Automatic Verbal Autopsy Classification Using Multinomial Logistic Regression Classifier by Using Recursive Feature Elimination

Abstract

Verbal autopsy is one of the finest medical process to identify automatically the cause of a death afore medical ascendant entities will certify it. Identifying the exact cause is intricate and fuzzy in nature. The dataset with an exact cause of death is a paramount implement for every country to make the presage about the life style and medical facilities available to the people. Multinomial logistic regression was utilized in our study to relegate the exact cause of death. We used standard datasets like PHMRC and Matlab which were potentially accepted in medical field. The reason to utilize the Multinomial logistic Regression is that most of the dataset is consisting of 0 and 1 values which betoken the presence and absence of value in the attribute. We used three standard metrics like the sensitivity, Chance Corrected Concordance (CCC) and Cause-specific mortality fraction (CSMF) for a comparison of our model with precedent models like Insilico VA, Tariff and InterVA-4. Computed results show that proposed model is better than the precedent models.