Dataset Information

Machine learning health-related applications in low-income and middle-income countries: a scoping review protocol.

ABSTRACT: INTRODUCTION:Machine learning (ML) has been used in bio-medical research, and recently in clinical and public health research. However, much of the available evidence comes from high-income countries, where different health profiles challenge the application of this research to low/middle-income countries (LMICs). It is largely unknown what ML applications are available for LMICs that can support and advance clinical medicine and public health. We aim to address this gap by conducting a scoping review of health-related ML applications in LMICs. METHODS AND ANALYSIS:This scoping review will follow the methodology proposed by Levac et al. The search strategy is informed by recent systematic reviews of ML health-related applications. We will search Embase, Medline and Global Health (through Ovid), Cochrane and Google Scholar; we will present the date of our searches in the final review. Titles and abstracts will be screened by two reviewers independently; selected reports will be studied by two reviewers independently. Reports will be included if they are primary research where data have been analysed, ML techniques have been used on data from LMICs and they aimed to improve health-related outcomes. We will synthesise the information following evidence mapping recommendations. ETHICS AND DISSEMINATION:The review will provide a comprehensive list of health-related ML applications in LMICs. The results will be disseminated through scientific publications. We also plan to launch a website where ML models can be hosted so that researchers, policymakers and the general public can readily access them.

SUBMITTER: Carrillo-Larco RM

PROVIDER: S-EPMC7223147 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning health-related applications in low-income and middle-income countries: a scoping review protocol.

Carrillo-Larco Rodrigo M RM Tudor Car Lorainne L Pearson-Stuttard Jonathan J Panch Trishan T Miranda J Jaime JJ Atun Rifat R

BMJ open 20200510 5

<h4>Introduction</h4>Machine learning (ML) has been used in bio-medical research, and recently in clinical and public health research. However, much of the available evidence comes from high-income countries, where different health profiles challenge the application of this research to low/middle-income countries (LMICs). It is largely unknown what ML applications are available for LMICs that can support and advance clinical medicine and public health. We aim to address this gap by conducting a ...[more]

PMID: 32393612

Similar Datasets

Project description:IntroductionGlobally, transgender and other gender diverse (trans) people face pervasive stigma, which contributes to health inequities across multiple health outcomes. Stigma is a fundamental cause of health inequities because it simultaneously limits access to resources, contributes to systemic vulnerability and generates chronic stress. Anti-trans stigma occurs across multiple socioecological levels, resulting in multiple possible definitions and measurements of trans stigma. Understanding how trans stigma has been measured in low-income and middle-income countries (LMICs) is critical to health promotion efforts for trans communities. Accordingly, this scoping review will identify and examine how anti-trans stigma has been measured in existing LMIC-specific research to inform best practices for measurement of anti-trans stigma that includes consideration of local context.Methods and analysisThis is the protocol for a scoping review of anti-trans stigma in LMICs. We will search (from January 2001 to December 2021) PubMed, WHO Global Medicus and EBSCO. Study selection will conform to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews Checklist. Original studies in English, Spanish, Arabic or Russian will be included. Reviewers will independently screen all citations, full-text articles and abstract data. Data analysis will involve quantitative and qualitative methods. A narrative summary of findings will be conducted.Ethics and disseminationAs a scoping review (no direct interaction with participants), this study is exempt from human subjects oversight. Understanding context-specific ways to measure anti-trans stigma is urgently needed to support trans health globally. The planned scoping review will help to address this gap. Results of the review will be disseminated in a peer-reviewed journal and likely in other media such as conferences, seminars and symposia. PROTOCOL REGISTRATION NUMBER: osf.io/qcs2v.

Project description:BackgroundThe impact and utility of machine learning (ML)-based prediction tools for cancer outcomes including assistive diagnosis, risk stratification, and adjunctive decision-making have been largely described and realized in the high income and upper-middle-income countries. However, statistical projections have estimated higher cancer incidence and mortality risks in low and lower-middle-income countries (LLMICs). Therefore, this review aimed to evaluate the utilization, model construction methods, and degree of implementation of ML-based models for cancer outcomes in LLMICs.MethodsPubMed/Medline, Scopus, and Web of Science databases were searched and articles describing the use of ML-based models for cancer among local populations in LLMICs between 2002 and 2022 were included. A total of 140 articles from 22,516 citations that met the eligibility criteria were included in this study.ResultsML-based models from LLMICs were often based on traditional ML algorithms than deep or deep hybrid learning. We found that the construction of ML-based models was skewed to particular LLMICs such as India, Iran, Pakistan, and Egypt with a paucity of applications in sub-Saharan Africa. Moreover, models for breast, head and neck, and brain cancer outcomes were frequently explored. Many models were deemed suboptimal according to the Prediction model Risk of Bias Assessment tool (PROBAST) due to sample size constraints and technical flaws in ML modeling even though their performance accuracy ranged from 0.65 to 1.00. While the development and internal validation were described for all models included (n=137), only 4.4% (6/137) have been validated in independent cohorts and 0.7% (1/137) have been assessed for clinical impact and efficacy.ConclusionOverall, the application of ML for modeling cancer outcomes in LLMICs is increasing. However, model development is largely unsatisfactory. We recommend model retraining using larger sample sizes, intensified external validation practices, and increased impact assessment studies using randomized controlled trial designs.Systematic review registrationhttps://www.crd.york.ac.uk/prospero/display_record.php?RecordID=308345, identifier CRD42022308345.

Project description:IntroductionNearly every field of medicine has some form of clinical practice guidelines. However, only within the past 5-10 years has the medical community acknowledged the need for well-developed guidelines tailored to the local healthcare needs and the resources available. In most low-income and middle-income countries (LMICs), healthcare workers depend on guidelines developed in high-income countries (HICs), yet many interventions validated in a HIC are ineffective when implemented in an LMIC. The variation in infrastructure, medical personnel, technology and environmental conditions exhibited in LMICs relative to HICs necessitates a careful appraisal of the evidence base used in clinical guideline recommendations. This review aims to map the use of resource-stratified guidelines across all fields of medicine. The review seeks to answer three questions for the identified guidelines: (1) what was the method of development, (2) have they been implemented and, if so, (3) have they been validated.MethodsThe search strategy will aim to locate studies from inception to November 2021. An initial limited search of PubMed and Scopus was undertaken to identify articles on the topic. The text words contained in the titles and abstracts of relevant articles, and the index terms used to describe the articles were used to develop a full search strategy for PubMed and Scopus. This scoping review will be conducted in accordance with the Joanna Briggs Institute (JBI) methodology for scoping reviews. Data to be extracted from each study will include population characteristics of both developers and intended implementation population, medical specialty, validation status, method of guideline development, whether the study is consensus or evidence-based in addition to a summary of recommendations for practice.Ethics and disseminationEthical approval is not required for this review. The plan for dissemination is to publish review findings in a peer-reviewed journal.

Project description:BackgroundA fifth of adults in low- and middle-income countries (LMICs) have multimorbid conditions, which are linked to socio-economic deprivation and aging. Multimorbidity is associated with high rates of functional problems and disability, increased healthcare utilization, and lower quality of life. Literature on multimorbidity and associations with function is mostly from high-income countries (HICs) and focused among older adults. Moreover, data regarding disease patterns and their impact on person-centered outcomes are limited. There is a need for research into understanding common patterns of multimorbidity, and their association with functional impairments, particularly in LMICs. Such information may contribute towards evidence-based and context-relevant strategic policy, planning, and delivery models for health and rehabilitation services, which is imperative in attaining Universal Health Coverage (UHC). The planned scoping review aims to provide an overview of the scope and nature of existing literature on multimorbidity patterns and function among adults in LMICs.MethodsA scoping review will be conducted using a five-step framework and reported according to the PRISMA-ScR guidelines. A comprehensive electronic search of PubMed/MEDLINE, Scopus, EBSCOhost, Scielo, Cochrane and Google Scholar will be conducted and updated from the last pilot search ran in September 2020. Studies of any design will be included if they are reported in English, published (between January 1976 and the last search date) in a peer-reviewed journal, and describe multimorbidity patterns and associations with physical functional impairments, activity limitations or participation restrictions among adults in LMICs. Search results will be independently screened by two reviewers and data extraction will cover study characteristics, participants' characteristics, multimorbidity measures, patterns analysis, and functional measures. Descriptive statistics and narrative synthesis will be used to synthesize and summarize findings.DiscussionPatients with multimorbidity have unique and cross-cutting needs, hence the need for integrated and person-centered approaches to policy, planning, and delivery of medical and rehabilitation services. Considering the shift towards UHC and primary healthcare-led management of chronic diseases, the proposed scoping review is timely. Findings will provide insights into the current extent and scope of multimorbidity research, and guide future inquiry in the field.Trial registrationOpen Science Framework (OSF), https://osf.io/gcy7z/.

Project description:BackgroundDigital technology is a means to uphold or violate human rights in various domains, including business, military, and health. Given the pervasiveness of mobile technology in low- and middle-income countries (LMICs), mobile health (mHealth) interventions present an opportunity to reach remote populations and enable them to exercise civil and political rights and economic, social, and cultural rights, such as the right to health and education. Simultaneously, the ubiquity of mobile phones involves processing sensitive data which can threaten rights, including the right to privacy and nondiscrimination. Digital health is often promoted as advancing human rights and health equity; however, digital rights are underexplored in the literature on mHealth in LMICs. As such, creating an understanding of the digital rights topics covered in the 2022 literature is important to avoid exacerbating existing inequities relating to digital health design, use, implementation, and access.ObjectiveThis scoping review aims to identify digital rights topics in the 2022 peer-reviewed literature on mHealth in LMICs.MethodsThe Arksey and O'Malley framework for scoping reviews guides this review. Searches were performed across 7 electronic databases (Web of Science, Scopus, Ovid, ACM Digital Library, IEEE Xplore, ProQuest, and PubMed). The screening processes were guided by the research question "What digital rights topics have been explored in the 2022 literature on mHealth in LMICs?" Only papers addressing mHealth in LMICs and digital rights topics were included. Data extraction will include publication title, year, and type; first author's affiliation country; LMICs implicated; infrastructure challenges; study aims, design, limitations, and future work; health area; mHealth technology, functions, purpose or application, and target end users; human or digital right terms used; explicit rights topics cited; and implied rights topics. The results will be reported using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) checklist.ResultsThis scoping review was registered in Open Science Framework (December 22, 2022). Title and abstract screening and full-text paper screening were completed in 2023. This resulted in 56 papers being included in the study. The target date for completing data extraction and publishing a case study of the initial findings is the end of 2023. The full scoping review findings are expected to be disseminated through various pathways benefiting academia, practice, and policy making by the end of 2024. These include journal papers, conference presentations, publicly available toolkits for research and practice, public webinars, and policy briefs with evidence-based policy recommendations emerging from this review.ConclusionsThe planned scoping review will identify digital rights topics in the 2022 literature at the intersection of mHealth and LMICs. Furthermore, it will highlight the importance of patient empowerment, data protection, and inclusion in mHealth research and related policies in LMICs.Trial registrationOpen Science Framework osf.io/7mz24; https://osf.io/7mz24.International registered report identifier (irrid)DERR1-10.2196/49150.

Dataset Information

Machine learning health-related applications in low-income and middle-income countries: a scoping review protocol.

Publications

Machine learning health-related applications in low-income and middle-income countries: a scoping review protocol.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets