Park Haesuk, Lo-Ciganic Wei-Hsuan, Huang James, Wu Yonghui, Henry Linda, Peter Joy, Sulkowski Mark, Nelson David R
Department of Pharmaceutical Outcomes and Policy, College of Pharmacy, University of Florida, HPNP Building Room 3325, 1225 Center Drive, Gainesville, FL, 32610, USA.
Health Outcomes & Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL, USA.
Sci Rep. 2022 Oct 27;12(1):18094. doi: 10.1038/s41598-022-22819-4.
Despite the availability of efficacious direct-acting antiviral (DAA) therapy, the number of people infected with hepatitis C virus (HCV) continues to rise, and HCV remains a leading cause of liver-related morbidity, liver transplantation, and mortality. We developed and validated machine learning (ML) algorithms to predict DAA treatment failure. Using the HCV-TARGET registry of adults who initiated all-oral DAA treatment, we developed elastic net (EN), random forest (RF), gradient boosting machine (GBM), and feedforward neural network (FNN) ML algorithms. Model performances were compared with multivariable logistic regression (MLR) by assessing C statistics and other prediction evaluation metrics. Among 6525 HCV-infected adults, 308 patients (4.7%) experienced DAA treatment failure. ML models performed similarly in predicting DAA treatment failure (C statistic [95% CI]: EN, 0.74 [0.69-0.79]; RF, 0.74 [0.69-0.80]; GBM, 0.72 [0.67-0.78]; FNN, 0.75 [0.70-0.80]), and all 4 outperformed MLR (C statistic [95% CI]: 0.51 [0.46-0.57]), and EN used the fewest predictors (n = 27). With Youden index, the EN had 58.4% sensitivity and 77.8% specificity, and nine patients were needed to evaluate to identify 1 DAA treatment failure. Over 60% treatment failure were classified in top three risk decile subgroups. EN-identified predictors included male sex, treatment < 8 weeks, treatment discontinuation due to adverse events, albumin level < 3.5 g/dL, total bilirubin level > 1.2 g/dL, advanced liver disease, and use of tobacco, alcohol, or vitamins. Addressing modifiable factors of DAA treatment failure may reduce the burden of retreatment. Machine learning algorithms have the potential to inform public health policies regarding curative treatment of HCV.
尽管有有效的直接抗病毒（DAA）疗法，但丙型肝炎病毒（HCV）感染者的数量仍在持续上升，HCV仍然是导致肝脏相关发病、肝移植和死亡的主要原因。我们开发并验证了用于预测DAA治疗失败的机器学习（ML）算法。利用启动全口服DAA治疗的成年人的HCV-TARGET登记数据，我们开发了弹性网络（EN）、随机森林（RF）、梯度提升机（GBM）和前馈神经网络（FNN）ML算法。通过评估C统计量和其他预测评估指标，将模型性能与多变量逻辑回归（MLR）进行比较。在6525名HCV感染的成年人中，308例患者（4.7%）经历了DAA治疗失败。ML模型在预测DAA治疗失败方面表现相似（C统计量[95%CI]：EN为0.74[0.69 - 0.79]；RF为0.74[0.69 - 0.80]；GBM为0.72[0.67 - 0.78]；FNN为0.75[0.70 - 0.80]），并且这4种模型均优于MLR（C统计量[95%CI]：0.51[0.46 - 0.57]），且EN使用的预测变量最少（n = 27）。根据约登指数，EN的灵敏度为58.4%，特异度为77.8%，每评估9例患者可识别1例DAA治疗失败。超过60%的治疗失败被归类在前三个风险十分位数亚组中。EN识别出的预测因素包括男性、治疗时间<8周、因不良事件停药、白蛋白水平<3.5g/dL、总胆红素水平>1.2g/dL、晚期肝病以及使用烟草、酒精或维生素。解决DAA治疗失败的可改变因素可能会减轻再次治疗的负担。机器学习算法有可能为有关HCV治愈性治疗的公共卫生政策提供信息。
