Identification of axial spondyloarthritis patients in a large dataset: the development and validation of novel methods

Objective Observational axial spondyloarthritis (axSpA) research in large datasets has been limited by a lack of adequate methods for identifying axSpA patients, since there are no billing codes in the United States for most subtypes of axSpA. The objective of this study was to develop methods to accurately identify axSpA patients in a large dataset. Methods The study population included 600 chart-reviewed Veterans, with and without axSpA, in the Veteran Health Administration between January 1, 2005 and June 30, 2015. AxSpA identification algorithms were developed with variables anticipated by clinical expert to be predictive of an axSpA diagnosis (demographics, billing codes, provider utilization, medications, laboratory results, and natural language processing [NLP] for key spondyloarthritis features). Random Forest and 5-fold cross validation were used for algorithm development and testing in the training subset (n=451). The algorithms were additionally tested in an independent testing subset (n=149). Results Three algorithms were developed: Full Algorithm, High Feasibility Algorithm, and Spond NLP Algorithm. In the testing subset, the areas under the curve with the receiver operating characteristic analysis were 0.96, 0.94, and 0.86, for the Full Algorithm, High Feasibility Algorithm, and the Spond NLP Algorithm, respectively. Algorithm sensitivities ranged from 82.8%- 95.0%, specificities from 78.0%- 95.1% and accuracies from 82.6%- 91.8%. Conclusion Novel axSpA identification algorithms performed well with classifying axSpA patients. These algorithms offer a range of performance and feasibility attributes that may be appropriate for a broad array of axSpA studies, but additional research is required to validate the algorithms in other cohorts.