# Electrocardiographic sex index: a continuous representation of sex

## TL;DR

This study introduces a continuous sex index from ECG data that better predicts health risks than binary sex classifications.

## Contribution

A novel continuous sex representation (ESI) derived from AI analysis of ECGs improves disease risk prediction.

## Key findings

- The ESI outperformed binary sex in predicting all-cause mortality, heart failure, and kidney failure.
- Lower ESI scores in males and higher scores in females correlated with greater clinical risk.
- The ESI and SDI demonstrated comparable or better accuracy than binary sex in risk prediction models.

## Abstract

Clinical risk calculators consider sex as a binary variable. However, sex is a complex trait with anatomic, physiologic, and metabolic attributes that are not easily summarized in this manner [1]. We propose a continuous representation of sex, the ECG Sex Index (ESI), derived via artificial intelligence analyses of electrocardiograms (ECG-AI).

We used an ECG repository at Wake Forest Baptist Health (Winston-Salem, NC) to develop a convolutional neural network-based ECG-AI model to detect sex from standard 12-lead ECGs. We utilized a rank-ordered transformation of the outcomes of ECG-AI to create the ESI. We also created a sex discordance index (SDI) from the ESI and assessed its utility in 1-year risk prediction for all-cause mortality, heart failure, and kidney failure.

The Wake Forest cohort included 3,573,844 ECGs and electronic health record data from 754,761 patients; 75% were White, 17% were Black, and 51% were female, with a mean age (SD) of 61 (17) years. The PhysioNet external validation cohort included 45,152 ECGs from 10,646 patients from two hospitals in China. The PhysioNet cohort was 100% Asian, 43.6% female, and had a mean age (SD) of 59 (20) years. ECG-AI provided a holdout area under the curve of 0.95 and an external validation area under the curve of 0.92. Lower ESI scores in males and higher ESI scores in females were associated with a greater risk for clinical outcomes. The ESI and SDI demonstrated comparable accuracy to binary sex in logistic regression analyses and outperformed binary sex in predicting clinical outcomes, highlighting their value as predictors in risk calculators for all-cause mortality, heart failure, and kidney failure.

The online version contains supplementary material available at 10.1186/s13293-025-00727-2.

An individual’s sex is typically classified as male or female at birth based on the presence of either a penis or a clitoris. However, there are many common features of male and female individuals at the metabolic and cellular levels. These commonalities are neglected in disease risk prediction models when an individual is labeled as male or female. This study proposes a novel, nonbinary representation of sex to be used in disease risk prediction models. Our novel nonbinary variable is derived via artificial intelligence applied to electrocardiographic data. It predicts all-cause mortality, heart failure, and kidney failure better than a binary sex variable.

The online version contains supplementary material available at 10.1186/s13293-025-00727-2.

We introduce an ECG-AI-driven continuous representation of sex, the ESI, which is a better predictor of cardiovascular and non-cardiovascular disease than binary sex.

The difference between an individual’s binary sex designation and their ESI value is associated with an increased risk for all-cause mortality, heart failure, and kidney failure.

A continuous representation of sex, the ESI, should be considered in risk prediction models for cardiovascular and renal outcomes, including mortality, heart failure, and kidney failure, where sex is hypothesized to be a relevant factor.

The online version contains supplementary material available at 10.1186/s13293-025-00727-2.