Computed Tomography Artificial Intelligence Detection for Atherosclerosis (CTAID-A) model, is a product introduced to classify atherosclerotic plaque quantitatively as the main cause of human mortality attributed to heart disease or atherosclerosis. However, the Coronary Computed Tomography Angiography (CCTA) screening tools for detecting the disease is still subjectively diagnosed by experts. As a result, inaccuracies and variations in reports can occur. Hence, it is a novelty validation approach that simulates and classify the radiomics features from CCTA images to classify atherosclerosis disease quantitatively accordingly to the characteristic of its plaque such as calcified, non-calcified, and mixed plaque. The algorithm supports the classification and validation of the radiomic features from various hospitals in Malaysia. Since early detection of atherosclerosis using non-invasive modalities such as CCTA is essential, adaptation of this artificial intelligence component is prominent for research, evaluation, and modeling to keep our health as the top priority. This validation framework is suited to CCTA image classification in hospitals and real-world applications. With the accuracy of above 0.9 comparable with other researcher in the world. We hoped that this model can be deploy into autodetection software that will give impact to the nation and support our sustainable development goal.