Cardiovascular disease is a leading cause of death worldwide, accounting for 32% of global deaths in 2019, a majority of which can first present themselves with similar symptoms to pulmonary pathologies. Unlike the modern diagnostic tools such as electrocardiogram (ECG), computed tomography (CT) or X-ray; auscultation is not only risk-free but also requires much simpler equipment, all the while retaining the potential to provide just as much insight into the patient’s condition as its competitors, especially when coupled with data processing. In addition to signal processing methods, machine learning and deep learning algorithms like decision tree, support vector machine or convolution neural network (CNN) were applied to an audio dataset recorded through the chest of patients, labeled with the abnormal sound type and the disease the patient was afflicted with, in order to diagnose the patient as healthy or potentially having problems in either their lungs or their heart. An electrical stethoscope is also developed using simple microelectronics to collect the audio from the patient's chest. The highest result was achieved with a CNN model classifying the abnormal sound type (up to 85.00%) then a decision tree algorithm predicting the health status of the patient (up to 88.24%). It showed a limited correlation between wheezing sound and lung disease, which corresponded to a high accuracy for the lung and healthy labels. Due to the use of deep learning methods for classifying the adventitious sound, the explainability for the sound type model is still low. A better understanding of the relationship between the disease, physical change, sound generation mechanics and its manifestation on the audio signal is required to better explain this model. The electrical stethoscope was operational and able to collect audio with low noise interference; however, more hardware-based processing is needed to compete with commercially available products.