Saliva RNA biomarkers predict concussion duration and detect symptom recovery: a comparison with balance and cognitive testing
Bibliographic record
Abstract
OBJECTIVE: The goals of this study were to assess the ability of salivary non-coding RNA (ncRNA) levels to predict post-concussion symptoms lasting ≥ 21 days, and to examine the ability of ncRNAs to identify recovery compared to cognition and balance. METHODS: RNA sequencing was performed on 505 saliva samples obtained longitudinally from 112 individuals (8-24-years-old) with mild traumatic brain injury (mTBI). Initial samples were obtained ≤ 14 days post-injury, and follow-up samples were obtained ≥ 21 days post-injury. Computerized balance and cognitive test performance were assessed at initial and follow-up time-points. Machine learning was used to define: (1) a model employing initial ncRNA levels to predict persistent post-concussion symptoms (PPCS) ≥ 21 days post-injury; and (2) a model employing follow-up ncRNA levels to identify symptom recovery. Performance of the models was compared against a validated clinical prediction rule, and balance/cognitive test performance, respectively. RESULTS: An algorithm using age and 16 ncRNAs predicted PPCS with greater accuracy than the validated clinical tool and demonstrated additive combined utility (area under the curve (AUC) 0.86; 95% CI 0.84-0.88). Initial balance and cognitive test performance did not differ between PPCS and non-PPCS groups (p > 0.05). Follow-up balance and cognitive test performance identified symptom recovery with similar accuracy to a model using 11 ncRNAs and age. A combined model (ncRNAs, balance, cognition) most accurately identified recovery (AUC 0.86; 95% CI 0.83-0.89). CONCLUSIONS: ncRNA biomarkers show promise for tracking recovery from mTBI, and for predicting who will have prolonged symptoms. They could provide accurate expectations for recovery, stratify need for intervention, and guide safe return-to-activities.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".