MultiD4CAD is a multimodal dataset of suspected Coronary Artery Disease (CAD) patients, comprising both imaging and clinical data. The imaging data obtained from cardiac CT includes epicardial (EAT) and pericoronary (PAT) adipose tissue segmentations. These metabolically active fat tissues play a key role in diagnosing various cardiovascular diseases. In addition, clinical data includes a set of biomarkers recognized as CAD risk factors. Specifically, the dataset includes 118 samples, divided into those without CAD patients (40) and those with CAD patients (78). The validated EAT and PAT segmentations make the dataset suitable for training predictive models based on radiomics and deep learning architectures. Moreover, challenges such as classification, segmentation, radiomic, and deep training tasks can be investigated and validated using the MultiD4CAD dataset. Here you can find the Data Use Agreement (DUA) to sign before using the dataset, together with the instructions to have access.