Alsaber Ahmad R, Al-Herz Adeeba, Alawadhi Balqees, Doush Iyad Abu, Setiya Parul, Al-Sultan Ahmad T, Saleh Khulood, Al-Awadhi Adel, Hasan Eman, Al-Kandari Waleed, Mokaddem Khalid, Ghanem Aqeel A, Attia Yousef, Hussain Mohammed, AlHadhood Naser, Ali Yaser, Tarakmeh Hoda, Aldabie Ghaydaa, AlKadi Amjad, Alhajeri Hebah
College of Business and Economics, American University of Kuwait, Salmiya, Kuwait.
Department of Rheumatology, Al-Amiri Hospital, Kuwait City, Kuwait.
Front Big Data. 2024 Oct 3;7:1406365. doi: 10.3389/fdata.2024.1406365. eCollection 2024.
Rheumatoid arthritis (RA) is a common condition treated with biological disease-modifying anti-rheumatic medicines (bDMARDs). However, many patients exhibit resistance, necessitating the use of machine learning models to predict remissions in patients treated with bDMARDs, thereby reducing healthcare costs and minimizing negative effects.
The study aims to develop machine learning models using data from the Kuwait Registry for Rheumatic Diseases (KRRD) to identify clinical characteristics predictive of remission in RA patients treated with biologics.
The study collected follow-up data from 1,968 patients treated with bDMARDs from four public hospitals in Kuwait from 2013 to 2022. Machine learning techniques like lasso, ridge, support vector machine, random forest, XGBoost, and Shapley additive explanation were used to predict remission at a 1-year follow-up.
The study used the Shapley plot in explainable Artificial Intelligence (XAI) to analyze the effects of predictors on remission prognosis across different types of bDMARDs. Top clinical features were identified for patients treated with bDMARDs, each associated with specific mean SHAP values. The findings highlight the importance of clinical assessments and specific treatments in shaping treatment outcomes.
The proposed machine learning model system effectively identifies clinical features predicting remission in bDMARDs, potentially improving treatment efficacy in rheumatoid arthritis patients.
类风湿性关节炎（RA）是一种常见疾病，通常使用生物改善病情抗风湿药物（bDMARDs）进行治疗。然而，许多患者表现出耐药性，因此需要使用机器学习模型来预测接受bDMARDs治疗患者的缓解情况，从而降低医疗成本并将负面影响降至最低。
本研究旨在利用科威特风湿病登记处（KRRD）的数据开发机器学习模型，以确定接受生物制剂治疗的RA患者缓解的预测临床特征。
该研究收集了2013年至2022年期间科威特四家公立医院1968例接受bDMARDs治疗患者的随访数据。使用套索回归、岭回归、支持向量机、随机森林、XGBoost和Shapley加性解释等机器学习技术来预测1年随访时的缓解情况。
该研究使用可解释人工智能（XAI）中的Shapley图来分析预测因素对不同类型bDMARDs缓解预后的影响。确定了接受bDMARDs治疗患者的主要临床特征，每个特征都与特定的平均SHAP值相关。研究结果突出了临床评估和特定治疗对塑造治疗结果的重要性。
所提出的机器学习模型系统有效地识别了预测bDMARDs缓解的临床特征，有可能提高类风湿性关节炎患者的治疗效果。
