International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 06 | June 2020 www.irjet.net p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 4824
AI-Assisted Prediction on Potential Health Risks
Ms. Anusha
Professor, Department of Computer Science Engineering Jain Deemed to be University
Bangalore, India
G Tharun Reddy
UG Scholar, Department of Computer Science Engineering Jain Deemed to be University
Bangalore, India
G Naveen
UG Scholar, Department of Computer Science Engineering Jain Deemed to be University
Bangalore, India
P Pavanchand
UG Scholar, Department of Computer Science Engineering Jain Deemed to be University
Bangalore, India
M Ravi Kiran
UG Scholar, Department of Computer Science Engineering Jain Deemed to be University
Bangalore, India
--------------------------------------------------------------------------------***------------------------------------------------------------------------------
Abstract - With the event of society and economy, people pay more attention to their own health. The demand for
personalized health services is gradually rising. However, thanks to the shortage of experienced doctors and physicians, most
healthcare organizations cannot meet the medical demand of the public. With the widespread use of hospital data systems,
there's a huge amount of generated data which may be wont to improve healthcare service. Thus, more and more data
processing applications are developed to supply people with more customized healthcare services. In this paper, we are
proposing an AI-assisted prediction system, which leverages data processing methods to reveal the connection between the
regular physical examination records and therefore the potential health risk. It can predict the examinee risk of physical
status next year and supports the physical examination records this year. The system provides a user-friendly interface for
both examinees and doctors. The examinee can know their potential health risks while doctors can get a group of examinees
with potential risks. It is an honest solution for the mismatch of insufficient medical resources and rising medical demands.
1. INTRODUCTION
Many healthcare organizations (hospitals, medical centers) around the world are busy in serving people with the best
healthcare services. Nowadays, people pay more attention to their health. They want higher quality and more personalized
healthcare services. However, with the limitation of the number of skilled doctors and physicians, most healthcare
organizations cannot meet the needs of the public. How to provide higher quality healthcare to more people with limited
manpower becomes a key issue. The healthcare sector is generally perceived as being ‘information-rich’ yet ‘knowledge-
poor'. Hospital systems typically generate huge amounts of data which takes the form of numbers, text, charts, and images.
There is a lot of hidden information in these data untouched. Data mining and predictive analytics techniques aim to reveal
patterns and rules by applying advanced data analysis techniques on a large set of data for descriptive and predictive
purposes. Data mining is suitable for processing large datasets from the hospital information system and finding relations
among data features. It takes only a few researchers to analyze data from hospital information systems, and provide huge
medical knowledge which can be used to support clinical decision making. Also, we could use data mining to provide a self-
service healthcare system, which can serve lots of people at the same time. The self-service healthcare system is of great
significance to solve the problem of imbalance between limited medical resources and demands. Healthcare data mining has
been most widely used for diagnosis, prognosis, or treatment planning.