research-article

Predictive modeling of bacterial infections and antibiotic therapy needs in critically ill adults

Authors:

Garrett Eickelberg,

L. Nelson Sanchez-Pinto,

Yuan LuoAuthors Info & Claims

Volume 109, Issue C

https://doi.org/10.1016/j.jbi.2020.103540

Published: 01 September 2020 Publication History

Graphical abstract

Display Omitted

Highlights

•

Unnecessary antibiotic regimens can harm patients without bacterial infections.

•

Our random forest-based prediction model can help predict bacterial infection risk.

•

Data-driven approaches can enhance antibiotic stewardship efforts.

Abstract

Unnecessary antibiotic regimens in the intensive care unit (ICU) are associated with adverse patient outcomes and antimicrobial resistance. Bacterial infections (BI) are both common and deadly in ICUs, and as a result, patients with a suspected BI are routinely started on broad-spectrum antibiotics prior to having confirmatory microbiologic culture results or when an occult BI is suspected, a practice known as empiric antibiotic therapy (EAT). However, EAT guidelines lack consensus and existing methods to quantify patient-level BI risk rely largely on clinical judgement and inaccurate biomarkers or expensive diagnostic tests. As a consequence, patients with low risk of BI often are continued on EAT, exposing them to unnecessary side effects. Augmenting current intuition-based practices with data-driven predictions of BI risk could help inform clinical decisions to shorten the duration of unnecessary EAT and improve patient outcomes. We propose a novel framework to identify ICU patients with low risk of BI as candidates for earlier EAT discontinuation. For this study, patients suspected of having a community-acquired BI were identified in the Medical Information Mart for Intensive Care III (MIMIC-III) dataset and categorized based on microbiologic culture results and EAT duration. Using structured longitudinal data collected up to 24-, 48-, and 72-hours after starting EAT, our best models identified patients at low risk of BI with AUROCs up to 0.8 and negative predictive values >93%. Overall, these results demonstrate the feasibility of forecasting BI risk in a critical care setting using patient features found in the electronic health record and call for more extensive research in this promising, yet relatively understudied, area.

References

[1]

J.A. Claridge, P. Pang, W.H. Leukhardt, J.F. Golob, J.W. Carter, A.M. Fadlalla, Critical analysis of empiric antibiotic utilization: establishing benchmarks, Surg. Infections 11 (2) (2010) 125–131.

[2]

M.P. Francino, Antibiotics and the human gut microbiome: dysbioses and accumulation of resistances, Front. Microbiol. 6 (2015) 1543.

[3]

C.-E. Luyt, N. Bréchot, J.-L. Trouillet, J. Chastre, Antibiotic stewardship in the intensive care unit, Crit. Care 18 (5) (2014) 480.

[4]

Z. Thomas, F. Bandali, J. Sankaranarayanan, T. Reardon, K.M. Olsen, A Multicenter evaluation of prolonged empiric antibiotic therapy in adult ICUs in the United States, Crit. Care Med. 43 (12) (2015) 2527–2534.

[5]

C.H. Weiss, S.D. Persell, R.G. Wunderink, D.W. Baker, Empiric antibiotic, mechanical ventilation, and central venous catheter duration as potential factors mediating the effect of a checklist prompting intervention on mortality: an exploratory analysis, BMC Health Services Res. 12 (2012) 198.

[6]

G. Zilahi, M.A. McMahon, P. Povoa, I. Martin-Loeches, Duration of antibiotic therapy in the intensive care unit, J. Thoracic Dis. 8 (12) (2016) 3774–3780.

[7]

N. Arulkumaran, M. Routledge, S. Schlebusch, J. Lipman, M.A. Conway, Antimicrobial-associated harm in critical care: a narrative review, Intensive Care Med. (2020).

[8]

Surveillance of Antimicrobial Resistance in Europe. In: Control ECfDPa, ed2017.

[9]

F. Prestinaci, P. Pezzotti, A. Pantosti, Antimicrobial resistance: a global multifaceted phenomenon, Pathog Glob Health. 109 (7) (2015) 309–318.

[10]

P. Dadgostar, Antimicrobial resistance: implications and costs, Infection Drug Resistance 12 (2019) 3903–3910.

[11]

Antibiotic resistance threats in the United States, in: Prevention CfDCa, Services UDoHaH, eds2013, 2013.

[12]

More evidence on link between antibiotic use and antibiotic resistance. ScienceDaily: European Centre for Disease Prevention and Control (ECDC); 07/27/2017, 2017.

[13]

Antimicrobial resistance: global report on surveillance, World Health Organization, 2014.

[14]

L.J. Shallcross, D.S.C. Davies, Antibiotic overuse: a key driver of antimicrobial resistance, Br. J. Gen. Pract. 64 (629) (2014) 604–605.

[15]

C.A. Michael, D. Dominey-Howes, M. Labbate, The antimicrobial resistance crisis: causes, consequences, and management, Front. Public Health 2 (2014) 145.

[16]

Core Elements of Hospital Antibiotic Stewardship Programs | Antibiotic Use | CDC, 2019.

[17]

B.C. Camins, M.D. King, J.B. Wells, et al., Impact of an antimicrobial utilization program on antimicrobial use at a large teaching hospital: a randomized controlled trial, Infect. Control Hosp. Epidemiol. 30 (10) (2009) 931–938.

[18]

B.G. Bell, F. Schellevis, E. Stobberingh, H. Goossens, M. Pringle, A systematic review and meta-analysis of the effects of antibiotic consumption on antibiotic resistance, BMC Infect. Dis. 14 (1) (2014) 13.

[19]

D.A. Goff, T.M. File, The risk of prescribing antibiotics “just-in-case” there is infection, Seminars Colon Rectal Surg. 29 (1) (2018) 44–48.

[20]

J.-L. Vincent, J. Rello, J. Marshall, et al., International study of the prevalence and outcomes of infection in intensive care units, JAMA 302 (21) (2009) 2323–2329.

[21]

D.C. Angus, W.T. Linde-Zwirble, J. Lidicker, G. Clermont, J. Carcillo, M.R. Pinsky, Epidemiology of severe sepsis in the United States: analysis of incidence, outcome, and associated costs of care, Crit. Care Med. 29 (7) (2001) 1303–1310.

[22]

F.B. Mayr, S. Yende, D.C. Angus, Epidemiology of severe sepsis, Virulence 5 (1) (2014) 4–11.

[23]

J.L. Vincent, E. Abraham, D. Annane, G. Bernard, E. Rivers, G. Van den Berghe, Reducing mortality in sepsis: new directions, Crit Care. 6 (Suppl 3) (2002) S1–S18.

[24]

K. Andre, M. Mark, K. Michael, et al., Guidelines for the management of adults with hospital-acquired, ventilator-associated, and healthcare-associated pneumonia, Am. J. Respir. Crit. Care Med. 171 (4) (2005) 388–416.

[25]

R.P. Dellinger, M.M. Levy, A. Rhodes, et al., Surviving sepsis campaign: international guidelines for management of severe sepsis and septic shock: 2012, Crit. Care Med. 41 (2) (2013) 580–637.

[26]

J.S. Solomkin, J.E. Mazuski, J.S. Bradley, et al., Diagnosis and management of complicated intra-abdominal infection in adults and children: guidelines by the Surgical Infection Society and the Infectious Diseases Society of America, Clin. iInfect. Dis.: Off. Publ. Infect. Dis. Soc. Am. 50 (2) (2010) 133–164.

[27]

J.J. Zimmerman, Society of critical care medicine presidential address−47th annual congress, February 2018, San Antonio, Texas, Crit. Care Med. 46 (6) (2018) 839–842.

[28]

A. Kumar, D. Roberts, K.E. Wood, et al., Duration of hypotension before initiation of effective antimicrobial therapy is the critical determinant of survival in human septic shock, Crit. Care Med. 34 (6) (2006) 1589–1596.

[29]

D. Misquitta, Early Prediction of Antibiotics in Intensive Care Unit Patients [Master’s Thesis]: Biomedical Informatics, Harvard Medical School, 2013.

[30]

Y. Luo, P. Szolovits, A.S. Dighe, J.M. Baron, 3D-MICE: integration of cross-sectional and longitudinal imputation for multi-analyte longitudinal clinical data. (1527-974X (Electronic)).

[31]

Y. Luo, P. Szolovits, A.S. Dighe, J.M. Baron, Using Machine Learning to Predict Laboratory Test Results, (1943-7722 (Electronic)).

[32]

S. Le Cessie, J.C. Van Houwelingen, Ridge estimators in logistic regression, J. Roy. Stat. Soc.: Ser. C (Appl. Stat.) 41 (1) (1992) 191–201.

[33]

L. Breiman, Random forests, Mach. Learn. 45 (1) (2001) 5–32.

Digital Library

[34]

C. Cortes, V. Vapnik, Support-vector networks, Mach. Learn. 20 (3) (1995) 273–297.

Digital Library

[35]

J.H. Friedman, Stochastic gradient boosting, Comput. Stat. Data Anal. 38 (4) (2002) 367–378.

Digital Library

[36]

C. Luna, D. Blanzaco, M. Niederman, et al., Resolution of ventilator-associated pneumonia: Prospective evaluation of the clinical pulmonary infection score as an early clinical predictor of outcome*, Crit. Care Med. 31 (3) (2019) 676–682.

[37]

F. Blot, B. Raynard, E. Chachaty, C. Tancrède, S. Antoun, G. Nitenberg, Value of gram stain examination of lower respiratory tract secretions for early diagnosis of nosocomial pneumonia, http://dxdoiorg/101164/ajrccm16259908088, 2000.

[38]

M. Campion, G. Scully, Antibiotic use in the intensive care unit: optimization and de-escalation, J. Intensive Care Med. 33 (12) (2018) 647–655.

[39]

L.P. Samuel, J.-M. Balada-Llasat, A. Harrington, R. Cavagnolo, Multicenter Multicenter Assessment of Gram Stain Error Rates, 2016.

[40]

E. de Jong, J.A. van Oers, A. Beishuizen, et al., Efficacy and safety of procalcitonin guidance in reducing the duration of antibiotic treatment in critically ill patients: a randomised, controlled, open-label trial, Lancet. Infect. Dis 16 (7) (2016) 819–827.

[41]

P. Schuetz, Y. Wirz, R. Sager, et al. Procalcitonin to initiate or discontinue antibiotics in acute respiratory tract infections, The Cochrane database of systematic reviews 10 (2017) Cd007498.

[42]

J.W. Cals, M.H. Ebell, C-reactive protein: guiding antibiotic prescribing decisions at the point of care, Br. J. Gen. Pract. 68 (668) (2018) 112–113.

[43]

J.R. Paonessa, R.D. Shah, C.I. Pickens, et al., Rapid detection of Methicillin-resistant Staphylococcus aureus in BAL: a pilot randomized controlled trial, Chest 155 (5) (2019) 999–1007.

[44]

L. Ward, M. Paul, S. Andreassen, Automatic learning of mortality in a CPN model of the systemic inflammatory response syndrome, Math. Biosci. 284 (2017) 12–20.

[45]

L. Ward, J.K. Møller, N. Eliakim-Raz, S. Andreassen, Prediction of Bacteraemia and of 30-day Mortality Among Patients with Suspected Infection using a CPN Model of Systemic Inflammation, IFAC-PapersOnLine. 51 (27) (2018) 116–121.

[46]

J.D. Parente, K. Möller, G.M. Shaw, J.G. Chase, Hidden Markov models for sepsis classification, IFAC-PapersOnLine 51 (27) (2018) 110–115.

[47]

M. Paul, S. Andreassen, A.D. Nielsen, et al., Prediction of bacteremia using TREAT, a computerized decision-support system, Clin. Infect. Dis.: Off. Publ. Infect. Dis. Soc. Am. 42 (9) (2006) 1274–1282.

[48]

E. Sheetrit, N. Nissim, D. Klimov, Y. Shahar, Temporal probabilistic profiles for sepsis prediction in the ICU, in: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019; Anchorage, AK, USA.

[49]

S.M. Vieira, J.P. Carvalho, A.S. Fialho, S.R. Reti, S.N. Finkelstein, J.M.C. Sousa, A decision support system for ICU readmissions prevention, in: Proceedings of the 2013 Joint Ifsa World Congress and Nafips Annual Meeting (Ifsa/Nafips), 2013, 251–256.

[50]

Y. Luo, Y. Xin, R. Joshi, L. Celi, P. Szolovits, Predicting ICU mortality risk by grouping temporal trends from a multivariate panel of physiologic measurements, in: Paper presented at: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence; 02/12/2016, 2016.

[51]

E. Gultepe, J.P. Green, H. Nguyen, J. Adams, T. Albertson, I. Tagkopoulos, From vital signs to clinical outcomes for patients with sepsis: a machine learning basis for a clinical decision support system, J. Am. Med. Inform. Assoc. 21 (2014) 315–325.

[52]

R. Brause, F. Hamker, J. Paetz, Septic shock diagnosis by neural networks and rule based systems, in: Computational intelligence techniques in medical diagnosis and prognosis, SpringerLink, 2002.

[53]

L. Peelen, N.F. de Keizer, E. Jonge, R.J. Bosman, A. Abu-Hanna, N. Peek, Using hierarchical dynamic Bayesian networks to investigate dynamics of organ failure in patients in the Intensive Care Unit, J. Biomed. Inform. 43 (2) (2010) 273–286.

[54]

S. Curto, J.P. Carvalho, C. Salgado, S.M. Vieira, J.M.C. Sousa, Predicting ICU readmissions based on bedside medical text notes, in: Paper presented at: 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE); 24-29 July 2016, 2016.

[55]

S. Nemati, A. Holder, F. Razmi, M.D. Stanley, G.D. Clifford, T.G. Buchman, An interpretable machine learning model for accurate prediction of sepsis in the ICU, Crit. Care Med. 46 (4) (2018) 547–553.

Index Terms

Predictive modeling of bacterial infections and antibiotic therapy needs in critically ill adults
1. Applied computing
  1. Life and medical sciences
2. Computing methodologies

Index terms have been assigned to the content through auto-classification.

Recommendations

Predictive modelling of survival and length of stay in critically ill patients using sequential organ failure scores

HighlightsA dataset of 14,480 critically ill patients within the ICU was collected.Machine learning models are constructed to predict patient length of stay and mortality.Prediction accuracy was improved by using a two-by-two classification ...
Clinical notes as prognostic markers of mortality associated with diabetes mellitus following critical care: A retrospective cohort analysis using machine learning and unstructured big data
Abstract Background
Clinical notes are ubiquitous resources offering potential value in optimizing critical care via data mining technologies.
Objective
To determine the predictive value of clinical notes as prognostic markers of 1-year all-cause ...
Graphical abstract

Display Omitted
Highlights
- Clinical text-based machine learning yielded high prognostic ability for predicting mortality of diabetes patients.
- Lasso approach coupled with natural language processing demonstrated capability to elucidate predictive tokens.
- ...
Designing a Pharmacokinetic Machine Learning Model for Optimizing Beta-Lactam Antimicrobial Dosing in Critically Ill Patients
ICMHI '24: Proceedings of the 2024 8th International Conference on Medical and Health Informatics

In the intensive care unit (ICU), accurate dosing of antimicrobials is crucial to not only benefit the patient but also society by reducing the burden of antimicrobial resistance, considered a major global health threat. Piperacillin-tazobactam (TZP) ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Journal of Biomedical Informatics

Journal of Biomedical Informatics Volume 109, Issue C

Sep 2020

196 pages

ISSN:1532-0464

Issue’s Table of Contents

Elsevier Inc.

Publisher

Elsevier Science

San Diego, CA, United States

Publication History

Published: 01 September 2020

Author Tags

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

0
Total Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 21 Nov 2024

Other Metrics

View Author Metrics

Citations

View Options

View options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents