A Framework for Classifying Unstructured Data of Cardiac Patients: A Supervised Learning Approach

Abstract

Data mining has recently emerged as an important field that helps in extracting useful knowledge from the huge amount of unstructured and apparently un-useful data. Data mining in health organization has highest potential in this area for mining the unknown patterns in the datasets and disease prediction. The amount of work done for cardiovascular patients in Pakistan is scarcely very less. In this research study, using classification approach of machine learning, we have proposed a framework to classify unstructured data of cardiac patients of the Armed Forces Institute of Cardiology (AFIC), Pakistan to four important classes. The focus of this study is to structure the unstructured medical data/reports manually, as there was no structured database available for the specific data under study. Multi-nominal Logistic Regression (LR) is used to perform multiclass classification and 10-fold cross validation is used to validate the classification models, in order to analyze the results and the performance of Logistic Regression models. The performance-measuring criterion that is used includes precision, f-measure, sensitivity, specificity, classification error, area under the curve and accuracy. This study will provide a road map for future research in the field of Bioinformatics in Pakistan.