Table 1_Machine learning-based predictive model for immune checkpoint inhibitors response in gastrointestinal cancers.docx

IntroductionGastrointestinal (GI) cancers present significant clinical challenges characterized by dismal survival outcomes and suboptimal prognoses. Currently, only partial indicators are available to predict the response of immunotherapy. A critical gap remains in the development of models capable of accurately predicting response rates to immunotherapy regimens. In this study, we developed a machine-learning (ML) model based on factorial, molecular, demographic, and clinical data to predict the response rate.
MethodsThis multicentre retrospective study analyzed the clinical data of 506 patients, comprising 352 cases collected from Zhongnan Hospital of Wuhan University and Hubei Cancer Hospital, along with 154 cases obtained from the publicly available dataset of Memorial Sloan-Kettering Hospital. We used 14 features as input features, such as the patient’s basic status, biochemical test results, and genetic test results. Eight ML methods were employed to build predictive models. Through rigorous validation using seven discriminative performance metrics (accuracy, precision, recall, F1-score, ROC-AUC, PR-AUC, and Brier score), the eXtreme Gradient Boosting (XGBoost) algorithm demonstrated superior predictive capability. Model interpretability was subsequently enhanced through Shapley Additive explanations (SHAP) analysis to elucidate feature contributions.
ResultsWe selected XGBoost with the best predictive performance to predict response (AUC: 0.829 [95% CI: 0.72–0.91], accuracy: 78.43%, sensitivity: 86.67%, specificity: 72.31%). The Delong test and calibration curve indicated that XGBoost significantly outperformed the other models in prediction. The SHAP values indicate that chemotherapy contributes the most to the model’s predictive accuracy (contribution score = 0.28), while Ki-67 exhibits the lowest contribution rate (0.01). In addition, the study showed that chemotherapy, higher hemoglobin (HGB), body mass index (BMI), age, lower neutrophil-to-lymphocyte ratio (NLR), and tumor stage positively influenced the output of the model.
ConclusionInterpretable XGBoost models have shown accuracy, efficiency, and robustness in determining the association between input features and response rates. Among the input features, chemotherapy and tumor stage played the most important role in the prediction model. Due to the varying efficacy of ICIs in gastrointestinal cancers, personalized predictive models can greatly assist clinical decision-making. This model fills this gap in clinical practice and can provide more precise support for personalized treatment and risk avoidance.

引言 胃肠道（GI）癌症是一类极具临床挑战的疾病，其特征为预后不佳、生存结局惨淡。目前仅能依靠部分指标预测免疫治疗应答情况，当前仍缺乏可精准预测免疫治疗方案应答率的模型，这是一项关键的研究空白。本研究基于多维度因子、分子、人口统计学及临床数据，构建了一款机器学习（ML）模型以预测免疫治疗应答率。
方法 本项多中心回顾性研究共分析了506例患者的临床数据，其中352例采集自武汉大学中南医院与湖北省肿瘤医院，剩余154例来自公开的纪念斯隆-凯特琳癌症中心（Memorial Sloan-Kettering Hospital）数据集。研究选取14项特征作为输入特征，涵盖患者基础状态、生化检验结果与基因检测结果等。本研究采用8种机器学习方法构建预测模型，通过准确率、精确率、召回率、F1分数、受试者工作特征曲线下面积（ROC-AUC）、精确率-召回率曲线下面积（PR-AUC）以及布里尔分数（Brier score）共7项判别性能指标进行严格验证后，极限梯度提升（XGBoost）算法展现出最优的预测性能。随后通过夏普利可加解释（SHAP）分析提升模型可解释性，以阐明各特征的贡献度。
结果 本研究选取预测性能最优的XGBoost模型进行应答预测，其受试者工作特征曲线下面积（AUC）为0.829[95%置信区间（CI）：0.72~0.91]，准确率为78.43%，灵敏度为86.67%，特异度为72.31%。德朗检验（Delong test）与校准曲线分析结果显示，XGBoost模型的预测性能显著优于其余所有模型。SHAP值分析结果表明，化疗对模型预测准确率的贡献度最高（贡献分数=0.28），而Ki-67的贡献度最低（0.01）。此外，本研究发现化疗、较高的血红蛋白（HGB）水平、体质量指数（BMI）、年龄、较低的中性粒细胞与淋巴细胞比值（NLR）以及肿瘤分期均对模型输出产生正向影响。
结论 可解释性XGBoost模型在解析输入特征与应答率之间的关联时，展现出优异的准确性、效率与鲁棒性。在所有输入特征中，化疗与肿瘤分期在预测模型中发挥了最为关键的作用。鉴于免疫检查点抑制剂（ICIs）在胃肠道癌症中的疗效存在个体差异，个性化预测模型可极大助力临床决策制定。本模型填补了临床实践中的该项空白，可为个性化治疗与风险规避提供更为精准的支持。