Analyses the Predictive Power of Machine Learning Procedures Over Multi Diseases Datasets

In today's age of technology, people do not prioritize their health or well-being. Due to frequent circumstances, regular visits to the hospital for check-ups are uncommon, this has led to an increase in illness among people. Nowadays, the majority of people suffer from various health issues like heart, diabetes, kidney disease. The World Health Organization (WHO) considers such chronic diseases are the leading causes of premature death, responsible for half of all deaths in most countries. Early identification of patients can prevent the disease from progressing. Various distributed investigations strongly illustrated that traditional diagnosis methods of chronic diseases are susceptible to bias and variation among medical professionals, making it challenging to timely identify issues accurately. However, huge published efforts denoting that ML based methodology can significantly improve the timely estimation of various health issues and despite the availability of up-to-date information and various machine learning-based tools, accurate diagnosis of such diseases is remaining as a challenge. To address this issue, this paper investigates the chronic diseases forecasting act of dissimilar machine learning techniques, recital evaluation of different ML procedures using the UCI machine learning disease dataset. Results are corroborated using accurateness & confusion matrix. This paper also deliberates the benefits and drawbacks of an accessible diseases prediction schemes for assisting novice researchers in understanding the disease prediction function of machine learning-based methodologies and determining the scope of future research.