Article Text

Download PDFPDF
Alerting on mortality among patients discharged from the emergency department: a machine learning model
  1. Yiftach Barash1,2,3,
  2. Shelly Soffer2,3,
  3. Ehud Grossman2,4,
  4. Noam Tau1,2,
  5. Vera Sorin1,2,
  6. Eyal BenDavid2,
  7. Avinoah Irony2,5,
  8. Eli Konen1,2,
  9. Eyal Zimlichman2,6,
  10. Eyal Klang1,2,3
  1. 1Department of Diagnostic Imaging, The Chaim Sheba Medical Center, Ramat Gan, Israel
  2. 2Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
  3. 3DeepVision lab, The Chaim Sheba Medical Center, Ramat Gan, Israel
  4. 4Internal Medicine, The Chaim Sheba Medical Center, Ramat Gan, Israel
  5. 5Emergency Department, The Chaim Sheba Medical Center, Ramat Gan, Israel
  6. 6Hospital Management, The Chaim Sheba Medcical Center, Ramat Gan, Israel
  1. Correspondence to Dr Eyal Klang, Chaim Sheba Medical Center, Tel Hashomer, Israel; eyalkla{at}


Objectives Physicians continuously make tough decisions when discharging patients. Alerting on poor outcomes may help in this decision. This study evaluates a machine learning model for predicting 30-day mortality in emergency department (ED) discharged patients.

Methods We retrospectively analysed visits of adult patients discharged from a single ED (1/2014–12/2018). Data included demographics, evaluation and treatment in the ED, and discharge diagnosis. The data comprised of both structured and free-text fields. A gradient boosting model was trained to predict mortality within 30 days of release from the ED. The model was trained on data from the years 2014–2017 and validated on data from the year 2018. In order to reduce potential end-of-life bias, a subgroup analysis was performed for non-oncological patients.

Results Overall, 363 635 ED visits of discharged patients were analysed. The 30-day mortality rate was 0.8%. A majority of the mortality cases (65.3%) had a known oncological disease. The model yielded an area under the curve (AUC) of 0.97 (95% CI 0.96 to 0.97) for predicting 30-day mortality. For a sensitivity of 84% (95% CI 0.81 to 0.86), this model had a false positive rate of 1:20. For patients without a known malignancy, the model yielded an AUC of 0.94 (95% CI 0.92 to 0.95).

Conclusions Although not frequent, patients may die following ED discharge. Machine learning-based tools may help ED physicians identify patients at risk. An optimised decision for hospitalisation or palliative management may improve patient care and system resource allocation.

  • accident & emergency medicine
  • information technology

Statistics from


  • Contributors EKl had full access to all of the data in the study and takes responsibility for the integrity of the data and the accuracy of the data analysis. Concept and design: EKl, YB, SS. Acquisition, analysis or interpretation of data: EKl, SS, EG, NT, VS, EBD, AI, EKo, EZ, YB. Drafting of the manuscript: YB, EKl, SS. Critical revision of the manuscript for important intellectual content: EKl, SS, EG, NT, VS, EBD, AI, EKo, EZ, YB. Algorithm design and statistical analysis: EKl. Administrative, technical or material support: EKl, SS, EG, NT, VS, EBD, AI, EKo, EZ, YB. Supervision: EKl, EZ, EG, EKo.

  • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

  • Competing interests None declared.

  • Patient consent for publication Not required.

  • Provenance and peer review Not commissioned; externally peer reviewed.

  • Data availability statement Data may be obtained from a third party and are not publicly available. This is a large hospital cohort protected by IRB.

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.