5.10 Expanding the value of artificial intelligence in concussion management — from concussion subtyping to treatment planning
Bibliographic record
Abstract
Objective Interdisciplinary assessment, the gold standard for assessment of concussion and identification of rehabilitation targets, is a barrier for many due to geographical or financial limitations. This study aimed to explore the opportunity of leveraging AI beyond subtyping concussion to its application and accuracy in generating AI driven treatment plans. Design A blinded chart review of 25 randomly selected de-identified subjects from the original algorithm sample based upon a machine learning approach that identified five distinct concussion subtypes along a complexity continuum. Participants Subjects had attended concussion assessment and rehabilitation at Advance Concussion Clinic (ACC), an interdisciplinary clinic in Vancouver, Canada. Main Results Assessment ‘prescriptions’ as generated by the AI model yielded system specific recommendations including physiotherapy queries of cervical, oculomotor, vestibular, and/or autonomic dysfunction, neuropsychology query of cognitive dysfunction, counselling query of emotional/mood dysfunction, and occupational therapy query of ADL dysfunction in school, work, or home. Comparison of clinical assessment recommendations to AI driven assessment queries matched at 99.2%, with the one discrepancy associated with human error not replicated by the AI model. A Permutation test to evaluate the accuracy of our AI model yielded a P_value≈0, demonstrating the efficacy of AI driven support in clinical decision making and prescription of targeted assessment and rehabilitation/treatment planning. Conclusions AI driven treatment planning supports a comprehensive view of the complex, multi-system injury that is concussion, potentially offering recovery opportunities otherwise unavailable to those for whom best practice interdisciplinary assessment may not be accessible or available.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.028 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".