Computerized Decision Support System and Fuzzy Logic Rules for Early Diagnosis of Pesticide-Induced Diseases

Abstract

Many reflexologists employ outdated concepts that do not align with modern anatomy, physiology, and biophysics. Those concepts undermine physicians' confidence in their diagnosis. This study aims to improve the quality of medical care for workers in the agro-industrial complex who are exposed to pesticides by a fuzzy mathematical model using acupuncture points reflexes. Data obtained from reflex diagnostic methods are utilized in hybrid fuzzy decision rules to build a predictive classification model that integrates medical diagnosis with artificial intelligence. Pesticide exposure leads to cardiovascular and nervous system bronchopulmonary diseases, as well as kidney and liver tissue pathology. The developed model generates decision rules for early prediction of nervous system disorders, particularly when the primary risk factor is exposure to agricultural pesticides containing nitrates. In modern medical practice, there is a growing interest in ancient methods of reflex diagnostics and therapies based on maintaining the energy balance of an organism's meridian structures. However, the lack of a solid theoretical foundation explaining the mechanisms of interaction between internal and surface meridian structures poses a significant obstacle to wider adoption of reflex diagnostic techniques. This limitation severely hampers the potential of acupuncture. Moreover, many reflexologists in practice tend to overstate the benefits of acupuncture, which may lead to errors, that undermine the appropriate approach to diagnosis and treatment. The proposed model proves valuable for the healthcare of agro-industrial complex workers, as its decision-making process achieves an accuracy rate of over 85% in forecasting nervous system disorders.