Computer Implementation of the International Standards for Neurological Classification of Spinal Cord Injury for Consistent and Efficient Derivation of Its Subscores Including Handling of Data from Not Testable Segments

Authors:
Publisher website
Google Scholar
Abstract
The International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI), defined by the American Spinal Injury Association (ASIA), and particularly the ASIA Impairment Scale (AIS) are widely used for research and clinical purposes. Although detailed procedures for scaling, scoring, and classification have been defined, misclassifications remain a major problem, especially for cases with missing (i.e., not testable [NT]) data. This work aimed to implement computer-based classification algorithms that included rules for handling NT data. A consistent and structured algorithmic scoring, scaling, and classification scheme, and a computerized application have been developed by redefining logical/mathematical imprecisions. Existing scoring rules are extended for handling NT segments. Design criterion is a pure logical approach so that substitution of non-testability for all valid examination scores leads to concordant results. Nine percent of 5542 datasets from 1594 patients in the database of the European Multicenter Study of Human Spinal Cord Injury (EM-SCI) contained NT segments. After adjusting computational algorithms, the classification accuracy was equivalent between clinical experts and the computational approach and resulted in 84% valid AIS classifications within datasets containing NT. Additionally, the computational method is much more efficient, processing approximately 200,000 classifications/sec. Computational algorithms offer the ability to classify ISNCSCI subscores efficiently and without the risk of human-induced errors. This is of particular clinical relevance, since these scores are used for early predictions of neurological recovery and functional outcome for patients with spinal cord injuries.

This publication has 14 references indexed in Scilit: