; Sharma, B.K. Artificial Intelligence in Prediction of PostMortem Interval (PMI) through Blood Biomarkers in
Forensic Examination–A Concept. In Proceedings of the 2019 Amity International Conference on Artificial Intelligence (AICAI),
Dubai, United Arab Emirates, 4–6 February 2019; IEEE: Piscataway, NJ, USA, 2019.
27. Zou, Y.; Zhuang, C.; Fang, Q.; Li, F. Big Data and Artificial Intelligence: New Insight into the Estimation of Postmortem Interval.
Fa Yi Xue Za Zhi 2020, 36, 86–90. [CrossRef]
28. Wang, Z.; Zhang, F.; Wang, L.; Yuan, H.; Guan, D.; Zhao, R. Advances in Artificial Intelligence-Based Microbiome for PMI
Estimation. Front. Microbiol. 2022, 13, 1034051. [CrossRef]
29. Gasteiger, J. Chemistry in Times of Artificial Intelligence. Chemphyschem 2020, 21, 2233–2242. [CrossRef]
30. Helma, C. Data Mining and Knowledge Discovery in Predictive Toxicology. SAR QSAR Environ. Res. 2004, 15, 367–383. [CrossRef]
31. Golomingi, R.; Haas, C.; Dobay, A.; Kottner, S.; Ebert, L. Sperm Hunting on Optical Microscope Slides for Forensic Analysis with
Deep Convolutional Networks—A Feasibility Study. Forensic Sci. Int. Genet. 2022, 56, 102602. [CrossRef]
32. Gupta, S.; Sharma, V. Artificial intelligence in forensic science. artificial intelligence in forensic science. Int. Res. J. Eng. Technol.
2020, 7, 7181–7184.
33. Sullivan, S.O.; Holzinger, A.; Zatloukal, K.; Saldiva, P.; Sajid, M.I.; Wichmann, D. Machine Learning Enhanced Virtual Autopsy.
Autops. Case Rep. 2017, 7, 3–7. [CrossRef]
34. Gerke, S.; Minssen, T.; Cohen, G. Ethical and Legal Challenges of Artificial Intelligence-Driven Healthcare. In Artificial Intelligence
in Healthcare; Elsevier: Amsterdam, The Netherlands, 2020; pp. 295–336.
35. Santin, M.; Brama, C.; Théro, H.; Ketheeswaran, E.; El-Karoui, I.; Bidault, F.; Gillet, R.; Gondim Teixeira, P.; Blum, A. Detecting
Abnormal Thyroid Cartilages on CT Using Deep Learning. Diagn. Interv. Imaging 2019, 100, 251–257. [CrossRef]
36. Qiu, S.; Joshi, P.S.; Miller, M.I.; Xue, C.; Zhou, X.; Karjadi, C.; Chang, G.H.; Joshi, A.S.; Dwyer, B.; Zhu, S.; et al. Development
and Validation of an Interpretable Deep Learning Framework for Alzheimer’s Disease Classification. Brain 2020, 143, 1920–1933.
[CrossRef]
Diagnostics 2023, 13, 2992 11 of 11

37. Salazar, L.; Vasquez, J.F.; Torres, C.L.B.; Camacho, J.; Turbay, C.I.; Garnica, D.E.; Torralba, F.; Isaza-Restrepo, D.; Alferez, S.
Prediction of Acute Complications in Patients with Myocardial Infarction Using Artificial Intelligence. J. Am. Coll. Cardiol. 2023,
81, 2404. [CrossRef]
38. Attia, Z.I.; Kapa, S.; Yao, X.; Lopez-Jimenez, F.; Mohan, T.L.; Pellikka, P.A.; Carter, R.E.; Shah, N.D.; Friedman, P.A.; Noseworthy,
P.A. Prospective validation of a deep learning electrocardiogram algorithm for the detection of left ventricular systolic dysfunction.
J. Cardiovasc. Electrophysiol. 2019, 30, 668–674. [CrossRef]
39. Alsharqi, M.; Woodward, W.J.; Mumith, J.A.; Markham, D.C.; Upton, R.; Leeson, P. Artificial intelligence and echocardiography.
Echo Res. Pract. 2018, 5, R115–R125. [CrossRef]
40. Zhang, Y.-H.; Guo, L.-J.; Yuan, X.-L.; Hu, B. Artificial Intelligence-Assisted Esophageal Cancer Management: Now and Future.
World J. Gastroenterol. 2020, 26, 5256–5271. [CrossRef] [PubMed]
41. Rajpurkar, P.; Chen, E.; Banerjee, O.; Topol, E.J. AI in Health and Medicine. Nat. Med. 2022, 28, 31–38. [CrossRef] [PubMed]
42. Young, A.T.; Xiong, M.; Pfau, J.; Keiser, M.J.; Wei, M.L. Artificial Intelligence in Dermatology: A Primer. J. Investig. Dermatol. 2020,
140, 1504–1512. [CrossRef]
43. Dick, V.; Sinz, C.; Mittlböck, M.; Kittler, H.; Tschandl, P. Accuracy of Computer-Aided Diagnosis of Melanoma: A Meta-analysis.
JAMA Dermatol. 2019, 155, 1291–1299. [CrossRef] [PubMed]
44. Pedersen, M.; Verspoor, K.; Jenkinson, M.; Law, M.; Abbott, D.F.; Jackson, G.D. Artificial intelligence for clinical decision support
in neurology. Brain Commun. 2020, 2, fcaa096. [CrossRef]
45. Rathi, S.; Tsui, E.; Mehta, N.; Zahid, S.; Schuman, J.S. The Current State of Teleophthalmology in the United States. Ophthalmology
2017, 124, 1729–1734. [CrossRef] [PubMed]
46. Kröner, P.T.; Engels, M.M.; Glicksberg, B.S.; Johnson, K.W.; Mzaik, O.; van Hooft, J.E.; Wallace, M.B.; El-Serag, H.B.; Krittanawong,
C. Artificial intelligence in gastroenterology: A state-of-the-art review. World J. Gastroenterol. 2021, 27, 6794–6824. [CrossRef]
47. Idowu, I.O.; Fergus, P.; Hussain, A.; Dobbins, C.; Khalaf, M.; Eslava, R.V.C.; Keight, R. Artificial Intelligence for Detecting Preterm
Uterine Activity in Gynecology and Obstetric Care. In Proceedings of the 2015 IEEE International Conference on Computer
and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing;
Pervasive Intelligence and Computing, Liverpool, UK, 26–28 October 2015; pp. 215–220.
48. Sone, K.; Toyohara, Y.; Taguchi, A.; Miyamoto, Y.; Tanikawa, M.; Uchino-Mori, M.; Iriyama, T.; Tsuruga, T.; Osuga, Y. Application
of artificial intelligence in gynecologic malignancies: A review. J. Obstet. Gynaecol. Res. 2021, 47, 2577–2585. [CrossRef]
49. Hosny, A.; Parmar, C.; Quackenbush, J.; Schwartz, L.H.; Aerts, H.J.W.L. Artificial intelligence in radiology. Nat. Rev. Cancer 2018,
18, 500–510. [CrossRef]
50. Chen, H.; Zheng, Y.; Park, J.H.; Heng, P.A.; Zhou, S.K. Iterative Multi-Domain Regularized Deep Learning for Anatomical
Structure Detection and Segmentation from Ultrasound Images. In Proceedings of the International Conference on Medical Image
Computing and Computer-Assisted Intervention, Athens, Greece, 17–21 October 2016; pp. 487–495.
51. Ghafoorian, M.; Karssemeijer, N.; Heskes, T.; van Uden, I.W.M.; Sanchez, C.I.; Litjens, G.; de Leeuw, F.E.; van Ginneken, B.;
Marchiori, E.; Platel, B. Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensi-
ties. Sci. Rep. 2017, 7, 5110. [CrossRef]
52. Wang, H.; Zhou, Z.; Li, Y.; Chen, Z.; Lu, P.; Wang, W.; Liu, W.; Yu, L. Comparison of machine learning methods for classifying
mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images. EJNMMI Res. 2017, 7, 11.
[CrossRef] [PubMed]
53. Davenport, T.; Kalakota, R. The Potential for Artificial Intelligence in Healthcare. Future Healthc. J. 2019, 6, 94–98. [CrossRef]
54. Weng, S.F.; Reps, J.; Kai, J.; Garibaldi, J.M.; Qureshi, N. Can machine learning improve cardiovascular risk prediction using
routine clinical data? PLoS ONE 2017, 12, e0174944. [CrossRef] [PubMed]
55. Zhou, X.Y.; Guo, Y.; Shen, M.; Yang, G.Z. Application of artificial intelligence in surgery. Front. Med. 2020, 14, 417–430. [CrossRef]
56. Hu, Y.; Zhang, L.; Li, W.; Yang, G.Z. Robotic Sewing and Knot Tying for Personalized Stent Graft Manufacturing. In Proceedings
of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, 1–5 October 2018;
pp. 754–760.
57. Hu, Y.; Li, W.; Zhang, L.; Yang, G.Z. Designing, prototyping, and testing a flexible suturing robot for transanal endoscopic
microsurgery. IEEE Robot. Autom. Lett. 2019, 4, 1669–1675. [CrossRef]
58. Shademan, A.; Decker, R.S.; Opfermann, J.D.; Leonard, S.; Krieger, A.; Kim, P.C.W. Supervised autonomous robotic soft tissue
surgery. Sci. Transl. Med. 2016, 8, 337ra64. [CrossRef] [PubMed]
59. Poalelungi, D.G.; Musat, C.L.; Fulga, A.; Neagu, M.; Neagu, A.I.; Piraianu, A.I.; Fulga, I. Advancing Patient Care: How Artificial
Intelligence Is Transforming Healthcare. J. Pers. Med. 2023, 13, 1214. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.