Heart disease remains a leading global cause of mortality, with the alarming statistic that approximately one individual succumbs to a heart attack every minute. In our contemporary society, this issue has evolved into a pressing concern, demanding immediate attention. The early detection of heart disease presents a formidable challenge, but modern technology offers a promising solution. Machine learning, when applied to healthcare, emerges as a powerful technique capable of providing timely and precise predictions regarding the onset of heart disease. This application holds the potential to significantly impact the landscape of heart disease diagnosis, allowing for swifter and more accurate interventions. This dataset consists of many attributes like age, sex, and resting BP with samples Wi-fi module ESP 8266 is interfaced with IOT for transfer the patient data to doctor. Arduino Uno is involved as IOT to connect with BP sensor and ECG sensor to measure BP and pulse level of patient. The incorporation of a 3D Convolutional Neural Network (CNN) helps in enhancing both the accuracy and overall performance of the model. As part of this process, the back-propagation algorithm diligently computes the gradient of the error function, facilitating the iterative adjustment of neuron weights. In our dataset, the utilization of a tenfold cross-validation technique proves to be adequately effective in addressing model complexity and ensuring robust results. The key objective for the model to be proposed is to attain a high level of accuracy and performance, while also offering flexibility and a high probability of success.