Literature DB >> 33465096

A comparison of machine learning models versus clinical evaluation for mortality prediction in patients with sepsis.

William P T M van Doorn1,2, Patricia M Stassen3,4, Hella F Borggreve3, Maaike J Schalkwijk3, Judith Stoffers3, Otto Bekers1,2, Steven J R Meex1,2.   

Abstract

INTRODUCTION: Patients with sepsis who present to an emergency department (ED) have highly variable underlying disease severity, and can be categorized from low to high risk. Development of a risk stratification tool for these patients is important for appropriate triage and early treatment. The aim of this study was to develop machine learning models predicting 31-day mortality in patients presenting to the ED with sepsis and to compare these to internal medicine physicians and clinical risk scores.
METHODS: A single-center, retrospective cohort study was conducted amongst 1,344 emergency department patients fulfilling sepsis criteria. Laboratory and clinical data that was available in the first two hours of presentation from these patients were randomly partitioned into a development (n = 1,244) and validation dataset (n = 100). Machine learning models were trained and evaluated on the development dataset and compared to internal medicine physicians and risk scores in the independent validation dataset. The primary outcome was 31-day mortality.
RESULTS: A number of 1,344 patients were included of whom 174 (13.0%) died. Machine learning models trained with laboratory or a combination of laboratory + clinical data achieved an area-under-the ROC curve of 0.82 (95% CI: 0.80-0.84) and 0.84 (95% CI: 0.81-0.87) for predicting 31-day mortality, respectively. In the validation set, models outperformed internal medicine physicians and clinical risk scores in sensitivity (92% vs. 72% vs. 78%;p<0.001,all comparisons) while retaining comparable specificity (78% vs. 74% vs. 72%;p>0.02). The model had higher diagnostic accuracy with an area-under-the-ROC curve of 0.85 (95%CI: 0.78-0.92) compared to abbMEDS (0.63,0.54-0.73), mREMS (0.63,0.54-0.72) and internal medicine physicians (0.74,0.65-0.82).
CONCLUSION: Machine learning models outperformed internal medicine physicians and clinical risk scores in predicting 31-day mortality. These models are a promising tool to aid in risk stratification of patients presenting to the ED with sepsis.

Entities:  

Mesh:

Year:  2021        PMID: 33465096      PMCID: PMC7815112          DOI: 10.1371/journal.pone.0245157

Source DB:  PubMed          Journal:  PLoS One        ISSN: 1932-6203            Impact factor:   3.240


  34 in total

1.  From Local Explanations to Global Understanding with Explainable AI for Trees.

Authors:  Scott M Lundberg; Gabriel Erion; Hugh Chen; Alex DeGrave; Jordan M Prutkin; Bala Nair; Ronit Katz; Jonathan Himmelfarb; Nisha Bansal; Su-In Lee
Journal:  Nat Mach Intell       Date:  2020-01-17

2.  The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3).

Authors:  Mervyn Singer; Clifford S Deutschman; Christopher Warren Seymour; Manu Shankar-Hari; Djillali Annane; Michael Bauer; Rinaldo Bellomo; Gordon R Bernard; Jean-Daniel Chiche; Craig M Coopersmith; Richard S Hotchkiss; Mitchell M Levy; John C Marshall; Greg S Martin; Steven M Opal; Gordon D Rubenfeld; Tom van der Poll; Jean-Louis Vincent; Derek C Angus
Journal:  JAMA       Date:  2016-02-23       Impact factor: 56.272

Review 3.  2001 SCCM/ESICM/ACCP/ATS/SIS International Sepsis Definitions Conference.

Authors:  Mitchell M Levy; Mitchell P Fink; John C Marshall; Edward Abraham; Derek Angus; Deborah Cook; Jonathan Cohen; Steven M Opal; Jean-Louis Vincent; Graham Ramsay
Journal:  Crit Care Med       Date:  2003-04       Impact factor: 7.598

4.  A Gradient Boosting Machine Learning Model for Predicting Early Mortality in the Emergency Department Triage: Devising a Nine-Point Triage Score.

Authors:  Maximiliano Klug; Yiftach Barash; Sigalit Bechler; Yehezkel S Resheff; Talia Tron; Avi Ironi; Shelly Soffer; Eyal Zimlichman; Eyal Klang
Journal:  J Gen Intern Med       Date:  2019-11-01       Impact factor: 5.128

5.  Explainable machine-learning predictions for the prevention of hypoxaemia during surgery.

Authors:  Scott M Lundberg; Bala Nair; Monica S Vavilala; Mayumi Horibe; Michael J Eisses; Trevor Adams; David E Liston; Daniel King-Wai Low; Shu-Fang Newman; Jerry Kim; Su-In Lee
Journal:  Nat Biomed Eng       Date:  2018-10-10       Impact factor: 25.671

6.  Comparison of severity of illness scoring systems in the prediction of hospital mortality in severe sepsis and septic shock.

Authors:  Colleen A Crowe; Erik B Kulstad; Chintan D Mistry; Christine E Kulstad
Journal:  J Emerg Trauma Shock       Date:  2010-10

7.  Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial.

Authors:  David W Shimabukuro; Christopher W Barton; Mitchell D Feldman; Samson J Mataraso; Ritankar Das
Journal:  BMJ Open Respir Res       Date:  2017-11-09

8.  Performance Assessment of the Mortality in Emergency Department Sepsis Score, Modified Early Warning Score, Rapid Emergency Medicine Score, and Rapid Acute Physiology Score in Predicting Survival Outcomes of Adult Renal Abscess Patients in the Emergency Department.

Authors:  Su-Han Chang; Chiao-Hsuan Hsieh; Yi-Ming Weng; Ming-Shun Hsieh; Zhong Ning Leonard Goh; Hsien-Yi Chen; Tung Chang; Chip-Jin Ng; Joanna Chen-Yeen Seak; Chen-Ken Seak; Chen-June Seak
Journal:  Biomed Res Int       Date:  2018-09-19       Impact factor: 3.411

9.  LiSep LSTM: A Machine Learning Algorithm for Early Detection of Septic Shock.

Authors:  Josef Fagerström; Magnus Bång; Daniel Wilhelms; Michelle S Chew
Journal:  Sci Rep       Date:  2019-10-22       Impact factor: 4.379

10.  Interrater reliability: the kappa statistic.

Authors:  Mary L McHugh
Journal:  Biochem Med (Zagreb)       Date:  2012       Impact factor: 2.313

View more
  14 in total

1.  Prognostic tools for elderly patients with sepsis: in search of new predictive models.

Authors:  Fernando-Miguel Gamboa-Antiñolo
Journal:  Intern Emerg Med       Date:  2021-04-13       Impact factor: 3.397

2.  Identifying infected patients using semi-supervised and transfer learning.

Authors:  Fereshteh S Bashiri; John R Caskey; Anoop Mayampurath; Nicole Dussault; Jay Dumanian; Sivasubramanium V Bhavani; Kyle A Carey; Emily R Gilbert; Christopher J Winslow; Nirav S Shah; Dana P Edelson; Majid Afshar; Matthew M Churpek
Journal:  J Am Med Inform Assoc       Date:  2022-09-12       Impact factor: 7.942

3.  Explainable Machine-Learning Model for Prediction of In-Hospital Mortality in Septic Patients Requiring Intensive Care Unit Readmission.

Authors:  Chang Hu; Lu Li; Yiming Li; Fengyun Wang; Bo Hu; Zhiyong Peng
Journal:  Infect Dis Ther       Date:  2022-07-14

4.  Is the crystal ball broken? Another external validation of the post-withdrawal seizure-relapse prediction model.

Authors:  Samuel W Terman; Herm J Lamberink; Geertruida Slinger; Willem M Otte; James F Burke; Kees P J Braun
Journal:  Epilepsia       Date:  2021-10-11       Impact factor: 6.740

5.  Evaluating machine learning models for sepsis prediction: A systematic review of methodologies.

Authors:  Hong-Fei Deng; Ming-Wei Sun; Yu Wang; Jun Zeng; Ting Yuan; Ting Li; Di-Huan Li; Wei Chen; Ping Zhou; Qi Wang; Hua Jiang
Journal:  iScience       Date:  2021-12-20

6.  Development and Structure of an Accurate Machine Learning Algorithm to Predict Inpatient Mortality and Hospice Outcomes in the Coronavirus Disease 2019 Era.

Authors:  Stephen Chi; Aixia Guo; Kevin Heard; Seunghwan Kim; Randi Foraker; Patrick White; Nathan Moore
Journal:  Med Care       Date:  2022-05-01       Impact factor: 2.983

7.  Rise of the Machines? Predicting Brivaracetam Response Using Machine Learning.

Authors:  Samuel W Terman
Journal:  Epilepsy Curr       Date:  2021-10-15       Impact factor: 7.500

Review 8.  Machine learning techniques for mortality prediction in emergency departments: a systematic review.

Authors:  Amin Naemi; Thomas Schmidt; Marjan Mansourvar; Mohammad Naghavi-Behzad; Ali Ebrahimi; Uffe Kock Wiil
Journal:  BMJ Open       Date:  2021-11-02       Impact factor: 2.692

Review 9.  Machine Learning for Cardiovascular Outcomes From Wearable Data: Systematic Review From a Technology Readiness Level Point of View.

Authors:  Arman Naseri Jahfari; David Tax; Marcel Reinders; Ivo van der Bilt
Journal:  JMIR Med Inform       Date:  2022-01-19

Review 10.  Artificial Intelligence in Infection Management in the ICU.

Authors:  Thomas De Corte; Sofie Van Hoecke; Jan De Waele
Journal:  Crit Care       Date:  2022-03-22       Impact factor: 9.097

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.