A Medical Information Recommender System for Disease Prediction and its Treatment

I INTRODUCTION

The use of computer systems in decision making, prediction

and recommendation has been a trending topic

of research for more than a decade. The recent advances

in medical science can be attributed to advances

in computer technology. But, the prediction of medical

behavior is still a very challenging task which is

Permission to make digital or hard copies of all or part of this work for

personal or classroom use is granted without fee provided that copies are

not made or distributed for profit or commercial advantage and that copies

bear this notice and the full citation on the first page. To copy otherwise, or

republish, to post on servers or to redistribute to lists, requires prior specific

permission and/or a fee.

VINCI 2014, August 5–8, 2014, Sydney, Australia.

Copyright 2014 ACM 978-1-4503-2765-7...$10.00

done with the help of a medical professional. The occurrence

of every disease shows a pattern based on its

symptoms. The main focus of this paper is to propose

a system to exploit these patterns for predicting the associated

diseases and the time that might be spent on

their treatment.

By prediction we mean to forecast an occurrence of a

condition based on some mathematical calculation. For

implementing this prediction, we need a recommender

system. A recommender system is a system which reads

an input, nds a pattern in it which is based on the

dataset given to train the system. Based on the pattern

it gures out a solution for the problem.

A nave solution can be to create a database of every

possible disease and its symptoms and predicting diseases

based on that. The biggest drawback about this

solution is that the eciency and speed of this solution

are very less and the siz...

... middle of paper ...

...this paper, we have addressed the problem of predicting

diseases and their respective cure time based on

the preliminary symptoms. The main focus is on the

classication of symptoms based on their severity and

importance and using this knowledge to calculate a numerical

value to identify diseases.

The future work can focus on using the medical history

of the user with current symptoms in prediction

of diseases. The test results for various medical conditions

can be used to further improve the reliability of

the system. One more novel thing that can be added is

medicine prediction for the patient.

abbrv

REFERENCES

1. S Sudha. Disease prediction in data mining

technique{a survey. IJCAIT, 2(1):17{21, 2013.

2. Meisamshabanpoor and Mehregan Mahdavi.

Implementation of a recommender system on

medical recognition and treatment. IJEEEE,

2(4):315{318, 2012.