Emergence of Artificial Intelligence in numerous domains is driven by the need for automation, efficiency, and innovation. The rapid advancement of computing technology has made it possible to process large amounts of data in real-time, enabling Artificial Intelligence (AI) applications to scale especially in medical domain. By ensuring earlier and more accurate diagnoses, individualized treatment plans can be figured out. Thus, the advanced modeling for automatic disease identification has the potential to enhance the patients. One of the very important areas in medicine where AI can do wonders is Fetal Cardiac Anomaly (FCA) diagnosis because even in the technological era the diagnosis rate for the most developed countries is around 50%. Compared to other anomalies, FCAs are often more complex and have a greater impact on fetal development, making early diagnosis and management especially important. This research is focusing on framing machine learning algorithms for diagnosing FCA. The feature used here is Local binary pattern (LBP) and the classification algorithms are implemented using LBP. The performance of algorithms and the best classifier are determined for detecting FCA is reported.