Predicting Trachoma Using Machine Learning Techniques

Akbar Khan, Abdul Samad, Faizullah Khan, Surat Khan

Abstract


Machine learning is the area of artificial intelligence which uses statistical methods for data classifications. It is now usually applied in different areas like business, government, education and health. In health sector, it is almost used for the prediction, risk factor identification and many more. Among these applications it is used for different eye diseases. Trachoma is a common eye disease that causes blindness. This paper aims to use different techniques of machine learning algorithms and to find out the most effected factor causing trachoma.

Keywords


Machine learning; WEKA; Decision Tree; Random Forest; J48; Support Vector Machine

Full Text:

PDF

References


Alemayehu M, Koye DN, Tariku A, Yimam K. (2015). Prevalence of active trachoma and its associated

factors among rural and urban children in Dera Woreda, Northwest Ethiopia: a comparative crosssectional

study. Biomed research international 2015 (2015):1-8.

Emerson PM, Burton M, Solomon AW, Bailey R, Mabey D. (2006). The SAFE strategy for trachoma

control: using operational research for policy, planning and implementation. Bulletin of the World Health

Organization 84(8):613-619.

He H, Garcia EA. (2009). Learning from imbalanced data. IEEE Transactions on knowledge and data

engineering 21(9):1263-1284.

Hsieh YH, Bobo LD, Quinn TC, West S. K. (2000). Risk factors for trachoma: 6-year follow-up of children

aged 1 and 2 years. American Journal of Epidemiology 152(3):204-211.

Morris J. (2004). Beyond clinical documentation: using the EMR as a quality tool. Health management

technology 25(11):20-25.

Mowafy MA., Saad NE, El-Mofty HM, ElAnany MG, Mohamed MS. (2014). The prevalence of Chlamydia

trachomatis among patients with acute conjunctivitis in Kasr Alainy ophthalmology clinic. The Pan African

medical journal 17(151):1-6.

Vallejo-Alonso B, Rodrigues-Castellanos A, Arregui-Ayastuy G. (2011). Identifying, measuring, and

valuing knowledge-based intangible assets. New perspectives. New York, IGI Global.



Contacts | Feedback
© 2002-2014 BUITEMS