Key result
AI-enhanced mobile ECG achieves >0.98 ROC-AUC across most cardiovascular diagnostic categories.
Why the study?
Cardiovascular disease burden and clinician workloads are increasing while clinician numbers decline, creating a need for automated mobile systems to support cardiovascular health management.
Does an AI-enhanced mobile ECG hardware and cloud deep-learning system accurately detect 20 types of ECG abnormalities and reverse lead placement compared to cardiologist annotations?
Does an AI-enhanced mobile ECG hardware and cloud deep-learning system accurately detect 20 types of ECG abnormalities and reverse lead placement compared to cardiologist annotations?
Answers are grounded in this paper and cite their sources.
A lightweight portable single-lead ECG device paired with a cloud CNN-RNN deep learning service and WeChat Mini Program accurately classifies 20 ECG diagnostic categories (17 with ROC-AUC >0.98) and enables scalable out-of-hospital cardiovascular health management.
The number of patients with cardiovascular diseases is rapidly increasing in the world. The workload of existing clinicians is consequently increasing. However, the number of cardiovascular clinicians is declining. In this paper, we aim to design a mobile and automatic system to improve the abilities of patients' cardiovascular health management while also reducing clinicians' workload. Our system includes both hardware and cloud software devices based on recent advances in Internet of Things (IoT) and Artificial Intelligence (AI) technologies. A small hardware device was designed to collect high-quality Electrocardiogram (ECG) data from the human body. A novel deep-learning-based cloud service was developed and deployed to achieve automatic and accurate cardiovascular disease detection. Twenty types of diagnostic items including sinus rhythm, tachyarrhythmia, and bradyarrhythmia are supported. Experimental results show the effectiveness of our system. Our hardware device can guarantee high-quality ECG data by removing high-/low-frequency distortion and reverse lead detection with 0.9011 Area Under the Receiver Operating Characteristic Curve (ROC-AUC) score. Our deep-learning-based cloud service supports 20 types of diagnostic items, 17 of them have more than 0.98 ROC-AUC score. For a real world application, the system has been used by around 20,000 users in twenty provinces throughout China. As a consequence, using this service, we could achieve both active and passive health management through a lightweight mobile application on the WeChat Mini Program platform. We believe that it can have a broader impact on cardiovascular health management in the world.
No takes yet. Share an insight, caveat, or question.
Fu et al. (2021) studied Cardiovascular diseases and ECG abnormalities (including sinus rhythm, tachyarrhythmia, and bradyarrhythmia) (n=15,437). AI-enhanced mobile ECG hardware device and deep-learning-based cloud service (CNN-RNN hybrid model) vs. Ground-truth labels annotated and revised by at least two cardiologists was evaluated on Diagnostic classification performance (ROC-AUC) across 20 types of ECG diagnostic items on the hold-out test set. The AI-enhanced mobile ECG system achieved an ROC-AUC >0.98 for 17 of 20 cardiovascular diagnostic items and 0.9011 for reverse lead detection.
Synapse has enriched 10 related papers. Consider them for comparative context: