A time-varying neural network model improved the prediction of atrial fibrillation compared to the CHARGE-AF risk model, achieving an AUROC of 0.827 versus 0.725.
Cohort (n=2,994,837)
Does a time-varying neural network machine learning model improve the prediction of incident atrial fibrillation compared to existing risk models in adults without a history of AF?
A time-varying machine learning model using routinely collected primary care data significantly improved the prediction of incident atrial fibrillation compared to existing risk scores, potentially reducing the number needed to screen.
Absolute Event Rate: 0.827% vs 0.725%
BACKGROUND: Atrial fibrillation (AF) is the most common sustained heart arrhythmia. However, as many cases are asymptomatic, a large proportion of patients remain undiagnosed until serious complications arise. Efficient, cost-effective detection of the undiagnosed may be supported by risk-prediction models relating patient factors to AF risk. However, there exists a need for an implementable risk model that is contemporaneous and informed by routinely collected patient data, reflecting the real-world pathology of AF. METHODS: This study sought to develop and evaluate novel and conventional statistical and machine learning models for risk-predication of AF. This was a retrospective, cohort study of adults (aged ≥30 years) without a history of AF, listed on the Clinical Practice Research Datalink, from January 2006 to December 2016. Models evaluated included published risk models (Framingham, ARIC, CHARGE-AF), machine learning models, which evaluated baseline and time-updated information (neural network, LASSO, random forests, support vector machines), and Cox regression. RESULTS: Analysis of 2,994,837 individuals (3.2% AF) identified time-varying neural networks as the optimal model achieving an AUROC of 0.827 vs. 0.725, with number needed to screen of 9 vs. 13 patients at 75% sensitivity, when compared with the best existing model CHARGE-AF. The optimal model confirmed known baseline risk factors (age, previous cardiovascular disease, antihypertensive medication usage) and identified additional time-varying predictors (proximity of cardiovascular events, body mass index (both levels and changes), pulse pressure, and the frequency of blood pressure measurements). CONCLUSION: The optimal time-varying machine learning model exhibited greater predictive performance than existing AF risk models and reflected known and new patient risk factors for AF.
Hill et al. (Fri,) conducted a cohort in Atrial fibrillation (n=2,994,837). Time-varying neural network model vs. CHARGE-AF risk model was evaluated on Area under the receiver operating characteristic curve (AUROC). A time-varying neural network model improved the prediction of atrial fibrillation compared to the CHARGE-AF risk model, achieving an AUROC of 0.827 versus 0.725.