The application of artificial intelligence in the acute and sub-acute phases of spinal cord injury- a systematic review
Bibliographic record
Abstract
STUDY DESIGN: Systematic Review. OBJECTIVE: To describe applications of AI for traumatic SCI management with focus on diagnostics, prognostication, and therapeutic interventions. METHODS: , 2020, and March 18, 2025, dealing with clinical aspects in the acute, post-injury rehabilitative and first year phases of SCI were included. Studies on brain computer interface, robotics and non-neurologic aspects of SCI were excluded. Extracted were country of study, study design, focus of study, total participants, American Spinal Injury Association (ASIA) Impairment Scale (AIS), machine learning (ML) models, inputs, outcomes and performance metrices. RESULTS: A total of 23 studies with 120,931 individuals were identified. Classical Machine Learning Models, Ensemble Learning Models and Deep Learning Models were the most used ML families. Age, AIS, neurologic level of injury, sex, mechanism of injury and motor score were the most common inputs. Predictions of neurologic status, functionality status, Hospital/ICU utilizations, complications, survival, discharge destination and results of image segmentation and patient grouping were the outputs of interest. The performance metrices were satisfactory in most and higher than humans in some studies. CONCLUSION: AI can facilitate personalized approach to diagnosis of SCI, prediction of outcomes like neurological improvement, complications, functionality indicators like walking, selfcare and independence, re-admissions, prolonged length of stays, discharge destination and mortality after injury. It was also useful to suggest specific MAP goals and time of surgical intervention. These functions complement clinical judgement.
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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".