20 Outcome Study of Mild Traumatic Brain Injury Patients Integrating a Brain Electrical Activity-Based Decision Rule

Document Type

Conference Proceeding

Publication Date

10-2022

Publication Title

Annals of Emergency Medicine

Abstract

Background / Study Objectives

Clinical decision rules such as the Canadian Head CT rule have high sensitivity but lack specificity for identifying significant intracranial findings when evaluating patients with mild traumatic brain injury (mTBI). Advances in brain electrical activity (EEG) signal processing, real-time analyses, and use of an AI/machine learning for the derivation of brain activity-based biomarkers have greatly enhanced the pragmatism of EEG clinically. High accuracy and negative predictive value have been demonstrated (n-720) using an FDA cleared brain activity-based multivariate algorithm for predicting the likelihood of intracranial injuries with ≥ 1mL blood visible on a CT scan. The SIC algorithm was derived using machine learning to identify distinctive waveform patterns in these mTBI patients. The purpose of this study was to evaluate the utility of an EEG-based structural injury classification (SIC) when added to the clinical evaluation of mTBI patients.

Study Design / Methods

A multi-center, prospective observational cohort study. Patients were eligible that were 18-85 years, sought ED care for traumatic closed head injury within 72 hours, and had a GCS 14-15. We excluded patients with conditions that prevented application of electrodes on the forehead, known neurological disease such as dementia or stroke, use of anticoagulants, age <18 >years, and those with acute psychosis. We collected 5-10 minutes of eyes-closed EEG from frontal and frontotemporal regions, using an FDA cleared EEG-based algorithm (SIC). Clinician evaluations and imaging were conducted as per standard care with the addition of acquiring and sharing the results of the SIC algorithm with the clinicians. Clinicians were educated on the results of previous clinical trials utilizing this algorithm prior to study start up. Follow-ups included a symptom inventory and information on the need for additional clinical care or neuroimaging evaluation and was conducted by phone 72-96 hours after the initial evaluation.

Results / Findings

We present the results of the 142 subjects enrolled with a negative SIC result (those identified as likely no structural injury visible on CT). Their average age was 31.2 (18.3-75.3 years) and 86 (58%) were female. The most common injury was motor vehicle accident (70%). Treating clinicians nevertheless performed head CT on 36 (25%) participants, all of which were CT negative. Treating clinicians discharged the remaining 106 (75%) SIC negative participants without neuroimaging. In follow-up, 2 of these 106 participants returned to the hospital and received CT scans, both of which were found to be negative.

Conclusion

Integration of a rapid EEG-based algorithm in the evaluation of mTBI has the potential to reduce the utilization of neuroimaging.

Volume

80

Issue

4 Supplement

First Page

S10

DOI

10.1016/j.annemergmed.2022.08.043

Link to Full Text

Share

COinS