COPD全因死亡的机器学习与预测.pdf

COPD Original Research 委CHEST Check for updates All-Cause Mortality in COPD BACKGROUND: COPD is a leading cause of mortality. dyspnea, and airflow obstruction index. shinyapps.io/egmortalityapp/. FOR EDITORIAL COMMENT,SEE PAGE 846 ABBREVIATIONS: 6MWD =6-min walk distance; ADO =age,dyspnea. and airflow obstruction; BODE=BMI,airfiow obstruction, dyspnea, and exercise capacity: COPDGene -Genetic Epidemiology of COPD;survival forest; VIMP = variable importance ECLIPSE= Evaluation of COPD Longitudinally to ldentify Predictive Surrogate Endpoints; MLMP = machine learning mortality prediction; PA:A'= pulmonary artery to aorta;LAA <-950 Hu'=percent emphysema determined by the percent low attenuation area of the 952 Onginal Research COPD is one of the leading causes of mortality worldwide. Improving performance of mortality prediction models can identify patients with COPD who might benefit from earlier or more specific intervention. One widely used mortality prediction tool is the BMI, airflow obstruction, dyspnea, and exercise capacity (BODE) index. Studies that have modified the BODE index by varying the input' or adding serum biomarkersf have resulted in similar or slightly improved performance for mortality prediction. Other models include the dyspnea, airflow obstruction, smoking status, exacerbation frequency (DOSE) index; the age, dyspnea, and airflow obstruction (ADO)index; and the St. George's Respiratory Questionnaire score, airflow limitation, and exercise tolerance (SAFE)"index. A survival analysis in more than 3,500 subjects from 11 COPD cohorts compared predictive accuracy of several of these measures,finding that ADO, BODE,and BODE modifications performed best; after adjusting for age, BODE modifications outperformed ADO.'" A meta- the Division of Pulmonary and Critic