Overview / Usage

The electrocardiogram (ECG) is a commonly used medical technique for diagnosing heart issues. Analyzing ECG signals can assist in identifying abnormal heart abnormalities, which is helpful for prompt patient diagnosis and treatment. In this current study, we suggest a machine learning-based method for interpreting ECG signals that uses the the PQRS complexities to differentiate between normal and pathological signals. The suggested method analyses the ECG signals and data extracted from them using machine learning methodologies built on Python. The signals are then divided into groups of normal and abnormal signals, along with categories for the different types of abnormality, using the characteristics.

In order for the medical staff to access the patient's data during their monthly or yearly check-ups, the data collected from the patients will be saved in the dev cloud. For the early identification of cardiac problems, the method offers a non-invasive and economical treatment. To provide a more complete solution for the detection and treatment of cardiac problems, the suggested method may also be combined with other medical tools and systems. Overall, the suggested strategy holds promise for enhancing the healthcare sector by offering a precise and dependable way for the diagnosis of cardiac problems.

Methodology / Approach

The ECG signals are classified using ANN model then we got a result of normal and abnormal. Using those results the reason for the abnormalities are identified and store in the cloud based system.

Repository

https://github.com/vishnukarikalan07/ECG-CLASSIFICATION-INTELONE