Literature DB >> 33711001

A Simulated Prospective Evaluation of a Deep Learning Model for Real-Time Prediction of Clinical Deterioration Among Ward Patients.

Parth K Shah1, Jennifer C Ginestra2, Lyle H Ungar3, Paul Junker4, Jeff I Rohrbach4, Neil O Fishman5, Gary E Weissman2,5.   

Abstract

OBJECTIVES: The National Early Warning Score, Modified Early Warning Score, and quick Sepsis-related Organ Failure Assessment can predict clinical deterioration. These scores exhibit only moderate performance and are often evaluated using aggregated measures over time. A simulated prospective validation strategy that assesses multiple predictions per patient-day would provide the best pragmatic evaluation. We developed a deep recurrent neural network deterioration model and conducted a simulated prospective evaluation.
DESIGN: Retrospective cohort study.
SETTING: Four hospitals in Pennsylvania. PATIENTS: Inpatient adults discharged between July 1, 2017, and June 30, 2019.
INTERVENTIONS: None.
MEASUREMENTS AND MAIN RESULTS: We trained a deep recurrent neural network and logistic regression model using data from electronic health records to predict hourly the 24-hour composite outcome of transfer to ICU or death. We analyzed 146,446 hospitalizations with 16.75 million patient-hours. The hourly event rate was 1.6% (12,842 transfers or deaths, corresponding to 260,295 patient-hours within the predictive horizon). On a hold-out dataset, the deep recurrent neural network achieved an area under the precision-recall curve of 0.042 (95% CI, 0.04-0.043), comparable with logistic regression model (0.043; 95% CI 0.041 to 0.045), and outperformed National Early Warning Score (0.034; 95% CI, 0.032-0.035), Modified Early Warning Score (0.028; 95% CI, 0.027- 0.03), and quick Sepsis-related Organ Failure Assessment (0.021; 95% CI, 0.021-0.022). For a fixed sensitivity of 50%, the deep recurrent neural network achieved a positive predictive value of 3.4% (95% CI, 3.4-3.5) and outperformed logistic regression model (3.1%; 95% CI 3.1-3.2), National Early Warning Score (2.0%; 95% CI, 2.0-2.0), Modified Early Warning Score (1.5%; 95% CI, 1.5-1.5), and quick Sepsis-related Organ Failure Assessment (1.5%; 95% CI, 1.5-1.5).
CONCLUSIONS: Commonly used early warning scores for clinical decompensation, along with a logistic regression model and a deep recurrent neural network model, show very poor performance characteristics when assessed using a simulated prospective validation. None of these models may be suitable for real-time deployment.
Copyright © 2021 by the Society of Critical Care Medicine and Wolters Kluwer Health, Inc. All Rights Reserved.

Entities:  

Mesh:

Year:  2021        PMID: 33711001      PMCID: PMC8282687          DOI: 10.1097/CCM.0000000000004966

Source DB:  PubMed          Journal:  Crit Care Med        ISSN: 0090-3493            Impact factor:   9.296


  35 in total

1.  Early warning systems: the next level of rapid response.

Authors:  Kathy D Duncan; Christine McMullan; Barbara M Mills
Journal:  Nursing       Date:  2012-02

2.  A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models.

Authors:  Evangelia Christodoulou; Jie Ma; Gary S Collins; Ewout W Steyerberg; Jan Y Verbakel; Ben Van Calster
Journal:  J Clin Epidemiol       Date:  2019-02-11       Impact factor: 6.437

3.  Semi-supervised learning of the electronic health record for phenotype stratification.

Authors:  Brett K Beaulieu-Jones; Casey S Greene
Journal:  J Biomed Inform       Date:  2016-10-12       Impact factor: 6.317

4.  Quick Sepsis-related Organ Failure Assessment, Systemic Inflammatory Response Syndrome, and Early Warning Scores for Detecting Clinical Deterioration in Infected Patients outside the Intensive Care Unit.

Authors:  Matthew M Churpek; Ashley Snyder; Xuan Han; Sarah Sokol; Natasha Pettit; Michael D Howell; Dana P Edelson
Journal:  Am J Respir Crit Care Med       Date:  2017-04-01       Impact factor: 21.405

5.  Development and validation of an electronic medical record-based alert score for detection of inpatient deterioration outside the ICU.

Authors:  Patricia Kipnis; Benjamin J Turk; David A Wulf; Juan Carlos LaGuardia; Vincent Liu; Matthew M Churpek; Santiago Romero-Brufau; Gabriel J Escobar
Journal:  J Biomed Inform       Date:  2016-09-20       Impact factor: 6.317

6.  Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): the TRIPOD statement.

Authors:  Gary S Collins; Johannes B Reitsma; Douglas G Altman; Karel G M Moons
Journal:  Ann Intern Med       Date:  2015-01-06       Impact factor: 25.391

Review 7.  Performance of the quick Sequential (sepsis-related) Organ Failure Assessment score as a prognostic tool in infected patients outside the intensive care unit: a systematic review and meta-analysis.

Authors:  Jae-Uk Song; Cheol Kyung Sin; Hye Kyeong Park; Sung Ryul Shim; Jonghoo Lee
Journal:  Crit Care       Date:  2018-02-06       Impact factor: 9.097

8.  Comparison of Early Warning Scoring Systems for Hospitalized Patients With and Without Infection at Risk for In-Hospital Mortality and Transfer to the Intensive Care Unit.

Authors:  Vincent X Liu; Yun Lu; Kyle A Carey; Emily R Gilbert; Majid Afshar; Mary Akel; Nirav S Shah; John Dolan; Christopher Winslow; Patricia Kipnis; Dana P Edelson; Gabriel J Escobar; Matthew M Churpek
Journal:  JAMA Netw Open       Date:  2020-05-01

9.  Early warning scores for detecting deterioration in adult hospital patients: systematic review and critical appraisal of methodology.

Authors:  Stephen Gerry; Timothy Bonnici; Jacqueline Birks; Shona Kirtley; Pradeep S Virdee; Peter J Watkinson; Gary S Collins
Journal:  BMJ       Date:  2020-05-20

10.  Emergency department triage prediction of clinical outcomes using machine learning models.

Authors:  Yoshihiko Raita; Tadahiro Goto; Mohammad Kamal Faridi; David F M Brown; Carlos A Camargo; Kohei Hasegawa
Journal:  Crit Care       Date:  2019-02-22       Impact factor: 9.097

View more
  1 in total

1.  Sepsis Prediction for the General Ward Setting.

Authors:  Sean C Yu; Aditi Gupta; Kevin D Betthauser; Patrick G Lyons; Albert M Lai; Marin H Kollef; Philip R O Payne; Andrew P Michelson
Journal:  Front Digit Health       Date:  2022-03-08
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.