Rebecca Blundell, Christine d’Offay, Charles Hand, Daniel Tadmor, Alan Carson, David Gillespie, Matthew Reed, Aimun A. B. Jamjoom.
Abstract
Individuals who sustain a concussion can experience a range of symptoms which can significantly impact their quality of life and functional outcome. This study aims to understand the nature and recovery trajectories of post-concussion symptomatology by applying an unsupervised machine learning approach to data captured from a digital health intervention (HeadOn).
Introduction
Individuals who sustain a concussion can experience a constellation of post-concussion symptoms, including physical (e.g., headaches and dizziness), cognitive (e.g., difficulty concentrating and memory problems), emotional (e.g., depression and anxiety) symptoms and sleep disturbance (hypo- or hyper-somnolence) [1].
Materials and methods
HeadOn is a digital health intervention designed to support patients with their recovery after a concussion (Fig 1). It was developed using a systematic evidence-, theory-, and person-based approach and the Medical Research Council (MRC) guidance on the development of complex interventions [9,10].
Results
A total of 94 patients were included in the study. Average patient age was 41(±16) and 65.9% were female. At the time of concussion, 31 (32.9%) had consumed alcohol and 18 (19.1%) concussions were sports related.
Discussion
Post-concussion symptoms can have a significant impact on patients’ function and quality of life [4,7]. Understanding concussion symptomatology and dynamics is vital to inform personalised patient management. In this study, we present one of the largest post-concussion symptomatology datasets which was gathered using digital ecological momentary assessments.
Conclusions
Post-concussion symptomatology is highly heterogenous and can have a significant impact on patient outcome. By leveraging digital ecological momentary assessments, we have captured a rich dataset of post-concussion symptom burden over a 35-day period.
Citation: Blundell R, d’Offay C, Hand C, Tadmor D, Carson A, Gillespie D, et al. (2025) Post-concussion symptom burden and dynamics: Insights from a digital health intervention and machine learning. PLOS Digit Health 4(1): e0000697. https://doi.org/10.1371/journal.pdig.0000697
Editor: Syed Sibte Raza Abidi, Dalhousie University, CANADA
Received: May 2, 2024; Accepted: November 10, 2024; Published: January 7, 2025
Copyright: © 2025 Blundell et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: Data is available via Edinburgh DataShare (https://doi.org/10.7488/ds/7849).
Funding: This study was funded by The National Institute of Health and Care Research Brain Injury MedTech Co-operative (www.brainmic.nihr.ac.uk), Grant number R46241. It was also by a business grant from the Scottish EDGE (www.scottishedge.com). The funders did not play any role in study design, data collection, analysis or manuscript preparation/publication.
Competing interests: AJ, CD, DG and CH are shareholders in HeadOn Health Ltd, which has an exclusive license to commercialize the HeadOn intellectual property.
