Related Experiment Video
Updated: Oct 5, 2025
Fetal Mouse Cardiovascular Imaging Using a High-frequency Ultrasound 30/45MHZ System
Published on: May 5, 2018
Using Innovative Machine Learning Methods to Screen and Identify Predictors of Congenital Heart Diseases
Yanji Qu1, Xinlei Deng2, Shao Lin2
1Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China.
Insights
Machine learning models can predict congenital heart diseases (CHDs) using maternal clinical data. Elevated uric acid, glucose, and altered coagulation levels are key predictors, enabling earlier screening and prevention strategies for CHDs.
Area of Science:
- Cardiology
- Genetics
- Medical Informatics
Background:
- Congenital heart diseases (CHDs) represent a significant global health burden, being the most common birth defects.
- Previous research identified genetic and environmental factors for CHDs, but high-volume clinical indicators were underutilized for prediction.
- Predicting CHDs necessitates integrating diverse data, including clinical laboratory results and patient-reported information.
Purpose of the Study:
- To develop and validate a machine learning model for predicting CHDs.
- To identify key clinical laboratory predictors for CHDs.
- To establish novel predictive thresholds for early CHD screening and prevention.
Main Methods:
- A birth cohort study involving 5,390 mother-child pairs was conducted at a major cardiac center in China (2011-2017).
- An Explainable Boosting Machine (EBM) model was employed, utilizing 1,127 potential predictors from questionnaires and clinical laboratory data.
- Model performance was assessed using the area under the ROC curve (AUC), with top predictors and their thresholds identified.
Main Results:
- The prediction model achieved an AUC of 76%, with 34 out of the top 35 predictors being clinical laboratory tests.
- Maternal serum uric acid (UA), glucose, and coagulation levels were identified as the most significant predictors.
- Specific thresholds (e.g., UA >4.38 mg/dl, shortened activated partial thromboplastin time <33.33 s) indicated elevated CHDs risk (1.17-1.54 relative risk).
Conclusions:
- Maternal uric acid, glucose, and coagulation levels are highly consistent and significant predictors of CHDs.
- Thresholds for these markers, even below current clinical abnormality definitions, can aid in developing effective CHD screening and prevention strategies.
- An online predictive tool was developed to assist in CHD screening and prevention efforts.
Abstract:
Objective: Congenital heart diseases (CHDs) are associated with an extremely heavy global disease burden as the most common category of birth defects. Genetic and environmental factors have been identified as risk factors of CHDs previously. However, high volume clinical indicators have never been considered when predicting CHDs. This study aimed to predict the occurrence of CHDs by considering thousands of variables from self-reported questionnaires and routinely collected clinical laboratory data using machine learning algorithms. Methods: We conducted a birth cohort study at one of the largest cardiac centers in China from 2011 to 2017. All fetuses were screened for CHDs using ultrasound and cases were confirmed by at least two pediatric cardiologists using echocardiogram. A total of 1,127 potential predictors were included to predict CHDs. We used the Explainable Boosting Machine (EBM) for prediction and evaluated the model performance using area under the Receive Operating Characteristics (ROC) curves (AUC). The top predictors were selected according to their contributions and predictive values. Thresholds were calculated for the most significant predictors. Results: Overall, 5,390 mother-child pairs were recruited. Our prediction model achieved an AUC of 76% (69-83%) from out-of-sample predictions. Among the top 35 predictors of CHDs we identified, 34 were from clinical laboratory tests and only one was from the questionnaire (abortion history). Total accuracy, sensitivity, and specificity were 0.65, 0.74, and 0.65, respectively. Maternal serum uric acid (UA), glucose, and coagulation levels were the most consistent and significant predictors of CHDs. According to the thresholds of the predictors identified in our study, which did not reach the current clinical diagnosis criteria, elevated UA (>4.38 mg/dl), shortened activated partial thromboplastin time (<33.33 s), and elevated glucose levels were the most important predictors and were associated with ranges of 1.17-1.54 relative risks of CHDs. We have developed an online predictive tool for CHDs based on our findings that may help screening and prevention of CHDs. Conclusions: Maternal UA, glucose, and coagulation levels were the most consistent and significant predictors of CHDs. Thresholds below the current clinical definition of "abnormal" for these predictors could be used to help develop CHD screening and prevention strategies.
