Estimating ECG Intervals from Lead-I Alone: External Validation of Supervised Models

TL;DR

This study develops and validates deep learning models to accurately estimate key ECG intervals from lead-I ECGs, enabling out-of-hospital cardiovascular monitoring with high accuracy across multiple datasets.

Contribution

The paper introduces novel deep learning models capable of estimating ECG intervals from lead-I alone, validated on large external datasets without retraining.

Findings

Achieved MAE of 6.3 ms for QRS, 11.9 ms for QT, and 9.2 ms for PR intervals.

Models successfully identify presence of P-waves in ECGs with atrial fibrillation.

Outperformed existing baseline algorithms in external validations.

Abstract

The diagnosis, prognosis, and treatment of a number of cardiovascular disorders rely on ECG interval measurements, including the PR, QRS, and QT intervals. These quantities are measured from the 12-lead ECG, either manually or using automated algorithms, which are readily available in clinical settings. A number of wearable devices, however, can acquire the lead-I ECG in an outpatient setting, thereby raising the potential for out-of-hospital monitoring for disorders that involve clinically significant changes in ECG intervals. In this work, we therefore developed a series of deep learning models for estimating the PR, QRS, and QT intervals using lead-I ECG. From a corpus of 4.2 million ECGs from patients at the Massachusetts General Hospital, we train and validate each of the models. At internal holdout validation, we achieve mean absolute errors (MAE) of 6.3 ms for QRS durations and 11.9 ms for QT intervals, and an MAE of 9.2 ms for estimating PR intervals. Moreover, as a well-defined P-wave does not always exist in ECG tracings - for example, when there is atrial fibrillation - we trained a model that can identify when there is a P-wave, and consequently, a measurable PR interval. We validate our models on three large external healthcare datasets without any finetuning or retraining - 3.2 million ECG from the Brigham and Womens Hospital, 668 thousand from MIMIC-IV, and 20 thousand from PTB-XL - and achieve similar performance. Also, our models significantly outperform two publicly available baseline algorithms. This work demonstrates that ECG intervals can be tracked from only lead-I ECG using deep learning, and highlights the potential for out-of-hospital applications.