Zhang Sheng, Lu Gaochen, Wang Weihong, Li Qianqian, Wang Rui, Zhang Zulun, Wu Xia, Liang Chenchen, Liu Yujie, Li Pan, Wen Quan, Cui Bota, Zhang Faming
Department of Microbiota Medicine & Medical Center for Digestive Diseases, the Second Affiliated Hospital of Nanjing Medical University, Nanjing, China.
Jiangsu Engineering Research Center for Advanced Microbiota Medicine, Key Lab of Holistic Integrative Enterology, the Second Affiliated Hospital of Nanjing Medical University, Nanjing, China.
Comput Struct Biotechnol J. 2024 Aug 24;24:583-592. doi: 10.1016/j.csbj.2024.08.021. eCollection 2024 Dec.
Machine learning based on clinical data and treatment protocols for better clinical decision-making is a current research hotspot. This study aimed to build a machine learning model on washed microbiota transplantation (WMT) for ulcerative colitis (UC), providing patients and clinicians with a new evaluation system to optimize clinical decision-making. Patients with UC who underwent WMT via mid-gut or colonic delivery route at an affiliated hospital of Nanjing Medical University from April 2013 to June 2022 were recruited. Model ensembles based on the clinical indicators were constructed by machine-learning to predict the clinical response of WMT after one month. A total of 366 patients were enrolled in this study, with 210 patients allocated for training and internal validation, and 156 patients for external validation. The low level of indirect bilirubin, activated antithrombin III, defecation frequency and cholinesterase and the elderly and high level of creatine kinase, HCO and thrombin time were related to the clinical response of WMT at one month. Besides, the voting ensembles exhibited an area under curve (AUC) of 0.769 ± 0.019 [accuracy, 0.754; F1-score, 0.845] in the internal validation; the AUC of the external validation was 0.614 ± 0.017 [accuracy, 0.801; F1-score, 0.887]. Additionally, the model was available at https://wmtpredict.streamlit.app. This study pioneered the development of a machine learning model to predict the one-month clinical response of WMT on UC. The findings demonstrate the potential value of machine learning applications in the field of WMT, opening new avenues for personalized treatment strategies in gastrointestinal disorders. clinical trials, NCT01790061. Registered 09 February 2013 - Retrospectively registered, https://clinicaltrials.gov/study/NCT01790061.
基于临床数据和治疗方案的机器学习以实现更好的临床决策是当前的研究热点。本研究旨在构建一个针对溃疡性结肠炎（UC）的经清洗微生物群移植（WMT）的机器学习模型，为患者和临床医生提供一个新的评估系统以优化临床决策。招募了2013年4月至2022年6月在南京医科大学附属医院通过中肠或结肠给药途径接受WMT的UC患者。通过机器学习构建基于临床指标的模型集成，以预测WMT一个月后的临床反应。本研究共纳入366例患者，其中210例患者分配用于训练和内部验证，156例患者用于外部验证。间接胆红素水平低、抗凝血酶III活化、排便频率和胆碱酯酶水平低以及年龄较大和肌酸激酶、HCO和凝血酶时间水平高与WMT一个月后的临床反应相关。此外，投票集成在内部验证中的曲线下面积（AUC）为0.769±0.019[准确率，0.754；F1分数，0.845]；外部验证的AUC为0.614±0.017[准确率，0.801；F1分数，0.887]。此外，该模型可在https://wmtpredict.streamlit.app上获取。本研究率先开发了一种机器学习模型来预测WMT对UC的一个月临床反应。研究结果证明了机器学习应用在WMT领域的潜在价值，为胃肠道疾病的个性化治疗策略开辟了新途径。临床试验，NCT01790061。2013年2月9日注册——追溯注册，https://clinicaltrials.gov/study/NCT01790061。
