BEHRT: Transformer for Electronic Health Records
This work addresses the need for early disease indication and detection in precision healthcare, offering potential benefits for patients, carers, and healthcare resource allocation, though it appears incremental as it builds on existing deep EHR models with a novel architecture.
The paper tackles the problem of early disease detection from electronic health records by introducing BEHRT, a transformer-based model that achieves an absolute improvement of 8.0-10.8% in Average Precision Score over existing state-of-the-art methods when predicting the onset of 301 conditions using data from nearly 1.6 million individuals.
Today, despite decades of developments in medicine and the growing interest in precision healthcare, vast majority of diagnoses happen once patients begin to show noticeable signs of illness. Early indication and detection of diseases, however, can provide patients and carers with the chance of early intervention, better disease management, and efficient allocation of healthcare resources. The latest developments in machine learning (more specifically, deep learning) provides a great opportunity to address this unmet need. In this study, we introduce BEHRT: A deep neural sequence transduction model for EHR (electronic health records), capable of multitask prediction and disease trajectory mapping. When trained and evaluated on the data from nearly 1.6 million individuals, BEHRT shows a striking absolute improvement of 8.0-10.8%, in terms of Average Precision Score, compared to the existing state-of-the-art deep EHR models (in terms of average precision, when predicting for the onset of 301 conditions). In addition to its superior prediction power, BEHRT provides a personalised view of disease trajectories through its attention mechanism; its flexible architecture enables it to incorporate multiple heterogeneous concepts (e.g., diagnosis, medication, measurements, and more) to improve the accuracy of its predictions; and its (pre-)training results in disease and patient representations that can help us get a step closer to interpretable predictions.