Why the study?
Heart disease diagnosis often requires multiple time-consuming medical examinations to detect root causes, motivating early identification of cardiomegaly using limited diagnostic parameters.
Machine learning techniques, specifically Recurrent Fuzzy Neural Networks, show high accuracy in predicting cardiomegaly using limited diagnostic parameters.
RFNN may aid cardiomegaly prediction with limited data; hypothesis-generating and requires prospective validation before clinical use.
Problems related to heart is one of the fundamentally developing issue throughout the globe, prompting a large portion of deaths because of heart issues. The weight of cardiovascular sickness can be enhanced via hazard disease and accordingly essential counteractive action is an imperative need for all engineers of well-being arrangement. For every heart based diseases we need to undergo different medical examinations which kills lot of time to detect the exact root cause, rather than going for several diagnosis mechanisms. In this paper we propose that with limited parameters from the diagnosis results we can identify the issue of Cardiomegaly at early stages.
No takes yet. Share an insight, caveat, or question.
Doppala et al. (2019) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: