The [International Standards for Neurological Classification of SCI (ISNCSCI)](https://asia-spinalinjury.org/international-standards-neurological-classification-sci-isncsci-worksheet/) evaluates motor and sensory impairment across the body and helps localize the neurologic level of the spinal cord injury and grade the severity of that injury. However, conducting a full ISNCSCI assessment is time consuming leading to the recent proposal of the expedited ISNCSCI (E-ISCNSCI) assessment focussing on key muscle function. In this challenge, participants will attempt to impute full ISNCSCI scores from E-ISNCSCI examinations by analyzing a subset of the data from the [Sygen multicenter clinical trial](https://pubmed.ncbi.nlm.nih.gov/11805614/). Additional data includes demographic information, comorbidities, surgical interventions, and medical complications.

This data challenge involves two tracks addressing the imputation task from two distinct angles. The first construct addressed here is the inference of full ISNCSCI assessments from the shortened examination. **We will score performance based on a regression metric, the coefficient of determination for the imputed sensory scores**.
It is likely, that an earlier full ISNCSCI assessment may offer essential information for this imputation task. Thus [the second track](https://www.kaggle.com/competitions/asia-2026-challenge-longitudinal-isncsci-imputation) aims to provide the same imputation task, however includes data on an earlier full ISNCSCI assessment as well (and the respective assessment time).

Why these outcomes? Essentially all functions of the body are influenced by spinal cord injury and are important to predict, including arm and hand function, bowel and bladder function, respiratory function, blood pressure control, and skin integrity. However, there are no available datasets that capture these rich aspects of function. Our goal with this challenge is to assess the possibility of E-ISNCSCI to recapitulate full assessments.

A representative from the winning team for each track will be invited to present their work at the ASIA society annual meeting, with travel support available for the representatives.

There are additional open datasets available with data for spinal cord injury. Participants are invited to also use these data if it improves their prediction performance on the Sygen challenge data but need to provide information and the respective data upon request to the organizers in order to verify the performance reported stems truely from a learning task - teams using datasets which are not publicly available, including private datasets from their health care system will not be eligible. Any teams with access to the complete Sygen dataset are prohibited from using this data when training their algorithms. Leading teams will be asked to submit a write-up and code to reproduce their solution.