Precise risk-prediction model including arterial stiffness for new-onset atrial fibrillation using machine learning techniques.

Atrial fibrillation (AF) is the most common clinically significant cardiac arrhythmia and is an important risk factor for ischemic cerebrovascular events. This study used machine learning techniques to develop and validate a new risk prediction model for new-onset AF that incorporated the use electrocardiogram to diagnose AF, data from participants with a wide age range, and considered hypertension and measures of atrial stiffness. In Japan, Industrial Safety and Health Law requires employers to provide annual health check-ups to their employees. This study included 13 410 individuals who underwent health check-ups on at least four successive years between 2005 and 2015 (new-onset AF, n = 110; non-AF, n = 13 300). Data were entered into a risk prediction model using machine learning methods (eXtreme Gradient Boosting and Shapley Additive Explanation values). Data were randomly split into a training set (80%) used for model construction and development, and a test set (20%) used to test performance of the derived model. The area under the receiver operator characteristic curve for the model in the test set was 0.789. The best predictor of new-onset AF was age, followed by the cardio-ankle vascular index, estimated glomerular filtration rate, sex, body mass index, uric acid, γ-glutamyl transpeptidase level, triglycerides, systolic blood pressure at cardio-ankle vascular index measurement, and alanine aminotransferase level. This new model including arterial stiffness measure, developed with data from a general population using machine learning methods, could be used to identify at-risk individuals and potentially facilitation the prevention of future AF development.

Highly precise risk prediction model for new-onset hypertension using artificial intelligence techniques.

Hypertension is a significant public health issue. The ability to predict the risk of developing hypertension could contribute to disease prevention strategies. This study used machine learning techniques to develop and validate a new risk prediction model for new-onset hypertension. In Japan, Industrial Safety and Health Law requires employers to provide annual health checkups to their employees. We used 2005-2016 health checkup data from 18 258 individuals, at the time of hypertension diagnosis [Year (0)] and in the two previous annual visits [Year (-1) and Year (-2)]. Data were entered into models based on machine learning methods (XGBoost and ensemble) or traditional statistical methods (logistic regression). Data were randomly split into a derivation set (75%, n = 13 694) used for model construction and development, and a validation set (25%, n = 4564) used to test performance of the derived models. The best predictor in the XGBoost model was systolic blood pressure during cardio-ankle vascular index measurement at Year (-1). Area under the receiver operator characteristic curve values in the validation cohort were 0.877, 0.881, and 0.859 for the XGBoost, ensemble, and logistic regression models, respectively. We have developed a highly precise prediction model for future hypertension using machine learning methods in a general normotensive population. This could be used to identify at-risk individuals and facilitate earlier non-pharmacological intervention to prevent the future development of hypertension.

Electrocardiographic ST-T Area Assessed by a Computerized Quantitative Method and Its Relation to Cardiovascular Events: The J-HOP Study.

BACKGROUND: Although many studies have reported that the presence of minor or major ST-T change of electrocardiography (ECG) was associated with a risk of cardiovascular events, it is not clear whether there is a difference in the prognostic power depending on the summation of ST-T area (ST-Tarea) assessed by a quantitative method. METHODS: Electrocardiograms were performed in 834 clinical patients with one or more cardiovascular risks. ST-Tarea was assessed as the area enclosed by the baseline from the end of the QRS complex to the end of the ST-T segment using a computerized quantitative method. We used the lower magnitude of ST-Tarea in the V5 or V6 lead for the analysis. RESULTS: After a mean follow-up 8.4 ± 2.9 years (7,001 person-years), there were 92 cardiovascular events. With adjustment for covariates, the results from Cox proportional hazards models (Model 1) suggested that the lowest quartile of ST-Tarea was associated with a higher risk for cardiovascular outcome compared with the remaining quartile groups (hazard ratio, 2.08; 95% confidence interval, 1.36-3.16, P < 0.01). Even when adding the ECG left ventricular hypertrophy by Cornell voltage (Model 2) and Cornell product (Model 3) to Model 1, the significance remained (both P < 0.01). When we used ST-Tarea as a continuous variable substitute for the lowest quartile of ST-Tarea, these associations were similar in all models (all P < 0.01). CONCLUSION: The lower summations of ST-T area assessed by a computerized quantitative method were associated with increased risk of cardiovascular disease incidence in a clinical population.