LAUSR

Abstract Background There is recent increasing interest in physical fitness, and improvement in applications for this purpose have been standout amongst recent research efforts. An example of such a health application is the identification of coronary disease using PC-based determination strategies, wherein the information is acquired from different sources and assessed automatically by computational means. Objectives Implementation of a fuzzy-based clinical detection model for coronary risk prevention, which mainly comprises two main objectives: (1) designing weighted fuzzy standards, and (2) creating a fuzzy guidelines based choice supporting network. Methods In prior work, information was obtained from a supportive network which utilized learning from medical specialists, and ported this information into a PC processing queue. The entire process, however, is time consuming and tedious. Medical specialists reach conclusions based on manual observations, which can be inaccurate in some instances. To address this issue, machine learning procedures have been created to obtain information from patients. Results and Conclusions: Herein, a fuzzy rule-based clinical system is described for the automatic detection of Coronary Heart Disease (CHD). This was done by gathering information, implementing assessment procedures, and creating knowledge from patient clinical data.