Main content

The Use of Machine Learning and Predictive Modelling Methods in the Identification of Hosts for Viral Infections: Scoping Review Protocol

Show full item record

Title: The Use of Machine Learning and Predictive Modelling Methods in the Identification of Hosts for Viral Infections: Scoping Review Protocol
Author: Alberts, Famke; Keay, Sheila; Poljak, Zvonimir
Department: Department of Population Medicine
Abstract: Background: Advanced in-silico predictive modelling techniques combining methods of machine learning and bioinformatics have been applied to predict the reservoir of a virus and all hosts that exist within that reservoir. However, a systematic compilation of this body of research does not exist. Objectives: This protocol describes the methods that will be used to conduct a formal scoping review of current literature to address the question: “What machine learning methods have been applied to influenza virus and coronavirus genome data for identification of the potential reservoirs?”. Eligibility Criteria: Eligible studies will be primary research studies, in English, from any geographic location, published between 2000-2021, conducted using machine learning techniques within the context of understanding or predicting influenza virus or coronavirus host-range or transmission. Sources of Evidence: The following databases will be searched: PubMed, MEDLINE, ProQuest, Engineering Village, and Web of Science from 2000-2021. Charting Methods: We will extract data on general and specific study characteristics, identifying the steps taken in data gathering, processing, and analysis.
URI: https://hdl.handle.net/10214/26112
Date: 2021-07-28
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International


Files in this item

Files Size Format View
MachineLearningHosts_ScopingReviewProtocol.pdf 203.9Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record

Attribution-NonCommercial-NoDerivatives 4.0 International Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 International