A Hybrid Machine Learning Model Based on Semantic Information Can Optimize Treatment Decision for Naïve Single 3–5-cm HCC Patients
Wenzhen Ding, Zhen Wang, Fangyi Liu, Zhigang Cheng, Xiaoling Yu, Zhiyu Han, Hui Zhong, Jie Yu, Ping Liang
Abstract
<b><i>Background:</i></b> Tumor recurrence is an abomination for hepatocellular carcinoma (HCC) patients receiving local treatment. <b><i>Purpose:</i></b> The aim of the study was to build a hybrid machine learning model to recommend optimized first treatment (laparoscopic hepatectomy [LH] or microwave ablation [MWA]) for naïve single 3–5-cm HCC patients based on early recurrence (ER, ≤2 years) probability. <b><i>Methods:</i></b> This retrospective study collected 20 semantic variables of 582 patients (LH: 300, MWA: 282) from 13 hospitals with at least 24 months follow-up. Both groups were divided into training, validation, and test set, respectively. Five algorithms (logistics regression, random forest, neural network, stochastic gradient boosting, and eXtreme Gradient Boosting [XGB]) were used for model building. A model with highest area under the receiver operating characteristic curve (AUC) in a validation set of LH and MWA was selected to connect as a hybrid model which made decision based on ER probability. Model testing was performed in a comprehensive set comprising LH and MWA test sets. <b><i>Results:</i></b> Four variables in each group were selected to build LH and MWA models, respectively. LH-XGB model (AUC = 0.744) and MWA-stochastic gradient method (AUC = 0.750) model were selected for model building. In the comprehensive set, a treatment confusion matrix was established based on recommended and actual treatment. The predicted ER probabilities were comparable with the actual ER rates for various types of patients in matrix (<i>p</i> &#x3e; 0.05). ER rate of patients whose actual treatment consistent with recommendation was lower than that of inconsistent patients (LH: 21.2% vs. 46.2%, <i>p</i> = 0.042; MWA: 26.3% vs. 54.1%, <i>p</i> = 0.048). By recommending optimal treatment, the hybrid model can significantly reduce ER probability from 38.2% to 25.6% for overall patients (<i>p</i> &#x3c; 0.001). <b><i>Conclusions:</i></b> The hybrid model can accurately predict ER probability of different treatments and thereby provide reliable evidence to make optimal treatment decision for patients with single 3–5-cm HCC.