Study Design: Prospective, longitudinal cohort study. Objectives: To quantify the effect of formal training in the International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI) on the classification accuracy and to identify the most difficult ISNCSCI rules. Settings: European Multicenter Study on Human Spinal Cord Injury (EMSCI). Methods: EMSCI participants rated five challenging cases of full sensory, motor and anorectal examinations before (pre-test) and after (post-test) an ISNCSCI instructional course. Classification variables included sensory and motor levels (ML), completeness, ASIA Impairment Scale (AIS) and the zones of partial preservation. Results: 106 attendees were trained in 10 ISNCSCI workshops since 2006. The number of correct classifications increased significantly (Po0.00001) from 49.6% (2628 of 5300) in pre-testing to 91.5% (4849 of 5300) in post-testing. Every attendee improved, 12 (11.3%) achieved 100% correctness. Sensory levels (96.8%) and completeness (96.2%) are easiest to rate in posttesting, while ML (81.9%) and AIS (88.1%) are more difficult to determine. Most of the errors in ML determination arise from sensory levels in the high cervical region (C2 ÀC4), where by convention the ML is presumed to be the same as the sensory level. The most difficult step in AIS classification is the determination of motor incompleteness. Conclusion: ISNCSCI training significantly improves the classification skills regardless of the experience in spinal cord injury medicine. These findings need to be considered for the appropriate preparation and interpretation of clinical trials in spinal cord injury.

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. 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 nontestability 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 spi...