Comparing the predictive ability of a commercial artificial intelligence early warning system with physician judgement for clinical deterioration in hospitalised general internal medicine patients: a prospective observational study

Objective Our study compares physician judgement with an automated early warning system (EWS) for predicting clinical deterioration of hospitalised general internal medicine patients.Design Prospective observational study of clinical predictions made at the end of the daytime work-shift for an acade...

Full description

Saved in:
Bibliographic Details
Main Authors: Jonathan Arnold, Alex Davis, Baruch Fischhoff, Emmanuelle Yecies, Jon Grace, Andrew Klobuka, Deepika Mohan, Janel Hanmer
Format: Article
Language:English
Published: BMJ Publishing Group 2019-10-01
Series:BMJ Open
Online Access:https://bmjopen.bmj.com/content/9/10/e032187.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060676095016960
author Jonathan Arnold
Alex Davis
Baruch Fischhoff
Emmanuelle Yecies
Jon Grace
Andrew Klobuka
Deepika Mohan
Janel Hanmer
author_facet Jonathan Arnold
Alex Davis
Baruch Fischhoff
Emmanuelle Yecies
Jon Grace
Andrew Klobuka
Deepika Mohan
Janel Hanmer
author_sort Jonathan Arnold
collection DOAJ
description Objective Our study compares physician judgement with an automated early warning system (EWS) for predicting clinical deterioration of hospitalised general internal medicine patients.Design Prospective observational study of clinical predictions made at the end of the daytime work-shift for an academic general internal medicine floor team compared with the risk assessment from an automated EWS collected at the same time.Setting Internal medicine teaching wards at a single tertiary care academic medical centre in the USA.Participants Intern physicians working on the internal medicine wards and an automated EWS (Rothman Index by PeraHealth).Outcome Clinical deterioration within 24 hours including cardiac or pulmonary arrest, rapid response team activation or unscheduled intensive care unit transfer.Results We collected predictions for 1874 patient days and saw 35 clinical deteriorations (1.9%). The area under the receiver operating curve (AUROC) for the EWS was 0.73 vs 0.70 for physicians (p=0.571). A linear regression model combining physician and EWS predictions had an AUROC of 0.75, outperforming physicians (p=0.016) and the EWS (p=0.05).Conclusions There is no significant difference in the performance of the EWS and physicians in predicting clinical deterioration at 24 hours on an inpatient general medicine ward. A combined model outperformed either alone. The EWS and physicians identify partially overlapping sets of at-risk patients suggesting they rely on different cues or decision rules for their predictions.Trial registration number NCT02648828.
format Article
id doaj-art-891d025e967f48879f4f89d3572cbc4c
institution DOAJ
issn 2044-6055
language English
publishDate 2019-10-01
publisher BMJ Publishing Group
record_format Article
series BMJ Open
spelling doaj-art-891d025e967f48879f4f89d3572cbc4c2025-08-20T02:50:29ZengBMJ Publishing GroupBMJ Open2044-60552019-10-0191010.1136/bmjopen-2019-032187Comparing the predictive ability of a commercial artificial intelligence early warning system with physician judgement for clinical deterioration in hospitalised general internal medicine patients: a prospective observational studyJonathan Arnold0Alex Davis1Baruch Fischhoff2Emmanuelle Yecies3Jon Grace4Andrew Klobuka5Deepika Mohan6Janel Hanmer71 Division of General Internal Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA2 Engineering and Public Policy, Carnegie Mellon University College of Engineering, Pittsburgh, Pennsylvania, USA2 Engineering and Public Policy, Carnegie Mellon University College of Engineering, Pittsburgh, Pennsylvania, USA1 Division of General Internal Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA3 Division of Pulmonary & Critical Care Medicine, University of Michigan Department of Internal Medicine, Ann Arbor, Michigan, USA4 Department of Radiology, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA5 Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA1 Division of General Internal Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USAObjective Our study compares physician judgement with an automated early warning system (EWS) for predicting clinical deterioration of hospitalised general internal medicine patients.Design Prospective observational study of clinical predictions made at the end of the daytime work-shift for an academic general internal medicine floor team compared with the risk assessment from an automated EWS collected at the same time.Setting Internal medicine teaching wards at a single tertiary care academic medical centre in the USA.Participants Intern physicians working on the internal medicine wards and an automated EWS (Rothman Index by PeraHealth).Outcome Clinical deterioration within 24 hours including cardiac or pulmonary arrest, rapid response team activation or unscheduled intensive care unit transfer.Results We collected predictions for 1874 patient days and saw 35 clinical deteriorations (1.9%). The area under the receiver operating curve (AUROC) for the EWS was 0.73 vs 0.70 for physicians (p=0.571). A linear regression model combining physician and EWS predictions had an AUROC of 0.75, outperforming physicians (p=0.016) and the EWS (p=0.05).Conclusions There is no significant difference in the performance of the EWS and physicians in predicting clinical deterioration at 24 hours on an inpatient general medicine ward. A combined model outperformed either alone. The EWS and physicians identify partially overlapping sets of at-risk patients suggesting they rely on different cues or decision rules for their predictions.Trial registration number NCT02648828.https://bmjopen.bmj.com/content/9/10/e032187.full
spellingShingle Jonathan Arnold
Alex Davis
Baruch Fischhoff
Emmanuelle Yecies
Jon Grace
Andrew Klobuka
Deepika Mohan
Janel Hanmer
Comparing the predictive ability of a commercial artificial intelligence early warning system with physician judgement for clinical deterioration in hospitalised general internal medicine patients: a prospective observational study
BMJ Open
title Comparing the predictive ability of a commercial artificial intelligence early warning system with physician judgement for clinical deterioration in hospitalised general internal medicine patients: a prospective observational study
title_full Comparing the predictive ability of a commercial artificial intelligence early warning system with physician judgement for clinical deterioration in hospitalised general internal medicine patients: a prospective observational study
title_fullStr Comparing the predictive ability of a commercial artificial intelligence early warning system with physician judgement for clinical deterioration in hospitalised general internal medicine patients: a prospective observational study
title_full_unstemmed Comparing the predictive ability of a commercial artificial intelligence early warning system with physician judgement for clinical deterioration in hospitalised general internal medicine patients: a prospective observational study
title_short Comparing the predictive ability of a commercial artificial intelligence early warning system with physician judgement for clinical deterioration in hospitalised general internal medicine patients: a prospective observational study
title_sort comparing the predictive ability of a commercial artificial intelligence early warning system with physician judgement for clinical deterioration in hospitalised general internal medicine patients a prospective observational study
url https://bmjopen.bmj.com/content/9/10/e032187.full
work_keys_str_mv AT jonathanarnold comparingthepredictiveabilityofacommercialartificialintelligenceearlywarningsystemwithphysicianjudgementforclinicaldeteriorationinhospitalisedgeneralinternalmedicinepatientsaprospectiveobservationalstudy
AT alexdavis comparingthepredictiveabilityofacommercialartificialintelligenceearlywarningsystemwithphysicianjudgementforclinicaldeteriorationinhospitalisedgeneralinternalmedicinepatientsaprospectiveobservationalstudy
AT baruchfischhoff comparingthepredictiveabilityofacommercialartificialintelligenceearlywarningsystemwithphysicianjudgementforclinicaldeteriorationinhospitalisedgeneralinternalmedicinepatientsaprospectiveobservationalstudy
AT emmanuelleyecies comparingthepredictiveabilityofacommercialartificialintelligenceearlywarningsystemwithphysicianjudgementforclinicaldeteriorationinhospitalisedgeneralinternalmedicinepatientsaprospectiveobservationalstudy
AT jongrace comparingthepredictiveabilityofacommercialartificialintelligenceearlywarningsystemwithphysicianjudgementforclinicaldeteriorationinhospitalisedgeneralinternalmedicinepatientsaprospectiveobservationalstudy
AT andrewklobuka comparingthepredictiveabilityofacommercialartificialintelligenceearlywarningsystemwithphysicianjudgementforclinicaldeteriorationinhospitalisedgeneralinternalmedicinepatientsaprospectiveobservationalstudy
AT deepikamohan comparingthepredictiveabilityofacommercialartificialintelligenceearlywarningsystemwithphysicianjudgementforclinicaldeteriorationinhospitalisedgeneralinternalmedicinepatientsaprospectiveobservationalstudy
AT janelhanmer comparingthepredictiveabilityofacommercialartificialintelligenceearlywarningsystemwithphysicianjudgementforclinicaldeteriorationinhospitalisedgeneralinternalmedicinepatientsaprospectiveobservationalstudy