Page 368 - Special Topic Session (STS) - Volume 4

STS1080 Mahmoud Rafea et al.

A survey of Machine Learning Algorithms for

efficient biomarkers identification
2
Mahmoud Rafea , Passant Elkafrawy *, Mohammed M. Nasef , Rasha Elnemr ,
2
1
1
Amani Tariq Jamal *
3
1 Central Lab of Agriculture Expert Systems, Giza, Egypt
2 Mathematics and Computer Science Department, Faculty of Science, Menoufia University,
Shibin El Kom, Egypt,
3 Computer Science Department, Faculty of Computing and InformationTechnology, Jeddah
University, Jeddah, Saudi Arabia

Abstract
These days, health care industry generates a large amount of complex data
about patients. This increase in data volume requires ways in which data can
be extracted and processed efficiently. Machine learning algorithms could play
an efficient role in the field of disease diagnosis and biomarker discovery.
Machine learning attempts to tell how to automatically find a good predictor
based on past experiences. The recent researchers in machine learning
promise the improved accuracy of perception and diagnosis of disease. The
accurate diagnosis of some serious diseases is a very crucial task in medical
science. This paper discusses some of the machine learning algorithms in
biomedical field.

Keywords
Biomarkers identification, Machine learning, Big data Analytics for disease
prognosis

1. Introduction
Big data turns into Chunks due to multidisciplinary combined effort of
machine learning (ML), databases and statistics. Today, in medical sciences
disease diagnostic test is a serious task. It is very important to understand the
exact diagnosis of patients by clinical examination and assessment. For
effective diagnosis and cost effective management, decision support systems
that are based upon computer may play a vital role. Health care field generates
big data about clinical assessment, report regarding patient, cure, follow-ups,
medication etc. However, this data is acquired from long periods of data
collection, and clinical expertise for implementing the best diagnostic test and
interpreting test results based on patient’s history [1].
A large number of different systems for disease diagnosis were proposed
in the early days as in [2, 3]. Then researchers developed their own
representation methods guided by thoughts on how to handle a particular
medical problem. The development of these early systems gave rise to the
phrase knowledge-based system, or knowledge system, which is generally

357 | I S I W S C 2 0 1 9