Optimizing Concussion Care Seeking - Using Machine Learning to Predict Delayed Concussion Reporting

Aug 5, 2026

Upload by Maeve

Early medical attention after concussion can reduce symptom duration and burden, yet many concussions remain undiagnosed or are diagnosed late because key symptoms are not visible and rely on timely injury reporting. This case-control secondary analysis used Concussion Assessment, Research and Education (CARE) Consortium data to identify individual and institutional factors predicting immediate versus delayed reporting. Models achieved mean accuracies of 55.8%–62.6%, with institutional variables improving prediction by 1–6 percentage points, highlighting resource allocation pathways.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Background

Purpose

Study design

Methods

Results

Conclusion

Optimizing Concussion Care Seeking Using Machine Learning to Predict Delayed Concussion Reporting Emily Kroshus-Havril,* ScD, MPH , Daniel D. Leeds, PhD, Thomas W. McAllister, MD, Zachary Yukio Kerr, PhD, MPH , Kristen Knight, PhD, Johna K. Register-Mihalik, PhD, ATC, Robert C. Lynall, PhD, ATC , Christopher D’Lauro, PhD, Yuet Ho, BS, Muhibur Rahman, BS, Julianne D. Schmidt, PhD, ATC , and the CARE Consortium Investigators Investigation performed at the University of Georgia, Athens, Georgia, USA Background: Early medical attention after concussion may minimize symptom duration and burden; however, many concussions are undiagnosed or have a delay in diagnosis after injury. Many concussion symptoms (eg, headache, dizziness) are not visible, meaning that early identification is often contingent on individuals reporting their injury to medical staff. A fundamental understanding of the types and levels of factors that explain when concussions are reported can help identify promising directions for intervention. Purpose: To identify individual and institutional factors that predict immediate (vs delayed) injury reporting. Study Design: Case-control study; Level of evidence, 3 . Methods: This study was a secondary analysis of data from the Concussion Assessment, Research and Education (CARE) Consortium study. The sample included 3213 collegiate athletes and military service academy cadets who were diagnosed with a concussion during the study period. Participants were from 27 civilian institutions and 3 military institutions in the United States. Machine learning techniques were used to build models predicting who would report an injury immediately after a concussive event (measured by an athletic trainer denoting the injury as being reported ‘‘immediately’’ or ‘‘at a delay’’), including both individual athlete/cadet and institutional characteristics. Results: In the sample as a whole, combining individual factors enabled prediction of reporting immediacy, with mean accuracies between 55.8% and 62.6%, depending on classifier type and sample subset; adding institutional factors improved reporting prediction accuracies by 1 to 6 percentage points. At the individual level, injury-related altered mental status and loss of consciousness were most predictive of immediate reporting, which may be the result of observable signs leading to the injury report being externally mediated. At the institutional level, important attributes included athletic department annual revenue and ratio of athletes to athletic trainers. Conclusion: Further study is needed on the pathways through which institutional decisions about resource allocation, including decisions about sports medicine staffing, may contribute to reporting immediacy. More broadly, the relatively low accuracy of the machine learning models tested suggests the importance of continued expansion in how reporting is understood and facilitated. Keywords: concussion; care seeking; machine learning; college Concussions are a common injury in contact and collision activities, such as organized sport and military training.3,18 Early medical attention after injury is important to minimize symptom duration and burden.5 Despite this knowledge, estimates suggest that approximately half of concussions are never diagnosed, and of those that are diagnosed, another half are diagnosed at a delay.2,8,16 Some postinjury signs (eg, loss of consciousness [LOC]) are immediately observable, meaning that personnel in The American Journal of Sports Medicine 2024;52(9):2372–2383 DOI: 10.1177/03635465241259455 the injured individual’s environment can facilitate identification and medical attention. However, many symptoms (eg, headache, dizziness) are not visible, such that early medical attention is often contingent on honest and timely care seeking by individuals. With the goal of increasing timely diagnosis of concussion, leading sport and military organizations have prioritized concus

FAQs

Why is concussion reporting often delayed despite the importance of early care?

Many concussion symptoms are not visible, so early medical attention depends on individuals seeking care and reporting the injury honestly and promptly.

What factors were most predictive of immediate concussion reporting in the study?

At the individual level, altered mental status and loss of consciousness were most predictive of immediate reporting.

How did institutional characteristics affect the machine learning predictions?

Adding institutional factors improved reporting prediction accuracy by 1 to 6 percentage points; key attributes included athletic department annual revenue and the athlete-to-athletic-trainer ratio.

Aug 5, 2026

Upload by Maeve