This paper presents the algorithm and technical aspects of an intelligent diagnostic system for the detection of heart murmurs. The purpose of this research is to address the lack of effectively accurate cardiac auscultation present at the primary care physician office by development of an algorithm capable of operating within the hectic environment of the primary care office. The proposed algorithm consists of three main stages. First; denoising of input data (digital recordings of heart sounds), via Wavelet Packet Analysis. Second; input vector preparation through the use of Principal Component Analysis and block processing. Third; classification of the heart sound using an Artificial Neural Network. Initial testing revealed the intelligent diagnostic system can differentiate between normal healthy heart sounds and abnormal heart sounds (e.g., murmurs), with a specificity of 70.5% and a sensitivity of 64.7%.

The control of depth of anesthesia presents a challenging and realistic problem that calls for fast and adaptable control techniques. However, patient-to-patient variability in model parameters poses the question of which control strategy can generate best results. In this paper, we studied three different patient models, i.e., the slate model, the isoflurane unconsciousness model, and the isoflurane to muscle relaxation interaction model. Due to the simplicity of the PID control and easy implementation, a discrete PID controller with actuator saturation is considered in this study to supports these three pharmacokinetic models. The models being tested can give us an understanding of the effects of disposition of drug in the body by measuring the Mean Arterial Pressure (MAP). The system characteristics are such that the PID controller should regulate the error signal of the gases sodium nitroprusside (SNP) and isoflurane using MAP readings from the patient. The system responses under the discrete PID control are presented and the results show acceptable performance.

No abstract