Impact of ICD10 and secular changes on electronic medical record rheumatoid arthritis algorithms

Abstract

Objective The objective of this study was to compare the performance of an RA algorithm developed and trained in 2010 utilizing natural language processing and machine learning, using updated data containing ICD10, new RA treatments, and a new electronic medical records (EMR) system. Methods We extracted data from subjects with ≥1 RA International Classification of Diseases (ICD) codes from the EMR of two large academic centres to create a data mart. Gold standard RA cases were identified from reviewing a random 200 subjects from the data mart, and a random 100 subjects who only have RA ICD10 codes. We compared the performance of the following algorithms using the original 2010 data with updated data: (i) a published 2010 RA algorithm; (ii) updated algorithm, incorporating ICD10 RA codes and new DMARDs; and (iii) published algorithm using ICD codes only, ICD RA code ≥3. Results The gold standard RA cases had mean age 65.5 years, 78.7% female, 74.1% RF or antibodies to cyclic citrullinated peptide (anti-CCP) positive. The positive predictive value (PPV) for ≥3 RA ICD was 54%, compared with 56% in 2010. At a specificity of 95%, the PPV of the 2010 algorithm and the updated version were both 91%, compared with 94% (95% CI: 91, 96%) in 2010. In subjects with ICD10 data only, the PPV for the updated 2010 RA algorithm was 93%. Conclusion The 2010 RA algorithm validated with the updated data with similar performance characteristics as the 2010 data. While the 2010 algorithm continued to perform better than the rule-based approach, the PPV of the latter also remained stable over time.

Association of Sinusitis and Upper Respiratory Tract Diseases With Incident Rheumatoid Arthritis: A Case-control Study

“…We initially identified 2,017 adult RA cases in the MGB Biobank using a previously published algorithm for RA that incorporates diagnosis codes, laboratory results, and natural language processing (25,26). This algorithm has a 95% positive predictive value at 97% specificity for RA defined by the 2010 American College of Rheumatology/European League Against Rheumatism (ACR/EULAR) criteria (25).…”

ATLAS: An automated association test using probabilistically linked health records with application to genetic studies

“…We considered EHR records from two databases with which we performed linkage and the linked data-enabled downstream association analyses. The EHR data are stored in two separate databases: (i) the Crimson Clinical Discards database (herein referred to as Crimson and akin to database A) for a subset of RA patients of European descent previously identified in 2008 [19,20]; and (ii) the Mass General Brigham (MGB) Research Patient Data Registry (herein referred to as RPDR and akin to database B) subset of RA patients identified via an existing machine learning algorithm [21–23]. The Crimson RA cohort contains anonymized EHR data along with genotype data for n Crimson = 1,284 patients collected up to 2008.…”

Perspektiven für die rheumatologische Versorgungsforschung am Deutschen Rheuma-Forschungszentrum

“…Neben der klinischen Anwendung im Rahmen von bildgebender Diagnostik, Früherkennung und prognostischem Wert wird ML in der Versorgungsforschung dazu beitragen, die im Umfang zunehmenden Gesundheitsdaten der Patienten effizienter auszuwerten. Zum Beispiel können Diagnosealgorithmen in der Forschung mit elektronischen Krankenkassendaten durch ML verstetigt werden [ 9 ].…”