Liu Wentong, Ji Kaiyue, Tang Qianwen, Xia Weiqi, Zhang Wei, Shao Lina, Shi Jiana, Li Yukun, Huang Ping, Ye Xiaolan
Center for Clinical Pharmacy, Cancer Center, Department of Pharmacy, Zhejiang Provincial People's Hospital(Affiliated People's Hospital), Hangzhou Medical College, Hangzhou, Zhejiang, 310014, China.
School of Pharmacy, Hangzhou Normal University, Hangzhou, Zhejiang, 311121, China.
BMC Med Inform Decis Mak. 2025 Aug 8;25(1):295. doi: 10.1186/s12911-025-03142-0.
BACKGROUND: Anti-programmed cell death protein 1 (PD-1)/programmed cell death ligand 1 (PD-L1) immunotherapy has revolutionized cancer treatment. However, it can cause immune-related adverse events, including acute kidney injury (AKI). Such adverse events can interrupt treatment, affecting patient outcomes. Early prediction of AKI is essential for improved prognosis and personalized therapeutic strategies. Previous research has been constrained by significant limitations, underscoring the necessity for AKI risk prediction models for patients treated with PD-1/PD-L1 inhibitors. This study aimed to develop and validate an interpretable machine learning (ML) model for early AKI prediction in patients undergoing PD-1/PD-L1 inhibitor therapy using a retrospective cohort design. METHODS: This study collected data from patients treated with PD-1/PD-L1 inhibitors at Zhejiang Provincial People's Hospital between January 2018 and January 2024. Nine ML models were evaluated. SHapley Additive exPlanations (SHAP) were employed to rank feature importance and interpret the final model. Additionally, a web-based calculator based on the model was developed. RESULTS: Among the nine ML models evaluated, the Grandient Boosting Machine (GBM) model achieved the best predictive performance. In the validation set, the GBM model achieved an AUC of 0.850 (95%CI: 0.830-0.870). In the test set, the AUC was 0.795(95% CI: 0.747-0.844), demonstrating accurate AKI risk prediction. Calibration curves demonstrated a strong concordance between predicted and observed risk probabilities. An interpretable final GBM model with 13 features was developed after feature reduction based on feature importance ranking. A web-based calculator accessible at https://predicatingaki.shinyapps.io/PDmodel/ has been developed to assist clinicians in AKI risk assessment. CONCLUSION: This study developed and validated an interpretable ML model using a large dataset to predict AKI risk in patients receiving PD-1/PD-L1 inhibitor therapy. This model can assist clinicians in the early identification of high-risk patients, facilitating personalized treatment plans. TRIAL REGISTRATION: The study was conducted following the Declaration of Helsinki and was approved by the Ethics Committee of Zhejiang Provincial People's Hospital (Approval No. KT2024116) in 3 Jan. 2025. As it was a retrospective study with anonymized data, informed consent was waived.
背景：抗程序性细胞死亡蛋白1（PD-1）/程序性细胞死亡配体1（PD-L1）免疫疗法彻底改变了癌症治疗方式。然而，它可能会引发免疫相关不良事件，包括急性肾损伤（AKI）。此类不良事件可能会中断治疗，影响患者预后。AKI的早期预测对于改善预后和制定个性化治疗策略至关重要。先前的研究受到显著限制，这凸显了为接受PD-1/PD-L1抑制剂治疗的患者建立AKI风险预测模型的必要性。本研究旨在采用回顾性队列设计，开发并验证一种可解释的机器学习（ML）模型，用于预测接受PD-1/PD-L1抑制剂治疗患者的早期AKI。 方法：本研究收集了2018年1月至2024年1月期间在浙江省人民医院接受PD-1/PD-L1抑制剂治疗患者的数据。对9种ML模型进行了评估。采用SHapley加性解释（SHAP）对特征重要性进行排名并解释最终模型。此外，还基于该模型开发了一个基于网络的计算器。 结果：在评估的9种ML模型中，梯度提升机（GBM）模型具有最佳预测性能。在验证集中，GBM模型的曲线下面积（AUC）为0.850（95%CI：0.830-0.870）。在测试集中，AUC为0.795（95%CI：0.747-0.844），表明对AKI风险预测准确。校准曲线显示预测风险概率与观察到的风险概率之间具有高度一致性。在根据特征重要性排名进行特征约简后，开发了一个具有13个特征的可解释最终GBM模型。已开发出一个基于网络的计算器，可通过https://predicatingaki.shinyapps.io/PDmodel/访问，以协助临床医生进行AKI风险评估。 结论：本研究利用大型数据集开发并验证了一种可解释的ML模型，用于预测接受PD-1/PD-L1抑制剂治疗患者的AKI风险。该模型可协助临床医生早期识别高危患者，促进个性化治疗方案的制定。 试验注册：本研究遵循《赫尔辛基宣言》进行，并于2025年1月3日获得浙江省人民医院伦理委员会批准（批准号：KT2024116）。由于这是一项使用匿名数据的回顾性研究，因此无需获得知情同意。
Clin Orthop Relat Res. 2024-9-1
BMC Med Inform Decis Mak. 2025-7-15
Zotero 插件