Open AccessSupervised machine learning models applied to disease diagnosis and prognosis
Author(s) -
Maria C. Mariani,
Osei K. Tweneboah,
Al Masum Bhuiyan
Publication year - 2019
Publication title -
aims public health
Language(s) - English
Resource type - Journals
ISSN - 2327-8994
DOI - 10.3934/publichealth.2019.4.405
Subject(s) - random forest , machine learning , receiver operating characteristic , breast cancer , heart disease , disease , artificial intelligence , principal component analysis , computer science , regression analysis , cancer , regression , principal component regression , medicine , statistics , mathematics
This work analyses the diagnosis and prognosis of cancer and heart disease data using five Machine Learning (ML) algorithms. We compare the predictive ability of all the ML algorithms to breast cancer and heart disease. The important variables that causes cancer and heart disease are also studied. We predict the test data based on the important variables and compute the prediction accuracy using the Receiver Operating Characteristic (ROC) curve. The Random Forest (RF) and Principal Component Regression (PCR) provides the best performance in analyzing the breast cancer and heart disease data respectively.