Related Experiment Video
Updated: Jun 5, 2025
Fetal Mouse Cardiovascular Imaging Using a High-frequency Ultrasound 30/45MHZ System
Published on: May 5, 2018
Prediction of cyanotic and acyanotic congenital heart disease using machine learning models
Sana Shahid1, Haris Khurram2,3, Apiradee Lim2
1Department of Statistics, Bahauddin Zakariya University, Multan 60000, Punjab, Pakistan.
Insights
An artificial neural network model effectively predicts congenital heart disease in children. Early identification of risk factors like maternal diet and family history is crucial for better outcomes.
Area of Science:
- Pediatric Cardiology
- Medical Informatics
- Public Health
Background:
- Congenital heart disease (CHD) is a significant cause of illness and mortality in neonates and children.
- Early identification and prediction of CHD are critical for improving pediatric health outcomes.
Purpose of the Study:
- To develop and identify the optimal predictive model for cyanotic and acyanotic congenital heart disease in children during pregnancy.
- To pinpoint potential risk factors associated with congenital heart disease.
Main Methods:
- A dataset of 3900 mothers and children diagnosed with CHD was analyzed.
- Multivariate outlier detection was employed.
- Various machine learning models were evaluated, with the best selected based on AUC, sensitivity, and specificity.
Main Results:
- Acyanotic CHD was more prevalent (69.5%) than cyanotic CHD (30.5%).
- Males exhibited higher rates of both acyanotic and cyanotic CHD.
- Maternal frequent fast-food consumption during pregnancy increased the odds of cyanotic CHD by 1.28 times.
Conclusions:
- Positive family history, male gender, and maternal diet are significant risk factors for CHD.
- The Artificial Neural Network (ANN) model demonstrated superior predictive performance (AUC=0.9012).
- This predictive model and findings can aid clinicians and public health officials in early diagnosis and management of pediatric CHD in Pakistan.
Background:
Congenital heart disease is most commonly seen in neonates and it is a major cause of pediatric illness and childhood morbidity and mortality.
Aim:
To identify and build the best predictive model for predicting cyanotic and acyanotic congenital heart disease in children during pregnancy and identify their potential risk factors.
Methods:
The data were collected from the Pediatric Cardiology Department at Chaudhry Pervaiz Elahi Institute of Cardiology Multan, Pakistan from December 2017 to October 2019. A sample of 3900 mothers whose children were diagnosed with cyanotic or acyanotic congenital heart disease was taken. Multivariate outlier detection methods were used to identify the potential outliers. Different machine learning models were compared, and the best-fitted model was selected using the area under the curve, sensitivity, and specificity of the models.
Results:
Out of 3900 patients included, about 69.5% had acyanotic and 30.5% had cyanotic congenital heart disease. Males had more cases of acyanotic (53.6%) and cyanotic (54.5%) congenital heart disease as compared to females. The odds of having cyanotic was 1.28 times higher for children whose mothers used more fast food frequently during pregnancy. The artificial neural network model was selected as the best predictive model with an area under the curve of 0.9012, sensitivity of 65.76%, and specificity of 97.23%.
Conclusion:
Children having a positive family history are at very high risk of having cyanotic and acyanotic congenital heart disease. Males are more at risk and their mothers need more care, good food, and physical activity during pregnancy. The best-fitted model for predicting cyanotic and acyanotic congenital heart disease is the artificial neural network. The results obtained and the best model identified will be useful for medical practitioners and public health scientists for an informed decision-making process about the earlier diagnosis and improve the health condition of children in Pakistan.
