Sebastiao Rogério da Silva Neto, Thomás Tabosa Oliveira, Igor Vitor Teixeira, Samuel Benjamin Aguiar de Oliveira, Vanderson Souza Sampaio, Theo Lynn, Patricia Takako Endo
Abstract
Neglected tropical diseases (NTDs) primarily affect the poorest populations, often living in remote, rural areas, urban slums or conflict zones. Arboviruses are a significant NTD category spread by mosquitoes. Dengue, Chikungunya, and Zika are three arboviruses that affect a large proportion of the population in Latin and South America. The clinical diagnosis of these arboviral diseases is a difficult task due to the concurrent circulation of several arboviruses which present similar symptoms, inaccurate serologic tests resulting from cross-reaction and co-infection with other arboviruses.
Introduction
Neglected tropical diseases (NTDs) include a wide range of parasitic, viral, and bacterial diseases that prevail in tropical and subtropical conditions in 149 countries and affect one billion people every year [1]. One major category of NTDs are arthropod-borne viruses (or arbovirus diseases), a group of viruses that are found in nature and biologically transmitted between susceptible vertebrate hosts by hematophagous arthropods.
Materials and methods
The purpose of an SLR is to identify, select and critically appraise research on a specific topic. SLRs typically comprise three main phases: planning the review, conducting the review, and reporting the review results [39]. The goal of this paper is to present evidence on the state of the art of studies investigating the automatic classification of arboviral diseases to support clinical diagnosis based on ML and DL models.
Discussion
In this SLR on the use of ML and DL to support the clinical diagnosis of arboviral diseases, we found 963 publications, 15 of which fulfilled the inclusion criteria and were subsequently analysed in detail. We have reported our findings in five main categories: (1) disease focus, (2) ML and DL technique, (3) ML and DL model design, (4) data sets and attributes, and (5) evaluation metrics. Comparing the selected studies, even within these categories, due to the variation in focal disease and region, ML and DL technique, and ML and DL model configuration, is challenging.
Acknowledgments: Authors would like to thank National Council for Scientific and Technological Development (CNPq); Research Support Foundation of the State of Amazonas (FAPEAM); Health Surveillance Foundation Dr. Rosemary Costa Pinto; Foundation for Support to Science and Technology of the State of Pernambuco (FACEPE); and Universidade de Pernambuco (UPE), an entity of the Government of the State of Pernambuco focused on the promotion of Teaching, Research and Extension.
Citation: da Silva Neto SR, Tabosa Oliveira T, Teixeira IV, Aguiar de Oliveira SB, Souza Sampaio V, Lynn T, et al. (2022) Machine learning and deep learning techniques to support clinical diagnosis of arboviral diseases: A systematic review. PLoS Negl Trop Dis 16(1): e0010061. https://doi.org/10.1371/journal.pntd.0010061
Editor: Rhoel Ramos Dinglasan, University of Florida, UNITED STATES
Received: July 30, 2021; Accepted: December 6, 2021; Published: January 13, 2022.
Copyright: © 2022 da Silva Neto et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: All relevant data are within the manuscript.
Funding: VSS has a grant (062.00249/2020 [EDITAL N. 006/2019 - UNIVERSAL AMAZONAS]) from Fundação de Amparo à Pesquisa do Estado do Amazonas (FAPEAM) ( http://www.fapeam.am.gov.br/ ). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Competing interests: The authors have declared that no competing interests exist.
