Polymers are huge compounds made up of numerous monomers (repeatedsubunits). They have similar macro and micro properties, as well aselectrical transport qualities, semiconductive capabilities, and opticalfeatures. With the advent of conductive polyacetylene, conductivepolymers have gotten a lot of interest. These conductors have a wide rangeof electrical conductivity, which may be produced by doping, while beingmechanically flexible and having a high thermal stability. Polymers may becreated using a variety of methods, including chemical and electrochemicalpolymerization. With advancement in material stability and greaterproperty control, an increasing variety of new applications are now beinginvestigated.

Machine Learning has a significant application in the detection of disease because of the automated process. Using machine learning models, the detection of disease can be done with higher effectiveness and with less error which may be seen in the context of computations made by humans. In this research, the detection of multiple diseases has been done with the application of machine learning. In this research context, three data have been selected namely Heart Disease Data (from UCI Repository), Liver Disease Data (from Kaggle Repository) and Diabetes Data (from Kaggle Repository). To detect disease, four state-of-the-art classifiers have been applied along with the proposed hybrid model. By applying those classifiers or machine learning models, the detection of three diseases has been done along with the comparison of performances. In that comparison, it has been observed that the proposed hybrid model has performed the best to detect all three types of disease. In the detection of heart disease, the proposed model has achieved 96.7% accuracy, for liver disease, the accuracy has reached 97.42% and for diabetes disease detection, the proposed model has acquired 97.39% accuracy. These performances of the proposed hybrid model have also been seen to be higher compared to the existing approaches for the detection of similar diseases.

No abstract