Research map / Label-efficient and robust learning / Semi-supervised learning
DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace hand-engineered biomarkers with the supervised LSTM | DeepHeart · Diabetes | c-statistic: 0.7906 -> 0.8451 | Helped |
| Replace hand-engineered biomarkers with the supervised LSTM | DeepHeart · High Cholesterol | c-statistic: 0.5996 -> 0.6736 | Helped |
| Replace hand-engineered biomarkers with the supervised LSTM | DeepHeart · Sleep Apnea | c-statistic: 0.6583 -> 0.8041 | Helped |
| Replace hand-engineered biomarkers with the supervised LSTM | DeepHeart · High Blood Pressure | c-statistic: 0.7195 -> 0.7991 | Helped |
| Add heuristic heart-rate-variability pretraining | LSTM · High Cholesterol | c-statistic: 0.6736 -> 0.7148 | Helped |
| Add heuristic heart-rate-variability pretraining | LSTM · High Blood Pressure | c-statistic: 0.7991 -> 0.7427 | Hurt |
| Add heuristic heart-rate-variability pretraining | LSTM · Diabetes | c-statistic: 0.8451 -> 0.8366 | No clear effect |
| Add heuristic heart-rate-variability pretraining | LSTM · Sleep Apnea | c-statistic: 0.8041 -> 0.7951 | No clear effect |
| Add sequence-autoencoder pretraining | LSTM · High Cholesterol | c-statistic: 0.6736 -> 0.7441 | Helped |
| Add sequence-autoencoder pretraining | LSTM · Sleep Apnea | c-statistic: 0.8041 -> 0.8298 | Helped |
| Add sequence-autoencoder pretraining | LSTM · High Blood Pressure | c-statistic: 0.7991 -> 0.8086 | Helped |
| Add sequence-autoencoder pretraining | LSTM · Diabetes | c-statistic: 0.8451 -> 0.7998 | Hurt |
Closest papers by meaning
- Large-scale Training of Foundation Models for Wearable Biosignals (ICLR 2024 · similarity 0.87)
- OpenMHC: Accelerating the Science of Wearable Foundation Models (NeurIPS 2026 · similarity 0.85)
- Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions (ICML 2025 · similarity 0.82)
- Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model (ICLR 2025 · similarity 0.82)
- Scaling Wearable Foundation Models (ICLR 2025 · similarity 0.82)
- From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining (ICML 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.