Key result
Protocol outlines planned deep learning models to predict new-onset AF using primary care data.
Why the study?
Previous AF prediction models were limited by data sources and methodologies, leaving a need for an accurate model using routine healthcare data to identify patient-level risk before stroke occurs.
Can deep learning techniques applied to routinely collected primary care data accurately predict the risk of new-onset atrial fibrillation compared to traditional methods?
Can deep learning techniques applied to routinely collected primary care data accurately predict the risk of new-onset atrial fibrillation compared to traditional methods?
This protocol outlines the development of a deep learning-based prediction model for new-onset atrial fibrillation using routinely collected primary care data.
Protocol does not yet inform practice; leaves open whether deep learning improves new-onset AF prediction from primary care data.
INTRODUCTION: Atrial fibrillation (AF) is a major cardiovascular health problem: it is common, chronic and incurs substantial healthcare expenditure because of stroke. Oral anticoagulation reduces the risk of thromboembolic stroke in those at higher risk; but for a number of patients, stroke is the first manifestation of undetected AF. There is a rationale for the early diagnosis of AF, before the first complication occurs, but population-based screening is not recommended. Previous prediction models have been limited by their data sources and methodologies. An accurate model that uses existing routinely collected data is needed to inform clinicians of patient-level risk of AF, inform national screening policy and highlight predictors that may be amenable to primary prevention. METHODS AND ANALYSIS: We will investigate the application of a range of deep learning techniques, including an adapted convolutional neural network, recurrent neural network and Transformer, on routinely collected primary care data to create a personalised model predicting the risk of new-onset AF over a range of time periods. The Clinical Practice Research Datalink (CPRD)-GOLD dataset will be used for derivation, and the CPRD-AURUM dataset will be used for external geographical validation. Both comprise a sizeable representative population and are linked at patient-level to secondary care databases. The performance of the deep learning models will be compared against classic machine learning and traditional statistical predictive modelling methods. We will only use risk factors accessible in primary care and endow the model with the ability to update risk prediction as it is presented with new data, to make the model more useful in clinical practice. ETHICS AND DISSEMINATION: Permissions for CPRD-GOLD and CPRD-AURUM datasets were obtained from CPRD (ref no: 19_076). The CPRD ethical approval committee approved the study. The results will be submitted as a research paper for publication to a peer-reviewed journal and presented at peer-reviewed conferences. TRIAL REGISTRATION DETAILS: A systematic review to incorporate within the overall project was registered on PROSPERO (registration number CRD42021245093). The study was registered on ClinicalTrials.gov (NCT04657900).
No takes yet. Share an insight, caveat, or question.
Nadarajah et al. (2021) studied Atrial fibrillation. Deep learning techniques (convolutional neural network, recurrent neural network, Transformer) vs. Classic machine learning and traditional statistical predictive modelling methods was evaluated on Risk of new-onset atrial fibrillation over a range of time periods. This study protocol outlines the planned development and validation of deep learning models using primary care data to predict new-onset atrial fibrillation, with no results available yet.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: