Study of online health discussion fora for the detection of medication misusesÉlise misuses´misusesÉlise

Elise Bigeard (1, 2) , Frantz Thiessard (1) , Natalia Grabar (2)

1 Département de Pharmacologie
2 STL - Savoirs, Textes, Langage (STL) - UMR 8163

Misuses occur when patients do not respect prescriptions and commit actions which can lead to harmful results. Even if such situations are dangerous, patients do not inform medical doctors about such events. To obtain some information on misuses, it becomes necessary to study other sources of information. We propose to concentrate on discussion fora. The purpose of our work is to explore health fora with machine learning methods and to identify messages where users describe or mention drug misuses. Our approach detects the mesuses with up to 0.773 F-measure. This approach can help in routine detection of misuses and to provide material exploitable by health professionals.

Mots clés: Natural Language Processing; Supervised learning; Machine learning; Text mining; Biomedical informatics; Discussion forums; Internet; Knowledge discovery; Prototypes

Domaines: Sciences de l'information et de la communication; Traitement du texte et du document; Web; Sciences du Vivant [q-bio]

Elise Bigeard, Frantz Thiessard, Natalia Grabar. Study of online health discussion fora for the detection of medication misusesÉlise misuses´misusesÉlise. ICHI 2018 :The Sixth IEEE International Conference on Healthcare Informatics, Jun 2018, New-York, United States. ⟨halshs-01968340⟩