Chauvet Raphaël, Bousquet Cédric, Lillo-Lelouet Agnès, Zana Ilan, Ben Kimoun Ilan, Jaulent Marie-Christine
Sorbonne Université, INSERM, Université Paris 13, Laboratoire d'Informatique Médicale et d'Ingénierie des Connaissances en e-Santé, Paris, France.
EISTI, International Engineering School, 95000 Cergy-Pontoise, France.
Stud Health Technol Inform. 2020 Jun 16;270:1227-1228. doi: 10.3233/SHTI200375.
This poster presents a non-exhaustive study of machine learning classification algorithms on pharmacovigilance data. In this study, we have taken into account the patient's clinical data such as medical history, medications taken and their indications for prescriptions, and the observed side effects. From these elements we determine whether the patient case is considered serious or not. We show the performances of the different algorithms by their precision, recall and accuracy as well as their learning curves.
本海报展示了对药物警戒数据上机器学习分类算法的一项非详尽研究。在这项研究中，我们考虑了患者的临床数据，如病史、所服用的药物及其处方适应症，以及观察到的副作用。根据这些因素，我们确定患者病例是否被视为严重。我们通过不同算法的精确率、召回率、准确率以及它们的学习曲线来展示其性能。
