Mashima Yukinori, Tamura Takashi, Kunikata Jun, Tada Shinobu, Yamada Akiko, Tanigawa Masatoshi, Hayakawa Akiko, Tanabe Hirokazu, Yokoi Hideto
Clinical Research Support Center, Kagawa University Hospital, Kagawa, Japan.
Department of Medical Informatics, Kagawa University Hospital, Kagawa, Japan.
Cancer Inform. 2022 Mar 22;21:11769351221085064. doi: 10.1177/11769351221085064. eCollection 2022.
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.
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.
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 ( = .0027). There were significantly more misdetection cases in Group A than in Group B (15.3% in Group A; 1.2% in Group B, = .0012) due to negative findings or past history.
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.
近年来，自然语言处理（NLP）技术不断进步，其在医学领域的应用也得到了检验。然而，利用NLP从日语书写的病程记录中检测症状的应用仍然有限。我们旨在使用NLP从病程记录中检测出两种影响化疗持续进行的胃肠道症状——恶心/呕吐和腹泻，然后分析影响NLP的因素。
在本研究中，从2011年1月至2018年12月期间在日本香川大学医院接受静脉注射细胞毒性抗癌药物的5277例患者中随机选取200例患者。我们旨在使用NLP检测恶心/呕吐（A组）和腹泻（B组）的首次发生情况。通过与用作金标准的医生病程记录回顾的一致性来评估NLP的性能。
两组的一致性都很高：A组为83.5%（95%置信区间[CI]74.1 - 90.1），B组为97.7%（95%CI 91.3 - 99.9）。然而，B组的一致性明显更好（P = 0.0027）。由于阴性结果或既往病史，A组的误检病例明显多于B组（A组为15.3%；B组为1.2%，P = 0.0012）。
我们使用NLP准确检测出了恶心/呕吐和腹泻的发生情况。然而，由于阴性结果或既往病史，A组的误检病例更多，这可能受到医生更频繁记录恶心/呕吐情况的影响。
