Page 373 - Special Topic Session (STS) - Volume 4

STS1080 Mahmoud Rafea et al.
of normal proteins and disease proteins. The normal proteins consist of
Environment proteins, Food proteins, Commensal proteins, Tissue proteins.
The disease proteins are malignant proteins or pathogenic proteins. Then, they
proposed machine learning algorithms to analyze EDAS data. The aims of such
investigation have been to identify the minimum set of proteins that can be
used as biomarkers for a particular disease (Pathogens, and Malignancies).
This work moves from identifying single biomarker to discovering multiple
biomarkers foe each disease separately. Lastly, they represent their results
(detected biomarkers) in the form of rules. Based on these rules they proposed
a diagnostic model. This diagnostic model can diagnose any new case (new
EDAS) and determine if this case has a specific disease or not. If this new case
is diseased, the model can predict the ratio of the biomarkers at this case.

5. Conclusion and future work
This survey provides the brief description of machine learning techniques
for disease diagnosis and discovering biomarkers. The mentioned related work
concentrated on discovering the relationship between diseases and their
symptoms. However, no one of them try to detect the relationship between
the normal proteins and the diseased proteins. In the future, it is vital to predict
the relations between the diseases proteins and environmental actors present
in RBC.

References
1. Fatima, M. and Pasha, M. (2017) Survey of Machine Learning Algorithms
for Disease Diagnostic. Journal of Intelligent Learning Systems and
Applications, 9, 1-16. https://doi.org/10.4236/jilsa.2017.91001
2. Pople, H.E.: Heuristic methods for imposing structure on ill-structured
problems: the structure of medical diagnostics. In: Szolovits, P. (ed.)
Artificial Intelligence in Medicine .AAAS Selected Symposium, vol. 51, pp.
119–190. Westview Press, Boulder (1982)
3. Szolovits, P.: Artificial Intelligence in Medicine. AAAS Selected
Symposium, vol. 51. Westview Press, Boulder (1982).
4. Rafea M, Elkafrawy P, Nasef MM, Elnemr R and Jamal AT (2019) Applying
Machine Learning of Erythrocytes Dynamic Antigens Store in Medicine.
Front. Mol. Biosci. 6:19. doi: 10.3389/fmolb.2019.00019
5. Gitanjali, J., Ranichandra, C., & Pounambal, M. (2014) APRIORI algorithm
based medical data mining for frequent disease identification. IPASJ
International Journal of Information Technology (IIJIT), 2(4), 1-5.
6. Said I. , Haruna A. , Garko A. (2015) Association rule mining on medical
data To predict heart disease. International Journal of Science
Technology and Management, 4(8), 26-35.
7. Karthiyayini, R., & Jayaprakash, J. (2015) Association technique on
prediction of chronic diseases using Apriori algorithm. International

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