"Mortality prediction in patients with hyperglycaemic crisis using explainable machine learning: a prospective, multicentre study based on tertiary hospitals"
作者全名:"Xie, Puguang; Yang, Cheng; Yang, Gangyi; Jiang, Youzhao; He, Min; Jiang, Xiaoyan; Chen, Yan; Deng, Liling; Wang, Min; Armstrong, David G. G.; Ma, Yu; Deng, Wuquan"
作者地址:"[Xie, Puguang; Yang, Cheng; Jiang, Xiaoyan; Chen, Yan; Deng, Liling; Wang, Min; Ma, Yu; Deng, Wuquan] Chongqing Univ, Chongqing Univ Cent Hosp, Chongqing Emergency Med Ctr, Dept Endocrinol, 1 Jiankang Rd, Chongqing 400014, Peoples R China; [Xie, Puguang; Yang, Cheng; Jiang, Xiaoyan; Chen, Yan; Deng, Liling; Wang, Min; Ma, Yu; Deng, Wuquan] Chongqing Univ, Chongqing Univ Cent Hosp, Bioengn Coll, Chongqing Emergency Med Ctr, 1 Jiankang Rd, Chongqing 400014, Peoples R China; [Yang, Gangyi] Chongqing Med Univ, Affiliated Hosp 2, Dept Endocrinol, Chongqing 400010, Peoples R China; [Jiang, Youzhao] Peoples Hosp Chongqing Banan Dist, Dept Endocrinol, Chongqing 401320, Peoples R China; [He, Min] Chongqing Southwest Hosp, Gen Practice Dept, Chongqing 400038, Peoples R China; [Armstrong, David G. G.] Univ Southern Calif, Dept Surg, Keck Sch Med, Los Angeles, CA 90033 USA"
通信作者:"Ma, Y; Deng, WQ (通讯作者),Chongqing Univ, Chongqing Univ Cent Hosp, Chongqing Emergency Med Ctr, Dept Endocrinol, 1 Jiankang Rd, Chongqing 400014, Peoples R China.; Ma, Y; Deng, WQ (通讯作者),Chongqing Univ, Chongqing Univ Cent Hosp, Bioengn Coll, Chongqing Emergency Med Ctr, 1 Jiankang Rd, Chongqing 400014, Peoples R China."
来源:DIABETOLOGY & METABOLIC SYNDROME
ESI学科分类:CLINICAL MEDICINE
WOS号:WOS:000948405000004
JCR分区:Q2
影响因子:3.4
年份:2023
卷号:15
期号:1
开始页:
结束页:
文献类型:Article
关键词:Hyperglycaemic crisis; Mortality; Machine learning; Explainable model
摘要:"BackgroundExperiencing a hyperglycaemic crisis is associated with a short- and long-term increased risk of mortality. We aimed to develop an explainable machine learning model for predicting 3-year mortality and providing individualized risk factor assessment of patients with hyperglycaemic crisis after admission.MethodsBased on five representative machine learning algorithms, we trained prediction models on data from patients with hyperglycaemic crisis admitted to two tertiary hospitals between 2016 and 2020. The models were internally validated by tenfold cross-validation and externally validated using previously unseen data from two other tertiary hospitals. A SHapley Additive exPlanations algorithm was used to interpret the predictions of the best performing model, and the relative importance of the features in the model was compared with the traditional statistical test results.ResultsA total of 337 patients with hyperglycaemic crisis were enrolled in the study, 3-year mortality was 13.6% (46 patients). 257 patients were used to train the models, and 80 patients were used for model validation. The Light Gradient Boosting Machine model performed best across testing cohorts (area under the ROC curve 0.89 [95% CI 0.77-0.97]). Advanced age, higher blood glucose and blood urea nitrogen were the three most important predictors for increased mortality.ConclusionThe developed explainable model can provide estimates of the mortality and visual contribution of the features to the prediction for an individual patient with hyperglycaemic crisis. Advanced age, metabolic disorders, and impaired renal and cardiac function were important factors that predicted non-survival.Trial Registration Number: ChiCTR1800015981, 2018/05/04."
基金机构:
基金资助正文: