Method and system of detecting arrhythmia using photoplethysmogram signal

A system of detecting arrhythmia using photoplethysmogram (PPG) signals;

• said system comprising:
• an image capturing device (202) coupled with a mobile communication device (204), adapted for extracting photoplethysmogram signals from a patient;
• a feature extraction module (206) adapted for extracting cardiac parameter from the extracted photoplethysmogram (PPG) signals), wherein the extracted cardiac parameter is heart rate;
• an abnormality detection module (208) adapted for identifying presence of cardiac abnormalities as reinforcement filtering of detecting premature ventricular contraction and ventricular flutter from the extracted cardiac parameters;
• a closeness criteria evaluation module (210) adapted for analysing the extracted cardiac parameters to investigate statistical trend and to perform statistical closeness approximation of the extracted photoplethysmogram (PPG) signals;
• a decision module (212) adapted for predicting and subsequently classifying type of arrhythmia,
• wherein the analysing, predicting and subsequently classifying type of arrhythmia based on the extracted cardiac parameters comprises:
• finding train of heart rates at each cardiac cycle for given PPG signal;
• finding feature vector from mean heart rate values;
• finding the classification outcome set from the heart rate values using binary classifier k-means clustering technique;
• and
• deciding the type of arrhythmia based on the classification.

A non-transitory computer readable medium storing instructions which when executed by a possessor on a system, cause the processor to perform method for detecting arrhythmia using photoplethysmogram (PPG) signals comprising:

• extracting photoplethysmogram (PPG) signals by a mobile communication device from an image capturing device (202) coupled with the mobile communication device (204);
• extracting cardiac parameter from the extracted photoplethysmogram (PPG) signals using a feature extraction module (206)), wherein the extracted cardiac parameter is heart rate;
• identifying presence of cardiac abnormalities as reinforcement filtering of detecting premature ventricular contraction and ventricular flutter from the extracted cardiac parameters using an abnormality detection module (208);
• analysing the extracted cardiac parameters to investigate statistical trend and to perform statistical closeness approximation of the extracted photoplethysmogram (PPG) signals using a closeness criteria evaluation module (210);
• and
• predicting and subsequently classifying type of arrhythmia using a decision module (212),
• wherein the analysing, predicting and subsequently classifying type of arrhythmia based on the extracted cardiac parameters comprises:
• finding train of heart rates at each cardiac cycle for given PPG signal;
• finding feature vector from mean heart rate values;
• finding the classification outcome set from the heart rate values using binary classifier k-means clustering technique;
• and
• deciding the type of arrhythmia based on the classification.