Related Experiment Video
Updated: Dec 10, 2025
Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training
Published on: February 10, 2022
Improving preoperative risk-of-death prediction in surgery congenital heart defects using artificial intelligence
João Chang Junior1,2,3, Fábio Binuesa1, Luiz Fernando Caneo1
1Department of Cardiovascular Surgery-Pediatric Cardiac Unit, Heart Institute of University of São Paulo Medical School-HCFMUSP-InCor, São Paulo, Brazil.
Insights
Researchers developed a predictive model to estimate the risk of mortality in congenital heart disease (CHD) patients undergoing surgery. The Random Forest model accurately identified key predictors for preoperative mortality risk.
Area of Science:
- Cardiology
- Medical Informatics
- Artificial Intelligence in Medicine
Background:
- Congenital heart disease (CHD) is a leading cause of congenital anomalies, significantly impacting pediatric and adult morbidity and mortality.
- Limited research exists on predicting pre-surgical mortality risk in CHD patients.
- Accurate risk stratification is crucial for optimizing patient management and resource allocation.
Purpose of the Study:
- To develop and validate a predictive model for individual mortality risk in congenital heart disease patients undergoing cardiac surgery.
- To create a tool that is adapted to regional realities and applicable in clinical practice.
- To enhance preoperative risk assessment for improved patient outcomes.
Main Methods:
- Utilized data from 2,240 consecutive congenital heart disease patients undergoing surgery at InCor.
- Developed and validated a preoperative risk-of-death prediction model using six artificial intelligence algorithms, including Random Forest (RF).
- Evaluated model performance using metrics such as the area under the curve (AUC).
Main Results:
- The Random Forest model achieved the highest performance with an AUC of 0.902.
- Key predictors of mortality included prior ICU admission, diagnostic group, patient height, hypoplastic left heart syndrome, body mass, oxygen saturation, and pulmonary atresia.
- These predictors accounted for 67.8% of the mortality risk in the RF model.
Conclusions:
- Specific patient characteristics like height, BMI, oxygen saturation, and prior hospitalizations significantly influence in-hospital mortality.
- The developed model and associated web application (CgntSCORE) provide a valuable tool for researchers and clinicians to predict mortality risk.
- Findings align with international literature regarding high-risk diagnostic groups for fatal outcomes.
Background:
Congenital heart disease accounts for almost a third of all major congenital anomalies. Congenital heart defects have a significant impact on morbidity, mortality and health costs for children and adults. Research regarding the risk of pre-surgical mortality is scarce.
Objectives:
Our goal is to generate a predictive model calculator adapted to the regional reality focused on individual mortality prediction among patients with congenital heart disease undergoing cardiac surgery.
Methods:
Two thousand two hundred forty CHD consecutive patients' data from InCor's heart surgery program was used to develop and validate the preoperative risk-of-death prediction model of congenital patients undergoing heart surgery. There were six artificial intelligence models most cited in medical references used in this study: Multilayer Perceptron (MLP), Random Forest (RF), Extra Trees (ET), Stochastic Gradient Boosting (SGB), Ada Boost Classification (ABC) and Bag Decision Trees (BDT).
Results:
The top performing areas under the curve were achieved using Random Forest (0.902). Most influential predictors included previous admission to ICU, diagnostic group, patient's height, hypoplastic left heart syndrome, body mass, arterial oxygen saturation, and pulmonary atresia. These combined predictor variables represent 67.8% of importance for the risk of mortality in the Random Forest algorithm.
Conclusions:
The representativeness of "hospital death" is greater in patients up to 66 cm in height and body mass index below 13.0 for InCor's patients. The proportion of "hospital death" declines with the increased arterial oxygen saturation index. Patients with prior hospitalization before surgery had higher "hospital death" rates than who did not required such intervention. The diagnoses groups having the higher fatal outcomes probability are aligned with the international literature. A web application is presented where researchers and providers can calculate predicted mortality based on the CgntSCORE on any web browser or smartphone.
