• A scalable natural language pr...

Treffer: A scalable natural language processing framework for drug repurposing in chemotherapy-induced adverse events from clinical narrative records.

Title:
A scalable natural language processing framework for drug repurposing in chemotherapy-induced adverse events from clinical narrative records.
Authors:
Tsuchiya M; Division of Drug Informatics, Keio University Faculty of Pharmacy, 1-5-30 Shibakoen, Minato-ku, Tokyo 105-8512, Japan., Inoue M; Division of Drug Informatics, Keio University Faculty of Pharmacy, 1-5-30 Shibakoen, Minato-ku, Tokyo 105-8512, Japan., Kawazoe Y; Artificial Intelligence and Digital Twin in Healthcare, Graduate School of Medicine, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-0033, Japan., Shimamoto K; Artificial Intelligence and Digital Twin in Healthcare, Graduate School of Medicine, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-0033, Japan., Seki T; Department of Healthcare Information Management, The University of Tokyo Hospital, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8655, Japan., Imai S; Division of Drug Informatics, Keio University Faculty of Pharmacy, 1-5-30 Shibakoen, Minato-ku, Tokyo 105-8512, Japan., Kizaki H; Division of Drug Informatics, Keio University Faculty of Pharmacy, 1-5-30 Shibakoen, Minato-ku, Tokyo 105-8512, Japan., Shinohara E; Artificial Intelligence and Digital Twin in Healthcare, Graduate School of Medicine, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-0033, Japan., Yada S; Institute of Library, Information and Media Science, University of Tsukuba, 1-2, Kasuga, Tsukuba, Ibaraki 305-8550, Japan., Wakamiya S; Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology, 8916-5, Takayama, Ikoma, Nara 630-0192, Japan., Aramaki E; Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology, 8916-5, Takayama, Ikoma, Nara 630-0192, Japan., Hori S; Division of Drug Informatics, Keio University Faculty of Pharmacy, 1-5-30 Shibakoen, Minato-ku, Tokyo 105-8512, Japan. Electronic address: satokoh@keio.jp.
Source:
European journal of cancer (Oxford, England : 1990) [Eur J Cancer] 2026 Jan; Vol. 232, pp. 116157. Date of Electronic Publication: 2025 Nov 29.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Elsevier Science Ltd Country of Publication: England NLM ID: 9005373 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1879-0852 (Electronic) Linking ISSN: 09598049 NLM ISO Abbreviation: Eur J Cancer Subsets: MEDLINE
Imprint Name(s):
Publication: Oxford : Elsevier Science Ltd
Original Publication: Oxford ; New York : Pergamon Press, c1990-
MeSH Terms:
Drug Repositioning*/methods , Natural Language Processing* , Electronic Health Records* , Antineoplastic Agents*/adverse effects , Neoplasms*/drug therapy , Drug-Related Side Effects and Adverse Reactions*/prevention & control, Humans ; Retrospective Studies ; Female ; Male ; Middle Aged ; Aged
Contributed Indexing:
Keywords: Adverse events; Drug repurposing; Electronic health records; Natural language processing
Substance Nomenclature:
0 (Antineoplastic Agents)
Entry Date(s):
Date Created: 20251205 Date Completed: 20260104 Latest Revision: 20260104
Update Code:
20260105
DOI:
10.1016/j.ejca.2025.116157
PMID:
41349154
Database:
MEDLINE

Weitere Informationen

Background: Preventing chemotherapy-related adverse events (AEs) remains an unmet clinical challenge. Preclinical studies have suggested protective effects of several existing agents, but translation into human evidence has been limited. We aimed to establish proof of concept (PoC) for drug repurposing by applying a natural language processing (NLP)-based framework to electronic health record (EHR) narratives, thereby bridging preclinical findings with clinical validation.
Methods: We retrospectively analyzed 56,326 patients with cancer treated at the University of Tokyo Hospital (2004-2023). A transformer-based NLP model extracted symptomatic AEs from clinical notes. Candidate preventive drugs identified from preclinical evidence were assessed using propensity score matching and Cox proportional hazards models. We evaluated angiotensin II receptor blockers (ARBs) for fluoropyrimidine-induced oral mucositis and ramelteon for platinum-induced peripheral neuropathy, with laxatives serving as a negative control.
Results: NLP demonstrated high accuracy (precision 0.81-0.83; recall 0.95-0.97). After matching, ARB co-administration was significantly associated with reduced mucositis incidence (hazard ratio [HR] 0.58, 95 % confidence interval [CI] 0.44-0.77; P < 0.001), representing a clinical PoC consistent with mechanistic preclinical data. Ramelteon showed an exploratory protective signal against neuropathy (HR 0.60, 95 % CI:0.38-0.93; P = 0.024). No preventive association was observed for laxatives.
Conclusions: This study introduces a scalable NLP-epidemiology framework for non-invasive, real-world validation of drug repurposing candidates. The ARB finding provides human-level PoC evidence supporting prospective clinical testing, while the ramelteon signal warrants further exploration. Our approach demonstrates how EHR narratives can operationalize translational research, prioritizing safe, accessible agents for improving the tolerability of cancer treatment.
(Copyright © 2025 The Authors. Published by Elsevier Ltd.. All rights reserved.)

Declaration of Competing Interest Yoshimasa Kawazoe, Kiminori Shimamoto, and Emiko Shinohara are affiliated with the Department of Artificial Intelligence and Digital Twin in Healthcare, Graduate School of Medicine, University of Tokyo, an endowment department. This research was supported by an unrestricted grant from EM Systems, EPNextS, MRP CO., LTD., SHIP HEALTHCARE HOLDINGS, INC., SoftBank Corp., and NEC Corporation. These organizations had no role in the interpretation, writing, or publication of this work. The authors declare no conflicts of interest.