Cardiovascular disease (CVD) is the leading cause of death. The transition in cardiovascular disease threatens the economies of the less developed world. An electrocardiogram (ECG) machine is a device that checks the patient's heart rhythm and electrical activity. ECG signals give crucial information about the heart and numerous cardiac problems, such as coronary artery disease, myocardial infarction, and hypertension, which can be detected with an ECG report. The success rate for cardiac disease diagnosis will rise if ECG signals can be adequately recognized and interpreted. Classic signal processing and machine learning algorithms are utilized to evaluate the ECG signal and detect distinct types of arrhythmia for early treatment and prevention of cardiovascular diseases. To provide a sustainable solution for developing countries, we need to make an accurate diagnosis device that is portable and low-cost. This research aims to create a new low-cost ECG device and interface patients with HealthyPi v3 which is a miniature raspberry pibased vital sign monitor to record raw ECG signals. We proposed an integrated environment with classical ECG acquisition and classification techniques to obtain the preferable outcome. Also, we allowed us to assimilate with a mobile remote monitoring system to create a dynamic healthcare monitoring environment for the patients. This work implies the acquisition of real-time ECG data via HealthyPi V3 integrated with peripheral capillary oxygen saturation (SpO2) sensor and temperature sensor. The software is designed to read and analyze the hardware system-driven realtime ECG data, heart rate, blood pressure, respiratory rate, and temperature. To categorize the QRS complex of ECG data obtained and analyzed by the hardware-software system for heart disease prediction, Support Vector Machine (SVM) classifier, Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) is applied where CNN has achieved the highest accuracy while processing the signal.