Data Sheet 3_Integrating CT radiomics and transcriptomics: a biologically-informed machine learning model for predicting chemotherapy response in advanced laryngeal cancer.xlsx

BackgroundPredicting response to induction chemotherapy (IC) in advanced laryngeal cancer (LC) remains a clinical challenge. This study aimed to develop a non-invasive, interpretable model integrating CT radiomics and clinical features to predict chemotherapy outcomes.
MethodsWe retrospectively analyzed 161 advanced LC patients treated with IC. From pre-treatment CT images, 1,321 radiomics features were extracted, and a radiomics score (Rad-score) was constructed using LASSO regression. Transcriptomic analysis explored the biological basis of Rad-score. Independent predictors were identified via multivariate logistic regression and used to build five machine learning models. Model performance was evaluated using AUC, accuracy, and specificity. SHAP analysis was applied to interpret the optimal model.
ResultsFour robust radiomics features were selected to construct the Rad-score. The Rad-score demonstrated satisfactory discrimination with an Area Under the Curve (AUC) of 0.715 in the training set and 0.707 in the validation set. In multivariate analysis, the Rad-score (Odds Ratio [OR]=2.89, 95% CI: 1.29–6.48, P = 0.010), gap invasion and validation were identified as independent predictors of chemotherapy response. Among the machine learning models, the Random Forest model achieved the best performance, yielding an AUC of 0.914 in the training set, 0.856 in the validation set, and 0.810 in the external test set. Decision curve analysis confirmed the clinical utility of the model. SHAP analysis confirmed Rad-score and fat space invasion as core predictors, with synergistic effects.
ConclusionsWe developed a highly accurate and interpretable Random Forest model that integrates radiomics and clinical features to predict IC response in advanced LC. This tool enables precise risk stratification and personalized treatment decisions, sparing non-responders from ineffective therapy. Prospective studies are needed to validate its clinical utility.

背景：预测晚期喉癌（laryngeal cancer, LC）患者对诱导化疗（induction chemotherapy, IC）的应答反应仍是临床难题。本研究旨在构建一种无创且可解释的模型，整合CT影像组学与临床特征，以预测化疗疗效。
方法：本研究回顾性分析了161例接受诱导化疗的晚期喉癌患者。从治疗前CT图像中提取1321个影像组学特征，采用LASSO回归构建影像组学评分（Rad-score）。通过转录组学分析探究影像组学评分的生物学基础。经多因素logistic回归筛选独立预测因子，并以此构建5种机器学习模型。采用受试者工作特征曲线下面积（Area Under the Curve, AUC）、准确率及特异性评估模型性能。运用SHAP（SHapley Additive exPlanations）分析对最优模型进行可解释性解读。
结果：最终筛选出4个稳定的影像组学特征用于构建影像组学评分。该影像组学评分展现出良好的区分效能：训练集受试者工作特征曲线下面积（AUC）为0.715，验证集为0.707。多因素分析显示，影像组学评分（比值比[Odds Ratio, OR]=2.89，95%置信区间[Confidence Interval, CI]：1.29~6.48，P=0.010）、间隙侵犯及验证状态为化疗应答的独立预测因子。在5种机器学习模型中，随机森林（Random Forest）模型表现最优，其训练集AUC为0.914，验证集为0.856，外部测试集为0.810。决策曲线分析证实了该模型的临床实用价值。SHAP分析确认影像组学评分与脂肪间隙侵犯为核心预测因子，二者存在协同效应。
结论：本研究构建了一种高精度且可解释的随机森林（Random Forest）模型，整合影像组学与临床特征以预测晚期喉癌患者的诱导化疗应答情况。该工具可实现精准的风险分层与个体化治疗决策，使无应答患者免于无效治疗。未来需开展前瞻性研究以验证其临床应用价值。