Search

BackgroundIn patients with suspected obstructive coronary artery disease (CAD), evaluation using a pre-test probability model is the key element for diagnosis; however, its accuracy is controversial. This study aimed to develop machine learning (ML) models using clinically relevant biomarkers to predict the presence of stable obstructive CAD and to compare ML models with an established pre-test probability of CAD models.MethodsEight machine learning models for prediction of obstructive CAD were trained on a cohort of 1,312 patients [randomly split into the training (80%) and internal validation sets (20%)]. Twelve clinical and blood biomarker features assessed on admission were used to inform the models. We compared the best-performing ML model and established the pre-test probability of CAD (updated Diamond-Forrester and CAD consortium) models.ResultsThe CatBoost algorithm model showed the best performance (area under the receiver operating characteristics, AUROC, 0.796, and 95% confidence interval, CI, 0.740–0.853; Matthews correlation coefficient, MCC, 0.448) compared to the seven other algorithms. The CatBoost algorithm model improved risk prediction compared with the CAD consortium clinical model (AUROC 0.727; 95% CI 0.664–0.789; MCC 0.313). The accuracy of the ML model was 74.6%. Age, sex, hypertension, high-sensitivity cardiac troponin T, hemoglobin A1c, triglyceride, and high-density lipoprotein cholesterol levels contributed most to obstructive CAD prediction.ConclusionThe ML models using clinically relevant biomarkers provided high accuracy for stable obstructive CAD prediction. In real-world practice, employing such an approach could improve discrimination of patients with suspected obstructive CAD and help select appropriate non-invasive testing for ischemia.

BackgroundThere is a paucity of information about mortality related to light-intensity physical activity (LPA) in the older population. We examine the associations between physical activity and mortality, focusing on the effect of light-intensity physical activity and the dose-response relationship between physical activity and mortality.MethodsWe analyzed a total of 58,537 participants aged ≥ 65 years (mean age, 73.9 ± 5.8 years; male, 36.0%) in the Korean National Health Insurance Service database between 2009 and 2012. The Date of the end of follow-up was December 31, 2013. Individuals were divided into four categories according to physical activity intensity: totally sedentary (43.3%), LPA only (35.8%), LPA and moderate- to vigorous-intensity physical activity (MVPA) (16.3%), MVPA only (4.5%). Physical activity was quantified using standardized self-reported questionnaires which composed of the duration and frequency of physical activity.ResultsDuring a mean follow-up of 39.6 ± 14.0 months, 5,651 (9.7%) deaths occurred. Compared with totally sedentary individuals, those in the LPA only, LPA and MVPA, and MVPA only groups showed 26% [hazard ratio (HR) 0.74, 95% confidence interval (CI) 0.68–0.82], 27% (HR 0.73, 95% CI 0.63–0.84), and 34% (HR 0.66, 95% CI 0.54–0.79) lower all-cause mortality risk, showing an inverse relationship between physical activity intensity and mortality risk. In contrast, the LPA only, LPA and MVPA, and MVPA only groups represented a stronger inverse association with CV mortality (LPA: HR 0.76, 95% CI 0.62–0.92; LPA with MVPA: HR 0.74, 95% CI 0.55–0.999; MVPA, HR 0.57, 95% CI 0.37–0.87). Among participants performing LPA alone, participants performing less than the recommended dose of physical activity had lower all-cause mortality than those with sedentary activity (1–249 MET-min/week: HR 0.74, 95% CI 0.67–0.82, 250–499 MET-min/week: HR 0.65, 95% CI 0.59–0.72).ConclusionPhysical activity, even low doses of LPA, was associated with reduced mortality risk in the elderly population. This study may motivate sedentary individuals to engage in any physical activity for mortality benefits.