CSEIT1952154 | Received : 08 March 2019 | Accepted : 20 March 2019 | March-April -2019 [ 5 (2) : 543-546 ] International Journal of Scientific Research in Computer Science, Engineering and Information Technology © 2019 IJSRCSEIT | Volume 5 | Issue 2 | ISSN : 2456-3307 DOI : https://doi.org/10.32628/CSEIT1952154 543 Generalized Disease Prediction based on Symptoms Ramandeep Singh Sethi*, Aniket Thumar, Vaibhav Jain, Sachin Chavan Department of Computer Science and Engineering, NMIMS, Shirpur, Maharashtra, India ABSTRACT We are right now facing a daily reality where mobile utilization is developing exponentially. Mobile technology is omnipresent. It offers services that is customized to us – the 21st century user. Innovation has empowered us incredibly, we look for data anyplace and anytime. Digital health is acquainting new methodologies with the administration of health conditions. Research has exhibited noteworthy development in the effect that digital health is having on patients and overall healthcare. The selection of digital health tools, such as mobile healthcare apps, holds incredible guarantee with proof of these tools playing a positive role in both patient results and the expenses. Portable applications can enable patients to be effectively associated with each phase of their healthcare venture. This fundamentally enhances patient commitment and the patient experience, and urges purchasers to be responsible for their own health. Portable apps can tailor health content as indicated by the patients, or healthcare providers, mobile history and current conduct. These customized mobile experiences help convey highly pertinent information at the right time, based on user priority. Keywords : Data Mining, Classification, Clustering I. INTRODUCTION The disease prediction systems available in the market currently have decent accuracy but they are not available to everyone. The systems which are available publicly don’t provide personalized treatment and remedies. Also, these systems don’t take BMI (Body Mass Index) and drugs that patient is taking currently into consideration during the prediction process. This affects their accuracy significantly. Data mining is a pattern discovery technique that is used to find the concealed qualities from huge measure of information. As the patient’s populace and medications increases, the restorative databases also grows day by day. The examination of these therapeutic data is intricate without the PC- based analysis architecture. The PC-based analysis architecture provides the robotized medical determination system. This robotized determination system supports the medical expert to make systematic decision in therapy and ailment forecast. Data mining is the quickly developing area for the doctors to deal with huge amount of patient’s data sets from multiple point of view such as understanding of complex symptomatic tests, interpreting past outcomes and accumulating the different information together. Customarily hospital’s conclusion is molded by the medical expert’s inspection and predicting the result rather than the inference obtained from the huge data. This robotized determination system leads to increase the service’s standards and reduces the medical cost. II. RELATED WORK Darcy A. Davis Used ICD9-CM to predict future disease risks. They used clustering to predict the disease based on similar patient’s medical history [1].