A Cardiac Deep Learning Model (CDLM) to Predict and Identify the Risk Factor of Congenital Heart Disease

Area of Science:

• Cardiology
• Medical Informatics
• Public Health

Background:

• Congenital heart disease (CHD) is a major cause of newborn mortality, disproportionately affecting low- and middle-income countries.
• Limited resources and healthcare access exacerbate CHD mortality rates in vulnerable populations.
• Machine learning offers a promising avenue for developing predictive models to assess CHD mortality risk.

Purpose of the Study:

• To propose an innovative machine learning approach to minimize newborn mortality associated with congenital heart disease.
• To develop a diagnostic model that identifies key risk factors for CHD mortality in newborns.
• To empower healthcare professionals with tools for customized interventions and early detection strategies.

Main Methods:

• Analysis of data from infants diagnosed with CHD, including maternal clinical history and fetal health information.
• Development and application of a Cardiac Deep Learning Model (CDLM) for risk prediction.
• Evaluation of the model's performance using metrics such as sensitivity, specificity, and predictive values.

Main Results:

• The proposed CDLM demonstrated high performance in predicting CHD mortality risk.
• Key performance metrics include: sensitivity of 91.74%, specificity of 92.65%, positive predictive value of 90.85%, and negative predictive value of 55.62%.
• The model achieved a miss rate of 91.03%, indicating its effectiveness in identifying at-risk infants.

Conclusions:

• The CDLM provides a powerful tool for healthcare professionals to combat CHD-related newborn mortality.
• Accurate risk prediction enables targeted interventions, including intensified care and early treatment.
• This research has the potential to significantly improve healthcare outcomes and save lives worldwide.