Wei Xiaoqin, Wang Fang, Liu Ying, Li Zeyong, Xue Zhong, Tang Mingyue, Chen Xiaowen
School of Medical Imaging, North Sichuan Medical College, Nanchong City, Sichuan Province, People's Republic of China.
Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd, Shanghai, People's Republic of China.
J Hepatocell Carcinoma. 2024 Aug 30;11:1675-1687. doi: 10.2147/JHC.S470550. eCollection 2024.
To predict the efficacy of patients treated with hepatectomy and transarterial chemoembolization (TACE) based on machine learning models using clinical and radiomics features.
Patients with HCC whose first treatment was hepatectomy or TACE from June 2016 to July 2021 were collected in the retrospective cohort study. To ensure a causal effect of treatment effect and treatment modality, perfectly matched patients were obtained according to the principle of propensity score matching and used as an independent test cohort. Inverse probability of treatment weighting was used to control bias for unmatched patients, and the weighted results were used as the training cohort. Clinical characteristics were selected by univariate and multivariate analysis of cox proportional hazards regression, and radiomics features were selected using correlation analysis and random survival forest. The machine learning models (Death and Death) were constructed to predict the probability of patient death after treatment (hepatectomy and TACE) by combining clinical and radiomics features, and an optimal treatment regimen was recommended. In addition, a prognostic model was constructed to predict the survival time of all patients.
A total of 418 patients with HCC who received either hepatectomy (n=267, mean age, 58 years ± 11 [standard deviation]; 228 men) or TACE (n=151, mean age, 59 years ± 13 [standard deviation]; 127 men) were recruited. After constructing the machine learning models Death and Death, patients were divided into the hepatectomy-preferred and TACE-preferred groups. In the hepatectomy-preferred group, hepatectomy had a significantly prolonged survival time than TACE (training cohort: < 0.001; testing cohort: < 0.001), and vise versa for the TACE-preferred group. In addition, the prognostic model yielded high predictive capability for overall survival.
The machine learning models could predict the outcomes difference between hepatectomy and TACE, and prognostic models could predict the overall survival for HCC patients.
基于使用临床和影像组学特征的机器学习模型，预测接受肝切除术和经动脉化疗栓塞术（TACE）治疗的患者的疗效。
在这项回顾性队列研究中，收集了2016年6月至2021年7月首次接受肝切除术或TACE治疗的肝癌患者。为确保治疗效果与治疗方式之间的因果关系，根据倾向得分匹配原则获得完全匹配的患者，并将其用作独立测试队列。采用治疗权重逆概率法控制未匹配患者的偏倚，加权结果用作训练队列。通过Cox比例风险回归的单变量和多变量分析选择临床特征，使用相关分析和随机生存森林选择影像组学特征。构建机器学习模型（死亡和死亡），通过结合临床和影像组学特征预测患者治疗（肝切除术和TACE）后的死亡概率，并推荐最佳治疗方案。此外，构建了一个预后模型来预测所有患者的生存时间。
共招募了418例肝癌患者，其中接受肝切除术的患者267例（平均年龄58岁±11[标准差]；男性228例），接受TACE治疗的患者151例（平均年龄59岁±13[标准差]；男性127例）。构建机器学习模型“死亡”和“死亡”后，将患者分为肝切除术优先组和TACE优先组。在肝切除术优先组中，肝切除术的生存时间显著长于TACE（训练队列：<0.001；测试队列：<0.001），而在TACE优先组中则相反。此外，预后模型对总生存具有较高的预测能力。
机器学习模型可以预测肝切除术和TACE之间的疗效差异，预后模型可以预测肝癌患者的总生存情况。
