STEMI患者PCI術(shù)后急性腎損傷的機(jī)器學(xué)習(xí) 預(yù)測(cè)模型的構(gòu)建與驗(yàn)證

打開文本圖片集

關(guān)鍵詞：急性ST段抬高型心肌梗死（STEMI）；經(jīng)皮冠狀動(dòng)脈介入治療（PCI）；急性腎損傷（AKI）；機(jī)器學(xué)習(xí)

中圖分類號(hào)：R542.22；R692.5；TP18 文獻(xiàn)標(biāo)志碼：A

DOI：10.7652/jdyxb202503005

Construction and validation of machine learning predictive models for acute kidney injury after PCI in STEMI patients

LV Huasheng，LAZAIYI ?? Baheti，YUAN Teng，JIA Hongfei，

SHEN Haoliang，GULIJIAYINA ?? Zhaan，JI Wei，CHENYou （DepartmentofCardiology，TheFirstAffiliated Hospitalof Xinjiang Medical University，Urumqi 83Oooo，China）

ABSTRACT： ObjectiveTo construct and validate machine learning-based models to predict the risk of acute kidneyinjury（AKI） following percutaneous coronary intervention（PCI） in patients with acute ST-segment elevation myocardial infarction （STEMI）.MethodsA total of 2 315 STEMI patients who underwent PCI between January 2020 and June 2O23 were included；306（ 13.2% ）of them developed AKI. Baseline variables were screened using LASSO regression，with the optimal λ value selected via 1o-fold cross-validation to identifyAKI-associated features. Subsequently，eight distinct machine learning models were constructed and evaluated for their predictive performance.SHAP value analysis was employed to assssthe impact of key variables on model predictions.Results LASSO regresion identified seven variables significantly associated with AKI，including age，multivessel disease， preoperative creatinine，heart failure，white blood cell count，hemoglobin，and albumin levels.Among all the models，the light gradient boosting machine（LGBM）and extreme gradient boosting（XGB）demonstrated the best predictive performance，with training set AUCs being O.899（ 95% CI ： 0.877-0.921 ）and0.893（ 95% CI： 0.868-0.918） ，andvalidation set AUCs being 0.809（ 95% CI： 0.763-0.856 and0.871 95% CI： 0.833-0.909） ： respectively.SHAP analysis revealed that albumin，age，preoperative creatinine，and white blood cellcount were the primary contributors to AKI risk.ConclusionThis study successfully developed and validated machine learningbased predictive models capableof effectively identifying the risk of AKIfollowing PCI in STEMI patients，thus providing valuable support for clinical decision-making.

KEY WORDS：acute ST-elevation myocardial infarction （STEMI）；percutaneous coronary intervention（PCI）;acute kidney injury （AKI）；machine learning

急性ST段抬高型心肌梗死（ST-segmenteleva-tionmyocardialinfarction，STEMI是冠狀動(dòng)脈急性閉塞的嚴(yán)重表現(xiàn)，及時(shí)的經(jīng)皮冠狀動(dòng)脈介人治療（percutaneous coronary intervention，PCI）是改善STEMI患者預(yù)后的重要手段[1]。（剩余14528字）