# Deep neural networks can predict mortality from 12-lead electrocardiogram voltage data

arXiv: https://arxiv.org/abs/1904.07032 · HTML: https://mlsanity.com/paper/1904.07032/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2019.

## Built on by (most cited first, 21 of 21)

- [High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy with Cardiovascular Deep Learning](https://mlsanity.com/paper/2106.12511/) (2021)
- [Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery](https://mlsanity.com/paper/2305.17043/) (2023)
- [Unlocking the diagnostic potential of electrocardiograms through information transfer from cardiac magnetic resonance imaging](https://mlsanity.com/paper/2308.05764/) (2023)
- [Medical Imaging and Machine Learning](https://mlsanity.com/paper/2103.01938/) (2021)
- [Data Augmentation for Electrocardiograms](https://mlsanity.com/paper/2204.04360/) (2022)
- [Application of federated learning techniques for arrhythmia classification using 12-lead ECG signals](https://mlsanity.com/paper/2208.10993/) (2022)
- [Time Series Model Attribution Visualizations as Explanations](https://mlsanity.com/paper/2109.12935/) (2021)
- [Learning to Predict with Supporting Evidence: Applications to Clinical Risk Prediction](https://mlsanity.com/paper/2103.02768/) (2021)
- [Towards a Medical AI Scientist](https://mlsanity.com/paper/2603.28589/) (2026)
- [Defending Against Adversarial Attack in ECG Classification with Adversarial Distillation Training](https://mlsanity.com/paper/2203.09487/) (2022)
- [End-to-end Risk Prediction of Atrial Fibrillation from the 12-Lead ECG by Deep Neural Networks](https://mlsanity.com/paper/2309.16335/) (2023)
- [UniPACT: A Multimodal Framework for Prognostic Question Answering on Raw ECG and Structured EHR](https://mlsanity.com/paper/2601.17916/) (2026)
- [Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs](https://mlsanity.com/paper/2607.05013/) (2026)
- [Electrocardiographic Deep Learning for Predicting Post-Procedural Mortality](https://mlsanity.com/paper/2205.03242/) (2022)
- [ECG-Based Electrolyte Prediction: Evaluating Regression and Probabilistic Methods](https://mlsanity.com/paper/2212.13890/) (2022)
- [Predicting the Travel Distance of Patients to Access Healthcare using Deep Neural Networks](https://mlsanity.com/paper/2112.03541/) (2021)
- [FG-SSA: Features Gradient-based Signals Selection Algorithm of Linear Complexity for Convolutional Neural Networks](https://mlsanity.com/paper/2302.12711/) (2023)
- [Deep Survival Analysis from Adult and Pediatric Electrocardiograms: A Multi-center Benchmark Study](https://mlsanity.com/paper/2406.17002/) (2024)
- [Imaging-anchored multiomics in cardiovascular disease: integrating cardiac imaging, bulk, single-cell, and spatial transcriptomics](https://mlsanity.com/paper/2601.07871/) (2026)
- [In-Hospital Stroke Risk-State Classification from PPG-Derived Hemodynamic Features](https://mlsanity.com/paper/2602.09328/) (2026)
- [Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis](https://mlsanity.com/paper/2610.13510/) (2026)

## Abstract (arXiv)

The electrocardiogram (ECG) is a widely-used medical test, typically consisting of 12 voltage versus time traces collected from surface recordings over the heart. Here we hypothesize that a deep neural network can predict an important future clinical event (one-year all-cause mortality) from ECG voltage-time traces. We show good performance for predicting one-year mortality with an average AUC of 0.85 from a model cross-validated on 1,775,926 12-lead resting ECGs, that were collected over a 34-year period in a large regional health system. Even within the large subset of ECGs interpreted as 'normal' by a physician (n=297,548), the model performance to predict one-year mortality remained high (AUC=0.84), and Cox Proportional Hazard model revealed a hazard ratio of 6.6 (p<0.005) for the two predicted groups (dead vs alive one year after ECG) over a 30-year follow-up period. A blinded survey of three cardiologists suggested that the patterns captured by the model were generally not visually apparent to cardiologists even after being shown 240 paired examples of labeled true positives (dead) and true negatives (alive). In summary, deep learning can add significant prognostic information to the interpretation of 12-lead resting ECGs, even in cases that are interpreted as 'normal' by physicians.