Hiroshima Allergy and Respiratory Clinic, Hiroshima, Japan.
Kyorin Pharmaceutical Co. Ltd, Tokyo, Japan.
J Asthma. 2022 Jul;59(7):1328-1337. doi: 10.1080/02770903.2021.1923740. Epub 2021 May 18.
Analytical studies of risk factor assessment using machine learning have recently been reported. We performed an exploratory detection study of asthma exacerbation-related factors using health insurance claims data and machine learning to explore risk factors that have high generalizability and can be easily obtained in daily practice.
A dataset of asthma patients during May 2014-April 2019 from the Japanese insurance claims database, MediScope® (DB) was used. Patient characteristics and disease information were extracted, and association with occurrence of asthma exacerbation was evaluated to comprehensively search for exacerbation risk factors. Asthma exacerbations were defined as the co-occurrence of emergency medical procedures, such as emergency transport and intravenous steroid injections, with asthma claims, which were recorded in the database.
In total, 5,844 (13.7%) subjects had exacerbations in 42,685 eligible cases from the DB. Information on approximately 3,300 diseases was subjected to a machine learning, and 25 variables were extracted as variable importance and targeted for risk assessment. As a result, sex, days without exacerbation from cohort entry date at look-back period, Charlson Comorbidity Index, allergic rhinitis, chronic sinusitis, acute airway disease (upper airway), acute airway disease (lower airways), Chronic obstructive pulmonary disease/chronic bronchitis, gastroesophageal reflux disease, and hypertension were significantly associated with exacerbation. Dyslipidemia and periodontitis were detected as associated factors of reduced exacerbation risk.
A comprehensive analysis of claims data using machine learning showed asthma exacerbation risk factors mostly consistent with those in previous studies. Further examination in other fields is warranted.Supplemental data for this article is available online at https://doi.org/10.1080/02770903.2021.1923740 .
最近有研究报告称，使用机器学习进行危险因素评估的分析研究。我们使用医疗保险索赔数据和机器学习进行了一项探索性的哮喘恶化相关因素检测研究，以探索具有高通用性且在日常实践中易于获得的危险因素。
使用 MediScope®（DB）日本医疗保险索赔数据库中 2014 年 5 月至 2019 年 4 月期间的哮喘患者数据集。提取患者特征和疾病信息，并评估与哮喘恶化发生的关联，以全面搜索哮喘恶化的危险因素。数据库中记录的哮喘恶化定义为哮喘发作时同时出现紧急医疗程序，如紧急转运和静脉类固醇注射。
在 DB 中，从 42685 例合格病例中，共有 5844 例（13.7%）患者发生了恶化。对大约 3300 种疾病的信息进行了机器学习处理，提取了 25 个变量作为变量重要性并进行了风险评估。结果显示，性别、从队列入组日期开始的无恶化天数、Charlson 合并症指数、过敏性鼻炎、慢性鼻窦炎、急性气道疾病（上呼吸道）、急性气道疾病（下呼吸道）、慢性阻塞性肺疾病/慢性支气管炎、胃食管反流病和高血压与恶化显著相关。血脂异常和牙周炎被检测为降低恶化风险的相关因素。
使用机器学习对索赔数据进行综合分析显示，哮喘恶化的危险因素与以往研究大多一致。在其他领域进一步检查是必要的。本文补充数据可在 https://doi.org/10.1080/02770903.2021.1923740 在线获取。
