Spinal cord injury (SCI) can result in a sudden and substantial loss of function and independence. The standard for measuring injury severity is the [International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI) assessment](https://asia-spinalinjury.org/international-standards-neurological-classification-sci-isncsci-worksheet/). This is a comprehensive examination that measures strength and sensory function and different levels across the nervous system.

As an alternative to the full ISNCSCI examination, there is also an expedited version ([E-ISNCSCI](https://asia-spinalinjury.org/expedited-isncsci-exam/)). This can be performed in some circumstances to determine the neurological level of injury (NLI) and the American Spinal Injury Association (ASIA) Impairment Scale (AIS). 

The full ISNCSCI is typically performed early after an injury, with the E-ISNCSCI being more appropriate for subsequent examinations. However, it is uknown exactly how much information about assessing sensory function is lost using the E-ISNCSCI and how much can be recovered through data-driven imputation methods. 

This medical science data challenge, hosted by the [American Spinal Cord Injury Association (ASIA)](http://asia-spinalinjury.org/), aims to improve performance on this task and to invite data scientists into the field of spinal cord injury research.

**Goal:** This challenge aims to impute sensory scores from both a complete baseline ISNCSCI and subsequent E-ISNCSCI scores.

**Dual Track:** This competition includes both this track and imputating full ISNCSCI scores from E-ISNCSCI without a baseline ISNCSCI [which can be found here](https://www.kaggle.com/competitions/asia-2026-e-isncsci-imputation). Participants can submit to one or both.

**Participation Rules:**  Please carefully check the participation rules, which also indicate that in order to win the competition, the team must provide their code for review and execution.