Monash University
Browse

Naïve Bayes versus Support Vector Machines: A comparison of two algorithmic approaches for estimating cause of death from free-text

Download (3.15 MB)
Version 2 2020-10-20, 00:42
Version 1 2020-10-11, 10:42
thesis
posted on 2020-10-20, 00:42 authored by KRIDARAAN KOMAHAN
Determining cause of death is a basic role of vital registration. Unfortunately, most deaths globally are not registered at all or without an accurate cause of death. Verbal autopsy (VA) is an alternative mechanism to estimate cause of death. However, responding to the VA questionnaire often takes a significant period of time to complete and can prove challenging as it overlaps with the mourning period. This thesis is to explore if machine learning algorithms primarily naive Bayes and SVMs can be used to determine cause of death from free-text responses from a verbal autopsy questionnaire.

History

Principal supervisor

Daniel Reidpath

Year of Award

2020

Department, School or Centre

Jeffrey Cheah School of Medicine and Health Sciences (Monash University Malaysia)

Campus location

Malaysia

Course

Master of Biomedical Science

Degree Type

MASTERS

Faculty

Faculty of Medicine, Nursing and Health Sciences

Usage metrics

    Faculty of Medicine, Nursing and Health Sciences Theses

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC