DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction
This work addresses patient risk stratification for medical conditions using popular wearables, offering a new approach but with incremental method improvements.
The paper tackled cardiovascular risk prediction using wearable heart rate sensor data, achieving high accuracy for detecting conditions like diabetes (0.8451) and high blood pressure (0.8086) with a semi-supervised LSTM model.
We train and validate a semi-supervised, multi-task LSTM on 57,675 person-weeks of data from off-the-shelf wearable heart rate sensors, showing high accuracy at detecting multiple medical conditions, including diabetes (0.8451), high cholesterol (0.7441), high blood pressure (0.8086), and sleep apnea (0.8298). We compare two semi-supervised train- ing methods, semi-supervised sequence learning and heuristic pretraining, and show they outperform hand-engineered biomarkers from the medical literature. We believe our work suggests a new approach to patient risk stratification based on cardiovascular risk scores derived from popular wearables such as Fitbit, Apple Watch, or Android Wear.