Using Natural Language Processing Techniques to Detect Adverse Events From Progress Notes Due to Chemotherapy

Yukinori Mashima; Takashi Tamura; Jun Kunikata; Shinobu Tada; Akiko Yamada; Masatoshi Tanigawa; Akiko Hayakawa; Hirokazu Tanabe; Hideto Yokoi

doi:10.1177/11769351221085064

Using Natural Language Processing Techniques to Detect Adverse Events From Progress Notes Due to Chemotherapy

Cancer Inform. 2022 Mar 22:21:11769351221085064. doi: 10.1177/11769351221085064. eCollection 2022.

Authors

Yukinori Mashima^{1

2}, Takashi Tamura³, Jun Kunikata¹, Shinobu Tada⁴, Akiko Yamada², Masatoshi Tanigawa², Akiko Hayakawa³, Hirokazu Tanabe³, Hideto Yokoi^{1

2

4}

Affiliations

¹ Clinical Research Support Center, Kagawa University Hospital, Kagawa, Japan.
² Department of Medical Informatics, Kagawa University Hospital, Kagawa, Japan.
³ Pharmacoepidemiology & PMS Department, Daiichi Sankyo Co., Ltd., Tokyo, Japan.
⁴ Information Network Administration Office, Faculty of Medicine, Kagawa University, Kagawa, Japan.

Abstract

Objective: In recent years, natural language processing (NLP) techniques have progressed, and their application in the medical field has been tested. However, the use of NLP to detect symptoms from medical progress notes written in Japanese, remains limited. We aimed to detect 2 gastrointestinal symptoms that interfere with the continuation of chemotherapy-nausea/vomiting and diarrhea-from progress notes using NLP, and then to analyze factors affecting NLP.

Materials and methods: In this study, 200 patients were randomly selected from 5277 patients who received intravenous injections of cytotoxic anticancer drugs at Kagawa University Hospital, Japan, between January 2011 and December 2018. We aimed to detect the first occurrence of nausea/vomiting (Group A) and diarrhea (Group B) using NLP. The NLP performance was evaluated by the concordance with a review of the physicians' progress notes used as the gold standard.

Results: Both groups showed high concordance: 83.5% (95% confidence interval [CI] 74.1-90.1) in Group A and 97.7% (95% CI 91.3-99.9) in Group B. However, the concordance was significantly better in Group B (P = .0027). There were significantly more misdetection cases in Group A than in Group B (15.3% in Group A; 1.2% in Group B, P = .0012) due to negative findings or past history.

Conclusion: We detected occurrences of nausea/vomiting and diarrhea accurately using NLP. However, there were more misdetection cases in Group A due to negative findings or past history, which may have been influenced by the physicians' more frequent documentation of nausea/vomiting.

Keywords: Natural language processing; data mining; drug therapy; drug-related side effects and adverse reactions; electronic health records; pharmacovigilance; progress notes.