# Machine learning prediction of ARDS after heart valve surgery: development and validation in Northwest China

## TL;DR

This study develops an AI model to predict ARDS after heart valve surgery, using patient data from Northwest China to identify high-risk individuals early.

## Contribution

A novel machine learning model using six clinical predictors to accurately forecast ARDS risk after heart valve surgery.

## Key findings

- XGBoost model achieved an AUC of 0.853 in predicting ARDS after heart valve surgery.
- Key predictors include age, monocyte count, and intraoperative blood loss.
- The model provides a reliable tool for early risk stratification in high-risk patients.

## Abstract

To develop an AI-based predictive model for acute respiratory distress syndrome (ARDS) following cardiopulmonary bypass (CPB)-assisted heart valve replacement (HVR) to enable early identification of high-risk patients.

We retrospectively analyzed 400 patients who underwent CPB-assisted HVR between January 2023 and February 2025. After data preprocessing and feature selection, the dataset was split into training (n = 280) and test (n = 120) sets. Multiple machine learning models were developed and optimized, with XGBoost emerging as the optimal model based on training performance.

Among 400 patients, 56 (14%) developed ARDS postoperatively. Key predictors included Age, absolute monocyte count,right atrial transverse diameter, intraoperative blood loss, platelet count, main pulmonary artery diameter. The XGBoost model achieved excellent performance with an AUC of 0.853 and demonstrated good calibration (HL test p > 0.05).

The XGBoost model accurately predicts ARDS risk following CPB-assisted HVR using six clinically relevant predictors, providing a valuable tool for early risk stratification and potential intervention in high-risk patients.