Loosen Sven H, Krieg Sarah, Chaudhari Saket, Upadhyaya Swati, Krieg Andreas, Luedde Tom, Kostev Karel, Roderburg Christoph
Department of Gastroenterology, Hepatology and Infectious Diseases, University Hospital Duesseldorf, Medical Faculty, Heinrich Heine University Duesseldorf, 40225 Duesseldorf, Germany.
IQVIA, Bangalore 560103, Karnataka, India.
J Clin Med. 2023 Jul 24;12(14):4877. doi: 10.3390/jcm12144877.
Liver transplantation (LT) is a routine therapeutic approach for patients with acute liver failure, end-stage liver disease and/or early-stage liver cancer. While 5-year survival rates have increased to over 80%, long-term outcomes are critically influenced by extrahepatic sequelae of LT and immunosuppressive therapy, including diabetes mellitus (DM). In this study, we used machine learning (ML) to predict the probability of new-onset DM following LT.
A cohort of 216 LT patients was identified from the Disease Analyzer (DA) database (IQVIA) between 2005 and 2020. Three ML models comprising random forest (RF), logistic regression (LR), and eXtreme Gradient Boosting (XGBoost) were tested as predictors of new-onset DM within 12 months after LT.
18 out of 216 LT patients (8.3%) were diagnosed with DM within 12 months after the index date. The performance of the RF model in predicting the development of DM was the highest (accuracy = 79.5%, AUC 77.5%). It correctly identified 75.0% of the DM patients and 80.0% of the non-DM patients in the testing dataset. In terms of predictive variables, patients' age, frequency and time of proton pump inhibitor prescription as well as prescriptions of analgesics, immunosuppressants, vitamin D, and two antibiotic drugs (broad spectrum penicillins, fluocinolone) were identified.
Pending external validation, our data suggest that ML models can be used to predict the occurrence of new-onset DM following LT. Such tools could help to identify LT patients at risk of unfavorable outcomes and to implement respective clinical strategies of prevention.
肝移植（LT）是治疗急性肝衰竭、终末期肝病和/或早期肝癌患者的常规治疗方法。虽然5年生存率已提高到80%以上，但LT的肝外后遗症和免疫抑制治疗，包括糖尿病（DM），对长期预后有严重影响。在本研究中，我们使用机器学习（ML）来预测LT后新发DM的概率。
从2005年至2020年的疾病分析仪（DA）数据库（IQVIA）中识别出216例LT患者队列。测试了由随机森林（RF）、逻辑回归（LR）和极端梯度提升（XGBoost）组成的三个ML模型，作为LT后12个月内新发DM的预测指标。
216例LT患者中有18例（8.3%）在索引日期后12个月内被诊断为DM。RF模型预测DM发生的性能最高（准确率 = 79.5%，AUC 77.5%）。它在测试数据集中正确识别了75.0%的DM患者和80.0%的非DM患者。在预测变量方面，确定了患者的年龄、质子泵抑制剂处方的频率和时间，以及镇痛药、免疫抑制剂、维生素D和两种抗生素药物（广谱青霉素、氟轻松）的处方。
在进行外部验证之前，我们的数据表明ML模型可用于预测LT后新发DM的发生。此类工具可帮助识别有不良预后风险的LT患者，并实施相应的临床预防策略。
