Explainable machine learning for breast cancer diagnosis from mammography and ultrasound images: a systematic review.

BACKGROUND: Breast cancer is the most common disease in women. Recently, explainable artificial intelligence (XAI) approaches have been dedicated to investigate breast cancer. An overwhelming study has been done on XAI for breast cancer. Therefore, this study aims to review an XAI for breast cancer diagnosis from mammography and ultrasound (US) images. We investigated how XAI methods for breast cancer diagnosis have been evaluated, the existing ethical challenges, research gaps, the XAI used and the relation between the accuracy and explainability of algorithms. METHODS: In this work, Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist and diagram were used. Peer-reviewed articles and conference proceedings from PubMed, IEEE Explore, ScienceDirect, Scopus and Google Scholar databases were searched. There is no stated date limit to filter the papers. The papers were searched on 19 September 2023, using various combinations of the search terms 'breast cancer', 'explainable', 'interpretable', 'machine learning', 'artificial intelligence' and 'XAI'. Rayyan online platform detected duplicates, inclusion and exclusion of papers. RESULTS: This study identified 14 primary studies employing XAI for breast cancer diagnosis from mammography and US images. Out of the selected 14 studies, only 1 research evaluated humans' confidence in using the XAI system-additionally, 92.86% of identified papers identified dataset and dataset-related issues as research gaps and future direction. The result showed that further research and evaluation are needed to determine the most effective XAI method for breast cancer. CONCLUSION: XAI is not conceded to increase users' and doctors' trust in the system. For the real-world application, effective and systematic evaluation of its trustworthiness in this scenario is lacking. PROSPERO REGISTRATION NUMBER: CRD42023458665.

Adoption of electronic health record systems to enhance the quality of healthcare in low-income countries: a systematic review.

BACKGROUND: Electronic health record (EHR) systems are mentioned in several studies as tools for improving healthcare quality in developed and developing nations. However, there is a research gap in presenting the status of EHR adoption in low-income countries (LICs). Therefore, this study systematically reviews articles that discuss the adoption of EHR systems status, opportunities and challenges for improving healthcare quality in LICs. METHODS: We used Preferred Reporting Items for Systematic Reviews and Meta-Analyses in articles selected from PubMed, Science Direct, IEEE Xplore, citations and manual searches. We focused on peer-reviewed articles published from January 2017 to 30 September 2022, and those focusing on the status, challenges or opportunities of EHR adoption in LICs. However, we excluded articles that did not consider EHR in LICs, reviews or secondary representations of existing knowledge. Joanna Briggs Institute checklists were used to appraise the articles to minimise the risk of bias. RESULTS: We identified 12 studies for the review. The finding indicated EHR systems are not well implemented and are at a pilot stage in various LICs. The barriers to EHR adoption were poor infrastructure, lack of management commitment, standards, interoperability, support, experience and poor EHR systems. However, healthcare providers' perception, their goodwill to use EMR and the immaturity of health information exchange infrastructure are key facilitators for EHR adoption in LICs. CONCLUSION: Most LICs are adopting EHR systems, although it is at an early stage of implementation. EHR systems adoption is facilitated or influenced by people, environment, tools, tasks and the interaction among these factors.

Prevalence of soil-transmitted helminths infections among preschool and school-age children in Ethiopia: a systematic review and meta-analysis.

BACKGROUND: There is a lack of comprehensive national data on prevalence, geographical distribution of different species, and temporal trends in soil-helminthiasis (STHs). Therefore, this study aimed to provide a summary and location of the available data on STHs infection among preschool and school-age children in Ethiopia. METHODS: The search was carried out in Medline via PubMed, Scopus, Science Direct, Web of Science, and Google Scholar on data published between 1997 to February 2020 for studies describing the rate of STHs infection among preschool and school-age in Ethiopian. We followed the Patient, Intervention, Comparison, and Outcome (PICO) approach to identify the studies. Meta-regression was performed to understand the trends and to summarize the prevalence using the "metaprop" command using STATA software version 14.0 RESULTS: A total of 29,311 of the 61,690 children examined during the period under review were infected with one or more species of intestinal parasites yielding an overall prevalence of 48% (95% CI: 43-53%). The overall pooled estimate of STHs was 33% (95% CI: 28-38%). The prevalence was 44% (95% CI: 31-58%) in SNNPR, 34% (95% CI: 28-41%) in Amhara region, 31% (95% CI: 19-43%) in Oromia region and 10% (95% CI: 7-12%) in Tigray region. Soil-transmitted helminths infection rate has been decreasing from 44% (95% CI: 30-57%) pre-Mass Drug Administration (MDA) era (1997-2012) to 30% (95% CI: 25-34%) post-MDA (2013-2020), although statistically not significant (p = 0.45). A lumbricoides was the predominant species with a prevalence of 17%. CONCLUSION: Southern Nations Nationalities and Peoples Region, Amhara, and Oromia regions carry the highest-burden and are categorized to Moderate Risk Zones (MRZ) and therefore, requiring MDA once annually with Albendazole or Mebendazole. The prevalence of STHs decreased after MDA compared to before MDA, but the decline was not statistically significant. A. lumbricoides was the predominant species of STHs among preschool and school-age children in Ethiopia. The high prevalence of STHs observed in this review, underscores the need for better control and prevention strategies in Ethiopia.

Multidrug resistant tuberculosis treatment outcome in children in developing and developed countries: A systematic review and meta-analysis.

BACKGROUND: We aimed to compare and contrast the proportions of treatment outcome between developing and developed countries in children treated for multidrug resistance tuberculosis (MDR-TB). METHODS: We conducted a systematic review and meta-analysis of articles published on children treated for MDR-TB. We searched published articles from electronic databases: PubMed/Medline, EMBASE, Scopus and Web of Science for English articles without restricting publication year. We employed random-effects meta-analysis model to estimate the pooled proportions of treatment success, death, treatment failure and lost to follow up. RESULTS: We pooled data of 1,343 children obtained from 17 included studies, and the overall pooled treatment success was 77.0% (95% Confidence Interval (CI), 69.0-85.0). Pooled treatment success in developing countries was 73.0% (63.0-83.0), while in developed countries 87.0% (81.0-94.0). The overall pooled treatment failure was 3.0% (1.0-6.0), while death 8.0% (4.0-11.0) and lost to follow up 10.0% (6.0-4). CONCLUSION: MDR-TB treatment success in children is well achieved in both developed and developing countries by currently available drugs. Improving MDR-TB treatment programme is vital to achieve the maximum treatment successful. Promoting research on pediatric MDR-TB treatment outcome could also help to fill evidence gap.

Developing a Prototype Knowledge-Based System for Diagnosis and Treatment of Diabetes Using Data Mining Techniques.

BACKGROUND: Diabetes is a disease that affects the body's ability to produce or use insulin. A total of 425 million people are suffering from diabetes in the world. Of this, more than 16 million people live in the Africa Region, which is estimated to be around 41 million by 2045. The main objective of this study was to design and develop a prototype knowledge-based system using data mining techniques for diagnosis and treatment of diabetes. METHODS: For this study, experimental research design was employed, and the researchers used domain expert knowledge as a supplement of data mining techniques whereby three classification algorithms in WEKA; namely J48, PART and JRip were used, and finally the researchers decided to use the results of J48 classification algorithm. Ultimate Visual basic studio 2013 (Vb.net) was used to store knowledge and as front side of prototype. Common lisp prolog (Clisp) was used for obtained knowledge back end coding. RESULTS: Using a decision tree algorithm; namely J48, 2512 (95.1515%) of the instances were classified correctly, and 128 (4.8485 %) were classified incorrectly. The second most performing model was generated by JRip Classier. This model scored the 94.7348% accuracy on the general data to classify the status of diabetic patient datasets. It classified the 2501 instances of the records correctly. CONCLUSION: The J48 model was the best performing model with the best accuracy of results.

Resistance of Mycobacterium tuberculosis strains to Rifampicin: A systematic review and meta-analysis.

INTRODUCTION: Antitubercular drug resistance strain is a horrifying barrier to effective TB treatment and prevention. The present study aimed to determine the prevalence and geographical distribution of rifampicin-resistance M. tuberculosis (MTB) strains. METHODS: We searched two electronic databases, PubMed and EMBASE, until 26 March 2017 and updated our search on 27 April 2018 and accessed all prevalence studies of MTB strain and their drug susceptibility patterns to rifampicin. The pooled prevalence estimate was determined using random effects model. RESULTS: We identified 23 studies satisfying the inclusion criteria. The proportion of rifampicin resistance strains was diverged depending on the type of strains, country and Regions. The pooled estimate of rifampicin-resistance strains of MTB for the included studies was 4% (95% CI: 3-5%). In subgroup analysis based on World Health Organization (WHO) Regions, the pooled estimate of rifampicin-resistance strains of MTB was 11% (95% CI: 9-13%) with the Western Pacific Region 24%, Europian Region 10%, South-East Asian Region 6%, African Region 3% and Region of American 1%. Beijing family was the most dominant strain resistance to rifampicin with pooled prevalence of 14% (95% CI: 10-18%). The pooled prevalence of other families, i.e. EAI, T, CAS, MANU, Haarlem, LAM and Ural, was ≤2% for each. CONCLUSION: High burden of rifampicin resistance MTB strains was identified in the Western Pacific Region. Of these, Beijing family was predominantly resistance to rifampicin in Western Pacific Region and South-East Asian Region and also spread to European Region and Region of American.

Knowledge Management Implementation and the Tools Utilized in Healthcare for Evidence-Based Decision Making: A Systematic Review.

BACKGROUND: Healthcare is a knowledge driven process and thus knowledge management and the tools to manage knowledge in healthcare sector are gaining attention. The aim of this systematic review is to investigate knowledge management implementation and knowledge management tools used in healthcare for informed decision making. METHODS: Three databases, two journals websites and Google Scholar were used as sources for the review. The key terms used to search relevant articles include: "Healthcare and Knowledge Management"; "Knowledge Management Tools in Healthcare" and "Community of Practices in healthcare". RESULTS: It was found that utilization of knowledge management in healthcare is encouraging. There exist numbers of opportunities for knowledge management implementation, though there are some barriers as well. Some of the opportunities that can transform healthcare are advances in health information and communication technology, clinical decision support systems, electronic health record systems, communities of practice and advanced care planning. CONCLUSION: Providing the right knowledge at the right time, i.e., at the point of decision making by implementing knowledge management in healthcare is paramount. To do so, it is very important to use appropriate tools for knowledge management and user-friendly system because it can significantly improve the quality and safety of care provided for patients both at hospital and home settings.

Prevalence of and risk factors for multidrug-resistant tuberculosis in Iran and its neighboring countries: systematic review and meta-analysis.

Tuberculosis, in particular drug-resistant tuberculosis, is of global concern due to the high mortality and morbidity associated with it annually. The aim of this study was to determine the prevalence of and the risk factors for multidrug-resistant tuberculosis in Iran and its neighboring countries. Four databases (PubMed, BioMed Central, EMBASE, and Web of Science) were searched using key terms. Nineteen eligible articles were identified, of which 12 and seven were used for quantitative and qualitative analysis, respectively. The overall pooled estimate of the prevalence of multidrug-resistant tuberculosis, including both new and previously treated tuberculosis cases, in Iran, Iraq, Turkey and Pakistan was 16% (95% confidence interval [CI] 11-20). The patients with a previous tuberculosis treatment history (odds ratio [OR] = 6.45; 95% CI 5.12-7.79), those aged <45 years (OR = 1.57; 95% CI 1.12-2.03), and those who were males (OR = 1.83; 95% CI 1.19-2.48) had an increased pool risk of developing multidrug-resistant tuberculosis. The forest plot revealed that the pooled odds for the development of multidrug- resistant tuberculosis were 2.01 (95% CI 1.65-2.36). Poor adherence to treatment was one of the predictors of unsuccessful treatment outcomes. Multidrug-resistant tuberculosis is a great concern for public health programs in many countries globally, including those included in this review. The risk factors for the development of multidrug-resistant tuberculosis, specifically a previous tuberculosis treatment history, should be targeted through the implementation of specialized interventions.

Prevalence of and risk factors for multidrug-resistant tuberculosis in Iran and its neighboring countries: systematic review and meta-analysis

Abstract Tuberculosis, in particular drug-resistant tuberculosis, is of global concern due to the high mortality and morbidity associated with it annually. The aim of this study was to determine the prevalence of and the risk factors for multidrug-resistant tuberculosis in Iran and its neighboring countries. Four databases (PubMed, BioMed Central, EMBASE, and Web of Science) were searched using key terms. Nineteen eligible articles were identified, of which 12 and seven were used for quantitative and qualitative analysis, respectively. The overall pooled estimate of the prevalence of multidrug-resistant tuberculosis, including both new and previously treated tuberculosis cases, in Iran, Iraq, Turkey and Pakistan was 16% (95% confidence interval [CI] 11-20). The patients with a previous tuberculosis treatment history (odds ratio [OR] = 6.45; 95% CI 5.12-7.79), those aged <45 years (OR = 1.57; 95% CI 1.12-2.03), and those who were males (OR = 1.83; 95% CI 1.19-2.48) had an increased pool risk of developing multidrug-resistant tuberculosis. The forest plot revealed that the pooled odds for the development of multidrug- resistant tuberculosis were 2.01 (95% CI 1.65-2.36). Poor adherence to treatment was one of the predictors of unsuccessful treatment outcomes. Multidrug-resistant tuberculosis is a great concern for public health programs in many countries globally, including those included in this review. The risk factors for the development of multidrug-resistant tuberculosis, specifically a previous tuberculosis treatment history, should be targeted through the implementation of specialized interventions.