Evaluating the Portability of Rheumatoid Arthritis Phenotyping Algorithms: A Case Study on French EHRs.

Fiche publication


Date publication

mai 2023

Journal

Studies in health technology and informatics

Auteurs

Membres identifiés du Cancéropôle Est :
Pr SAULEAU Erik-André, Pr GOTTENBERG Jacques-Eric


Tous les auteurs :
Fabacher T, Sauleau EA, Leclerc Du Sablon N, Bergier H, Gottenberg JE, Coulet A, Névéol A

Résumé

Previous work has successfully used machine learning and natural language processing for the phenotyping of Rheumatoid Arthritis (RA) patients in hospitals within the United States and France. Our goal is to evaluate the adaptability of RA phenotyping algorithms to a new hospital, both at the patient and encounter levels. Two algorithms are adapted and evaluated with a newly developed RA gold standard corpus, including annotations at the encounter level. The adapted algorithms offer comparably good performance for patient-level phenotyping on the new corpus (F1 0.68 to 0.82), but lower performance for encounter-level (F1 0.54). Regarding adaptation feasibility and cost, the first algorithm incurred a heavier adaptation burden because it required manual feature engineering. However, it is less computationally intensive than the second, semi-supervised, algorithm.

Mots clés

Natural Language Processing, Phenotyping, Rheumatoid Arthritis

Référence

Stud Health Technol Inform. 2023 05 18;302:768-772