Scholarlink

Background <p>Programmed death ligand 1 (PD-L1) expression status, closely related to immunotherapy outcomes, is a reliable biomarker for screening patients who may benefit from immunotherapy. Here, we developed and validated an interpretable machine learning (ML) model based on contrast-enhanced computed tomography (CECT) radiomics for preoperatively predicting PD-L1 expression status in patients with gastric cancer (GC).</p> Methods <p>We retrospectively recruited 285 GC patients who underwent CECT and PD-L1 detection from two medical centers. A PD-L1 combined positive score (CPS) of ≥ 5 was considered to indicate a high PD-L1 expression status. Patients from center 1 were divided into training (<i>n</i> = 143) and validation sets (<i>n</i> = 62), and patients from center 2 were considered a test set (<i>n</i> = 80). Radiomics features were extracted from venous-phase CT images. After feature reduction and selection, 11 ML algorithms were employed to develop predictive models, and their performance in predicting PD-L1 expression status was evaluated using areas under receiver operating characteristic curves (AUCs). SHapley Additive exPlanations (SHAP) were used to interpret the optimal model and visualize the decision-making process for a single individual.</p> Results <p>Nine features significantly associated with PD-L1 expression status were ultimately selected to construct the predictive model. The light gradient-boosting machine (LGBM) model demonstrated the best performance for PD-L1 high expression status prediction in the training, validation, and test sets, with AUCs of 0.841(95% CI: 0.773, 0.908), 0.834 (95% CI:0.729, 0.939), and 0.822 (95% CI: 0.718, 0.926), respectively. The SHAP summary and bar plots illustrated that a feature’s value affected the feature’s impact attributed to the model. The SHAP waterfall plots were used to visualize the decision-making process for a single individual.</p> Conclusion <p>Our CT radiomics–based LGBM model may aid in preoperatively predicting PD-L1 expression status in GC patients, and the SHAP method may improve the interpretability of this model.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An interpretable machine learning model based on computed tomography radiomics for predicting programmed death ligand 1 expression status in gastric cancer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月12日

查看全文
  • Lihuan Dai,
  • Jinxue Yin,
  • Xin Xin,
  • Chun Yao,
  • Yongfang Tang,
  • Xiaohong Xia,
  • Yuanlin Chen,
  • Shuying Lai,
  • Guoliang Lu,
  • Jie Huang,
  • Purong Zhang,
  • Jiansheng Li,
  • Xiangguang Chen,
  • Xi Zhong

摘要

Background

Programmed death ligand 1 (PD-L1) expression status, closely related to immunotherapy outcomes, is a reliable biomarker for screening patients who may benefit from immunotherapy. Here, we developed and validated an interpretable machine learning (ML) model based on contrast-enhanced computed tomography (CECT) radiomics for preoperatively predicting PD-L1 expression status in patients with gastric cancer (GC).

Methods

We retrospectively recruited 285 GC patients who underwent CECT and PD-L1 detection from two medical centers. A PD-L1 combined positive score (CPS) of ≥ 5 was considered to indicate a high PD-L1 expression status. Patients from center 1 were divided into training (n = 143) and validation sets (n = 62), and patients from center 2 were considered a test set (n = 80). Radiomics features were extracted from venous-phase CT images. After feature reduction and selection, 11 ML algorithms were employed to develop predictive models, and their performance in predicting PD-L1 expression status was evaluated using areas under receiver operating characteristic curves (AUCs). SHapley Additive exPlanations (SHAP) were used to interpret the optimal model and visualize the decision-making process for a single individual.

Results

Nine features significantly associated with PD-L1 expression status were ultimately selected to construct the predictive model. The light gradient-boosting machine (LGBM) model demonstrated the best performance for PD-L1 high expression status prediction in the training, validation, and test sets, with AUCs of 0.841(95% CI: 0.773, 0.908), 0.834 (95% CI:0.729, 0.939), and 0.822 (95% CI: 0.718, 0.926), respectively. The SHAP summary and bar plots illustrated that a feature’s value affected the feature’s impact attributed to the model. The SHAP waterfall plots were used to visualize the decision-making process for a single individual.

Conclusion

Our CT radiomics–based LGBM model may aid in preoperatively predicting PD-L1 expression status in GC patients, and the SHAP method may improve the interpretability of this model.