[2S6-OS-7a] OS-7

[2S6-OS-7a-05] Evaluation of the usefulness of deep learning models for adverse event signal detection using patient complaints

〇Satoshi Watabe ¹、Satoshi Nishioka ¹、 Yuki Yanagisawa ¹、 Kyoko Sayama ¹、 Hayato Kizaki ¹、 Shungo Imai ¹、 Mitsuhiro Someya ²、Ryoo Taniguchi ²、Shuntaro Yada ³、 Eiji Aramaki ³、 Satoko Hori ¹ (1. Keio University, 2. Nakajima pharmacy, 3. Nara Institute of Science and Technology)

Keywords:Natural Language Processing, Deep Learning, anticancer drug, adverse drug event, pharmaceutical care record

It has been a while since the importance of listening to patient real voice was highlighted for better quality of adverse event (AE) evaluation. Our laboratory has reported novel deep leaning (DL) models that detect AE signals for hand-foot syndrome (HFS) or AEs limiting patients’ daily lives (AE-L) from cancer patient authored narratives. This study was designed to evaluate the DL models by applying them to S records in pharmaceutical care records following SOAP format, identifying characteristics and utility of the DL models. From 30,784 S records for 2,479 patients with at least one prescription history of anticancer drugs, our DL models extracted true AE signals with more than 80% accuracy for both HFS and AE-L, being also able to screen important AE signals requiring medical support from healthcare professionals. Our DL models could screen clinically important AE signals that would require intervention to treat the symptoms.