Deepr: A Convolutional Net for Medical Records
This addresses the bottleneck of feature engineering for healthcare professionals and researchers in predicting patient outcomes from medical records, though it is incremental as it builds on existing deep learning methods.
The paper tackled the problem of feature engineering for predictive systems from electronic medical records by introducing Deepr, an end-to-end deep learning system that automatically extracts features and predicts future risk, achieving superior accuracy in predicting unplanned readmission after discharge compared to traditional techniques.
Feature engineering remains a major bottleneck when creating predictive systems from electronic medical records. At present, an important missing element is detecting predictive regular clinical motifs from irregular episodic records. We present Deepr (short for Deep record), a new end-to-end deep learning system that learns to extract features from medical records and predicts future risk automatically. Deepr transforms a record into a sequence of discrete elements separated by coded time gaps and hospital transfers. On top of the sequence is a convolutional neural net that detects and combines predictive local clinical motifs to stratify the risk. Deepr permits transparent inspection and visualization of its inner working. We validate Deepr on hospital data to predict unplanned readmission after discharge. Deepr achieves superior accuracy compared to traditional techniques, detects meaningful clinical motifs, and uncovers the underlying structure of the disease and intervention space.