Using Random forest algorithm to classify Iron anaemia unspecified and coagulation defect unspecified diseases
Volume 23 , Issue 1 , February 2022 , Pages (653 - 662)
Authors
Mohammad Mahmood Faqe 1 ; Sara Noori Mohammad 1
1 University of Sulaimania
10.17656/jzsb.11183
Keywords
Abstract
Cancer is a general term for a large group of diseases that can affect any part of the body which is a leading cause of death worldwide, accounting for nearly 10 million deaths. A correct cancer diagnosis and classification are essential for suitable and effective treatment because every cancer type requires a specific treatment program. With the help of technology it has now become easier to predict this disease in patients. Many machine learning techniques used to analyse the dataset and then classified. In this study, most advanced and new machine learning technique Random Forest (RF) was used. Random Forest is a combination of a series of tree structure classifiers. It is a flexible even without hyper-parameter tuning, a great result most of the time. It is also one of the most used algorithms, because of its simplicity and diversity (it can be used for both classification and regression tasks). The used data obtained from 200 Iron anaemia and coagulation defect patients records in Hiwa hospital at 2019. There is multiple major factors developed cancer disease. These factors that are taken in this article include Gender, Age, Blood group, patient work, Food type, Place and The type of disease. The results of the analysis showed that accuracy of RF model is 85% which is a good ratio. Also, sensitivity model is 91.5. Finally, the rank of taken variable in term of importance is the Cured, Blood Group, Age, patient work, Place, food type and Gender respectively.
Statistics
- Article view362
- Downloads0
- First online15 February 2022
- Published at15 February 2022
- RIS
- BibTeX
- EndNote
- Mendeley
- APA (7th edition)
- MLA (9th edition)
- Chicago
- Harvard
- IEEE
- Vancouver