Disease prediction and diagnosis is one of the complex applications where data mining tools and techniques are used to providing successful results because of significant improvements in technology. This research identifies gaps in the research on disease prediction, diagnosis and treatment and it also proposes a model to systematically close those gaps. Data mining have great potential for healthcare industry to enable health systems to systematically use data and identify the efficiency and improve care with reduce cost. The data mining techniques to Multi disease treatment it can provide reliable performance. So the system can be effective in reducing the death toll. The healthcare industry collects huge amounts of healthcare data which, unfortunately are not “mined” to discover hidden information for effective decision making. This proposed work has developed a prototype for the Multi Sickness Prediction System (MSPS) using data mining techniques by to compute the chance of prevalence of explicit unwellness from medical knowledge by using k-means, Large Memory Storage and Retrieval (LAMSTAR) and Medical diagnosis methodology. The system uses service oriented architecture (SOA) whereby the system elements of diagnosis, data portal and alternative miscellaneous services are provided. This reduces the multiple diseases showing the similar symptoms problem and it will increase the accuracy of such diagnosis. This proposed system will provide some reliable decision finding the disease for healthcare support.