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

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. 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...

International standards for neurological classification of spinal cord injury: classification skills of clinicians versus computational algorithms

“…This kind of analysis was previously performed exclusively in the artificial setting of ISNCSCI instructional courses. 7,[10][11][12][13][14][15][16][17][18][19][20][21] In the framework of instructional courses, the effects of a formal ISNCSCI training are typically assessed by the same test before (pre-test) and after the training (post-test). In both tests, the attendees rate and classify a predefined set of ISNCSCI cases.…”

“…As outlined here, validated computer-aided algorithms will likely eliminate errors in ISNCSCI classification by humans. 16 Limitations This study uses data sets that were obtained almost 10 years ago and were predominantly classified by residents with different classification skills and level of training. A correlation between training levels and classification errors cannot be performed, because this information was not documented during the study period.…”

“…16 ISNCSCI data sets in EMSCI contain classification variables, as well as all segmental scores of light touch, pinprick, muscle function and anorectal examination. During the indicated time period, all ISNCSCI examinations and subsequent classifications were manually performed by SCI clinicians.…”

“…The details of the algorithms and the validation process are published elsewhere. 16 Both manual (clinician) and computational (computer) classification methods were statistically tested for differences in the following ISNCSCI variables: right/left sensory level, right/left motor level, AIS, sensory and motor zones of partial preservation for right and left side. At the time of the assessments (2003)(2004)(2005), the single NLI was not listed in the ISNCSCI assessment sheet (REV2001) 12 and was therefore not included in our analysis.…”

“…Therefore, the aim of this investigation was to describe and quantify any discrepancies in the ISNCSCI classification by typical SCI clinicians versus validated computational ISNCSCI algorithms. 16 This study was conducted as a part of the quality management system (ISO 9001:2008) of the European Multicenter Study on Human Spinal Cord Injury (EMSCI -http://emsci.org). 17 …”