ER2 and Deep Learning for Prediction of Adverse Health Outcomes

Emergency Room Evaluation for Older Users of Emergency Departments: Predicting Adverse Health Outcomes With Deep Learning Algorithms

An Emergency Department (ED) visit for an older adult is a high-risk medical intervention. Known adverse events (AE) include delirium, prolonged ED or hospital stay, hospitalization, recurrent ED visits and hospital death. These happen in a growing proportion in ED visitors over age 65 are over who are represented in ED visits.

Tools predicting AEs in the ED are of paramount importance to help decision-making on patient triage and disposition. They can help identify areas of unmet needs for seniors in order to develop targeted actions. Multiple scoring systems including "Programme de recherche sur l'intégration des services de maintien de l'autonomie" (PRISMA-7), Identification of Seniors at Risk (ISAR), Clinical Frailty Scale (CFS), Brief Geriatric Assessment (BGA) have extensively been studied in the ED and other settings for various outcomes. These tools rely on a simple scoring system that minimally trained staff can reliably and quickly administer. Doing otherwise is unlikely to be applicable to daily clinical practice.

As prediction accuracy has not significantly improved in the past decade, perhaps new analysis strategies are necessary. The current hype surrounding deep learning comes from better and cheaper hardware and the availability of simple and open-source libraries supported by large companies and a broad community of users. Hence, implementing deep learning (DL) algorithms is now open to a wide range of settings, including medical care in a standard clinical practice. DL has been shown to be more accurate than the average board-certified specialist on very specific tasks. Prediction of various clinical outcomes has produced less dramatic results, perhaps as traditional (non-DL) models already outperformed clinicians for many disease states. Published DL approaches applied to outcome prediction in the ED have focused on acutely ill adults in general, specific conditions or administrative issues such as admitting department or ED overcrowding. None have targeted a specific age group like older ED visitors.

An important caveat to many DL approaches is interpretation of results. To develop interventions based on targeted features associated with AEs in a given model, it has to be somewhat transparent. If multiple layers of NNs improve prediction compared to linear regression, they often provide no clinically relevant insight on how and which variables interact to yield that result.

Study Overview

• Status: Withdrawn
• Conditions: Emergencies
• Intervention / Treatment: Other: ER2

• Study Type: Observational

Contacts and Locations

Study Locations

• Canada
  • Quebec
    • Montréal, Quebec, Canada, H3T 1E2
      • Jewish General Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 71 years and older (Older Adult)
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Between September 2017 and July 2020, 47 000 Emergency Department visits met the selection criteria. Training DL models on tabular data has been shown to be less effective than on unstructured sources such as images or sound. An appropriate mitigation strategy is to increase the quantity of data. Hence, all participants of the ER2 database will be included in the analysis. All visits will be included in the analysis.

Description

Inclusion Criteria:

• Age above 75 years old
• Unplanned Emergency department visit

Exclusion Criteria:

• Do not meet inclusion criteria

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Other

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
ER2 participants; all participants of ER2 database will be included in the analysis	Other: ER2; No intervention, data analysis only

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
ED length of stay	The length of emergencey department stay is defined as the average number of hours that patients spend in Emergency department.	through database constitution, from September 2017 to July 2020

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Prolonged hospital stay	The prolonged length of hospital stay is defined as a stay above the average number of days that patients spend in hospital	through database constitution, from September 2017 to July 2020
Number of partciipants with at least one hospitalizations	Defined as the admission in hospital after an admission in Emergency department	through database constitution, from September 2017 to July 2020
recurrent ED visits	Defined as all the Emergency department recurrent visit within 30 days	through database constitution, from September 2017 to July 2020
Number of partciipants with diagnosis of delirium	Defined as a diagnosis of delirium in teh medical chart of the patient	through database constitution, from September 2017 to July 2020
Number of partciipants with hospital death	Defined as a reported death during hospitalization	through database constitution, from September 2017 to July 2020

Collaborators and Investigators

• Sponsor: Jewish General Hospital
• Investigators: Principal Investigator: Olivier Beauchet, MD, McGill University

Study record dates

Study Major Dates

• Study Start (Actual): February 24, 2023
• Primary Completion (Actual): February 24, 2023
• Study Completion (Actual): February 24, 2023

Study Registration Dates

• First Submitted: December 14, 2020
• First Submitted That Met QC Criteria: December 17, 2020
• First Posted (Actual): December 22, 2020

Study Record Updates

• Last Update Posted (Actual): July 23, 2024
• Last Update Submitted That Met QC Criteria: July 22, 2024
• Last Verified: July 1, 2024

More Information

Terms related to this study

• Keywords: Geriatrics; Deep learning; Emergency rooms; adverse health events prevention
• Additional Relevant MeSH Terms: Pathologic Processes; Disease Attributes; Emergencies
• Other Study ID Numbers: 2021-2699

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No