ArticleSpinal cord2026
Web-based machine learning application for ambulation prognosis in the rehabilitation phase of spinal cord injury: a retrospective multicenter cohort study.
Article in Spinal cord, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. An erratum has been issued. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
- Erratum issued
Authors and funding
3 authors.
Funding
Abstract
STUDY
designA retrospective cohort study.
objectivesTo develop a machine learning (ML) model to predict ambulation prognosis one year post-injury in rehabilitation-phase spinal cord injury (SCI) individuals classified as American Spinal Injury Association Impairment Scale (AIS) grades B and C, and to implement it as a web application.
settingA multicenter database in the United States.
methodsData were collected from the National Spinal Cord Injury Database (NSCID) for the years 2011 to 2021. Traumatic SCI cases with complete neurological data at rehabilitation admission were included, based on the International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI). Model predictors included age at injury, acute length of stay, neurological level of injury, motor scores, and sensory scores. ML models were developed using nested 5-fold cross-validation and four algorithms: logistic regression, random forest, support vector machine, and extreme gradient boosting (XGB). Performance was assessed and compared using area under the curve (AUC), Brier score, and calibration slope, with a focus on AIS grades B and C. A web application was developed using the R package shiny and deployed via shinyapps.io.
results2034 cases were included in the analysis. XGB demonstrated the best performance in terms of AUC (0.855), Brier score (0.153), and calibration slope (0.900) and was selected as the final model. This model was implemented as a web application.
conclusionsThe developed model showed good performance for AIS grades B and C and was made practical via web application implementation.
Indexed as
Identifiers
41390882What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.