F. Javed, P.A. Venkatachalam, and A.F.M. Hani (Malaysia)
Expert System, Auscultation, Heart Murmurs, Digital Signal Processing, Artificial Neural Networks
Auscultation is a non-invasive, low cost screening method and has a high potential of providing valuable information about the conditions of the heart and its valves but it is highly subjective and depends on the skills and experience of the listener. In order to address the limitations of auscultation, we have combined a knowledge based system with digital signal processing algorithms for heart sound analysis and developed a Signal Processing Module integrated Expert System (SIPMES).The system uses digitized heart sounds and has the capability to diagnose the condition of heart. The knowledge base in SIPMES uses five data categories: patient’s personal and past medical history, clinical examination, auscultation, echocardiogram and chest x ray. SIPMES can support the general physician in making more accurate and reliable diagnosis at early stages. To test the validity of the system it has been tested by abnormal heart sound samples and medical data from 40 patients. The diagnosis made by the system has been counter checked by few senior cardiologists and a coincidence factor of 74% has been achieved.
Important Links:
Go Back
