BURN-OP: A screening tool for identifying a symptomatically distinct cluster of burn patients with the greatest healthcare needs at discharge
Bibliographic record
Abstract
OBJECTIVE: To identify burn patients needing intensive rehabilitation based on discharge symptoms. METHODS: We conducted a retrospective analysis of 1049 adult burn patients recruited to the Burn Injury Model System National Database. Using unsupervised hierarchical clustering, we identified three distinct patient clusters based on discharge symptoms and compared their clinical and demographic profiles, long-term rehabilitative needs, and self-reported quality of life. We also developed a weighted BUrn Rehabilitative Needs - OutPatient (BURN-OP) to prospectively identify patients with highest rehabilitative needs. RESULTS: Three burn patient clusters were identified: Cluster 1 with low, Cluster 2 with moderate, and Cluster 3 with high symptom burdens. Cluster 3, comprising 6 % of discharged patients, had notably longer hospital stays, older age at burn, larger total body surface area (TBSA), increased days on ventilator, a higher number of surgical procedures, concomitant inhalation injury, and higher weight loss from admission to discharge. Cluster 3 patients preferentially utilized a wide spectrum of rehabilitative services (including physiotherapy, occupational therapy, speech-language pathology, social work, psychologic services, vocational services) extending up to 2 years post-discharge. Their self-reported health outcomes were worse, with greater limitations in work/activity and elevated pain interference persisting 5-years post-discharge. BURN-OP demonstrated high specificity (98.99 %) and accuracy (96.19 %, ROC AUC: 0.93) in identifying Cluster 3 patients at discharge. CONCLUSIONS: We identify distinct burn patient clusters based on discharge symptoms, with Cluster 3 exhibiting the highest post-discharge healthcare needs. BURN-OP (https://burn-op.streamlit.app/) identifies high-risk patients, offering a tool for prioritizing interventions and designing trials that mitigate risk of Cluster 3 membership.
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 | 0.000 |
| 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".