Novel techniques for congestive heart failure detection / Alia Shawky Abd El Hamid Mohamed Khaled ; Suppervised Abdalla Saeed Ahmed Mohamed , Mohamed Ibrahim Owis

Thesis (M.Sc.) - Cairo University - Faculty Of Engineering - Department Of Biomedical Engineering

The heart is responsible for pumping blood to all the organs in the bodyBlood is pumped through the four chambers of the heart and four valves control the one - way flow of blood through the heartChanges in pressure as the heart contracts make the valves open and close , and cause the blood to flowThe role of the circulation mechanism is to deliver oxygen and essential metabolites to the tissues of the body and eliminate waste products and carbon dioxide Congestive heart failure is a common and serious medical condition where the heart is not able to pump enough blood to meet the body's energy demandsHeart failure typically develops slowly after injury to the heart , such as a heart attack , too much strain on the heart due to years of untreated high blood pressure or a diseased heart valveAs the heart muscle weakens , it needs to pump harder to keep blood flowing to the bodyHeart failure is not always apparentSome people in the very early stages of heart failure may have no symptoms at allOthers dismiss getting tired and being short of breath as simply signs of growing olderBut some symptoms are more obviousWhen the heart is not pumping properly or efficiently , daily activity can cause shortness of breath or difficulty in breathing when lying downThe legs and ankles may swell because too much water is retained in the bodyFeeling weak and tired is commonOrdinary daily activities become exhausting In this thesis , we consider the problem of detection of congestive heart failure using heart rate variability analysis techniques , which depends on the variations between consecutive heartbeatsThe problem is divided into three steps : preprocessing , feature extraction and classificationIn the preprocessing stage , the HRV raw signals are to be interpolated and detrendedTo extract the features in the second stage , heart rate variability analysis methods such as time - domain analysis , frequency - domain analysis (non - parametric and parametric methods) , time - frequency analysis (discrete wavelets transform (DWT)) , and nonlinear method (Poincaré Plot) are usedFor classification , three statistical classifiers are used : minimum distance classifier , k - nearest neighbor

Issued also as CD