Search

Objective: This study aimed to summarize the characteristics and methodological quality of systematic reviews on the application of artificial intelligence (AI) in clinical diagnosis and treatment. Methods: We systematically searched seven English- and Chinese-language literature databases to identify systematic reviews on the application of AI, deep learning, or machine learning in the diagnosis and treatment of any disease published in 2020. We evaluated the methodological quality of the included systematic reviews using “A Measurement tool for the assessment of multiple systematic reviews” (AMSTAR). We also conducted meta-analyses on the diagnostic accuracy of AI on selected disease categories with a large number of included studies and low clinical heterogeneity. Results: A total of 40 systematic reviews reporting 1,083 original studies were included, covering 31 diseases from 11 groups of diseases. Eleven systematic reviews were related to neoplasms and nine were systematic reviews related to diseases of the digestive system. We selected digestive system diseases for the meta-analysis. The pooled sensitivities (with 95% confidence interval (CI)) of AI to assist the diagnosis of helicobacter pylori, gastrointestinal ulcers, hemorrhage, esophageal tumors, gastric tumors, and intestinal tumors (with 95% CI) were 0.91 (0.83–0.95), 0.99 (0.76–1.00), 0.95 (0.83–0.99), 0.90 (0.85–0.93), 0.90 (0.82–0.95), and 0.93 (0.88–0.96), respectively, and the pooled specificities were 0.82 (0.77–0.87), 0.97 (0.86–1.00), 1.00 (0.99–1.00), 0.80 (0.71–0.87), 0.93 (0.87–0.97), and 0.89 (0.85–0.92), respectively. The AMSTAR items “the list of included studies” (n = 39, 97.5%) and “the characteristics of the included studies” (n = 39, 97.5%) had the highest compliance among the reviews; the compliance was relatively low to the items “the consideration of publication status” (n = 1, 2.5%), “the consideration of scientific quality” (n = 19, 47.5%), “data synthesis methods” (n = 18, 45.0%), and “ the evaluation of publication bias” (n = 13, 32.5%). Conclusions: The main subjects of systematic reviews on AI applications in clinical diagnosis and treatment published in 2020 were diseases of the digestive system and neoplasms. The methodological quality of the systematic reviews on AI needs to be improved, paying particular attention to publication bias and the rigorous evaluation of the quality of the included studies.

Aim: The study aimed to evaluate the reliability and usability of the CARE‐Radiology checklist in assessing radiological case reports and provide a basis for its broader adoption and optimization. Methods: Ten randomly selected radiological case reports published in scientific journals in 2020 were evaluated using the CARE‐Radiology checklist. Twenty‐six experts from 10 countries were invited to independently assess all ten reports. The reliability of the checklist was measured using Fleiss' Kappa, and Cronbach's alpha coefficient. Usability was evaluated by recording the time taken to complete the assessments and requesting the evaluators to rate each item on a Likert scale for its easiness of use. Results: The median time for evaluating one radiological case report was 15 min. The overall agreement among evaluators showed moderate reliability with a Kappa value of 0.47 and a Cronbach's alpha of 0.51. The mean compliance rate for the items of CARE‐Radiology was 61.8%, with some items exceeding 90% compliance. Items related to abstracts and keywords had the lowest compliance rates. The evaluators found most items easy to understand, with a few exceptions. Conclusions: The CARE‐Radiology checklist is relatively easy for researchers to use and understand. Continuous feedback is necessary for future revisions and updates, to enhance the effectiveness of the checklist, and to improve user experience. [ABSTRACT FROM AUTHOR]

Contact tracing is the process by which persons who are believed to have come into contact with a confirmed case-patient with an infectious disease during the infectious period are located [...]

Objective Complete and transparent reporting is of critical importance for randomized controlled trials (RCTs). The present study aimed to determine the reporting quality and methodological quality of RCTs for interventions involving artificial intelligence (AI) and their protocols.Methods We searched MEDLINE (via PubMed), Embase, Web of Science, CBMdisc, Wanfang Data, and CNKI from January 1, 2016, to November 11, 2020, to collect RCTs involving AI. We also extracted the protocol of each included RCT if it could be obtained. CONSORT-AI (Consolidated Standards of Reporting Trials–Artificial Intelligence) statement and Cochrane Collaboration's tool for assessing risk of bias (ROB) were used to evaluate the reporting quality and methodological quality, respectively, and SPIRIT-AI (The Standard Protocol Items: Recommendations for Interventional Trials–Artificial Intelligence) statement was used to evaluate the reporting quality of the protocols. The associations of the reporting rate of CONSORT-AI with the publication year, journal's impact factor (IF), number of authors, sample size, and first author's country were analyzed univariately using Pearson's chi-squared test, or Fisher's exact test if the expected values in any of the cells were below 5. The compliance of the retrieved protocols to SPIRIT-AI was presented descriptively.Results Overall, 29 RCTs and three protocols were considered eligible. The CONSORT-AI items “title and abstract” and “interpretation of results” were reported by all RCTs, with the items with the lowest reporting rates being “funding” (0), “implementation” (3.5%), and “harms” (3.5%). The risk of bias was high in 13 (44.8%) RCTs and not clear in 15 (51.7%) RCTs. Only one RCT (3.5%) had a low risk of bias. The compliance was not significantly different in terms of the publication year, journal's IF, number of authors, sample size, or first author's country. Ten of the 35 SPIRIT-AI items (funding, participant timeline, allocation concealment mechanism, implementation, data management, auditing, declaration of interests, access to data, informed consent materials and biological specimens) were not reported by any of the three protocols.Conclusions The reporting and methodological quality of RCTs involving AI need to be improved. Because of the limited availability of protocols, their quality could not be fully judged. Following the CONSORT-AI and SPIRIT-AI statements and with appropriate guidance on the risk of bias when designing and reporting AI-related RCTs can promote standardization and transparency.

Guideline writers have a responsibility to generate recommendations that are both evidence-based and free of bias. How best to quantify and report potential conflicts has been unclear. This extension of the Reporting Items for practice Guidelines in HealThcare (RIGHT) checklist provides a checklist-based approach to reviewing, assessing, and reporting conflicts of interest for guideline-writing bodies. Background: Conflicts of interest (COIs) of contributors to a guideline project and the funding of that project can influence the development of the guideline. Comprehensive reporting of information on COIs and funding is essential for the transparency and credibility of guidelines. Objective: To develop an extension of the Reporting Items for practice Guidelines in HealThcare (RIGHT) statement for the reporting of COIs and funding in policy documents of guideline organizations and in guidelines: the RIGHT-COI&F checklist. Design: The recommendations of the Enhancing the QUAlity and Transparency Of health Research (EQUATOR) network were followed. The process consisted of registration of the project and setting up working groups, generation of the initial list of items, achieving consensus on the items, and formulating and testing the final checklist. Setting: International collaboration. Participants: 44 experts. Measurements: Consensus on checklist items. Results: The checklist contains 27 items: 18 about the COIs of contributors and 9 about the funding of the guideline project. Of the 27 items, 16 are labeled as policy related because they address the reporting of COI and funding policies that apply across an organization's guideline projects. These items should be described ideally in the organization's policy documents, otherwise in the specific guideline. The remaining 11 items are labeled as implementation related and they address the reporting of COIs and funding of the specific guideline. Limitation: The RIGHT-COI&F checklist requires testing in real-life use. Conclusion: The RIGHT-COI&F checklist can be used to guide the reporting of COIs and funding in guideline development and to assess the completeness of reporting in published guidelines and policy documents. Primary Funding Source: The Fundamental Research Funds for the Central Universities of China. [ABSTRACT FROM AUTHOR]

Objective: As a large and populous country, China releases a high number of diagnostic criteria. However, the published diagnostic criteria have not yet been systematically analyzed. Therefore, the aim of this study is to investigate the characteristics, development methods, reporting quality, and evidence basis of diagnostic criteria published in China. Methods: We searched five databases for diagnostic criteria from their inception until July 31, 2023. All diagnostic criteria were screened through abstract and full‐text reading, and included if satisfying the prespecified criteria. Two researchers independently extracted data on the characteristics, development methods, reporting quality, and evidence basis of diagnostic criteria. Results: A total of 143 diagnostic criteria were included. In terms of development methods, the proportions of diagnostic criteria that involved a systematic literature search (n = 2; 1.4%; 95% confidence interval (CI), 0.4% to 5.0%), adoption of formal consensus methods (n = 4; 2.8%; 95% CI, 1.1% to 7.0%), and criteria validation (n = 9; 6.3%; 95% CI, 3.3% to 11.5%) were relatively low. Regarding reporting quality, the average compliance with the ACCORD checklist was 5.1%; none of the diagnostic criteria reported on registration, expert inclusion criteria, expert recruitment process, or consensus results. A majority (58.7%; 95% CI, 50.6% to 66.5%) of criteria did not cite any research, and only one (0.7%; 95% CI, 0.1% to 3.9%) criterion was derived from a systematic review. Moreover, only 16.1% (95% CI, 11.0% to 23.0%) of diagnostic criteria used evidence from the Chinese population. Conclusion: The diagnostic criteria developed in China exhibit serious flaws, particularly in evidence retrieval, formation of expert panels, consensus methods, and validation. Additionally, only few diagnostic criteria used a systematic synthesis of the evidence or evidence from the China. There is an urgent need to enhance the methodology for developing diagnostic criteria. [ABSTRACT FROM AUTHOR]

Introduction: Within many sub-Saharan African countries including Malawi, HIV prevalence varies widely between regions. This variability may be related to the distribution of population groups with specific sociobehavioural characteristics that influence the transmission of HIV and the uptake of prevention. In this study we intended to identify groups of people in Malawi with similar risk profiles. Methods: We used data from the Demographic and Health Survey in Malawi (2015 to 2016), and stratified the analysis by sex. We considered demographic, socio-behavioural and HIV-related variables. Using Latent Class Analysis (LCA), we identified groups of people sharing common sociobehavioural characteristics. The optimal number of classes (groups) was selected based on the Bayesian information criterion. We compared the proportions of individuals belonging to the different groups across the three regions and 28 districts of Malawi. Results: We found nine groups of women and six groups of men. Most women in the groups with highest risk of being HIV positive were living in female-headed households and were formerly married or in a union. Among men, older men had the highest risk of being HIV positive, followed by young (20 to 25) single men. Generally, low HIV testing uptake correlated with lower risk of having HIV. However, rural adolescent girls had a low probability of being tested (48.7%) despite a relatively high HIV prevalence. Urban districts and the Southern region had a higher percentage of high-prevalence and less tested groups of individuals than other areas. Conclusions: LCA is an efficient method to find groups of people sharing common HIV risk profiles, identify particularly vulnerable sub-populations, and plan targeted interventions focusing on these groups. Tailored support, prevention and HIV testing programmes should focus particularly on female household heads, adolescent girls living in rural areas, older married men and young men who have never been married. Keywords: latent class analysis; HIV prevalence; HIV testing; risk groups; spatial distribution; Malawi Additional information may be found under the Supporting Information tab for this article., 1 | INTRODUCTION Diagnosis of HIV-positive people is a critical step to improve access to treatment and control the HIV epidemic. In Eastern and Southern Africa, where HIV prevalence is [...]

Introduction: Socio-behavioural factors may contribute to the wide variance in HIV prevalence between and within sub-Saharan African (SSA) countries. We studied the associations between socio-behavioural variables potentially related to the risk of acquiring HIV. Methods: We used Bayesian network models to study associations between socio-behavioural variables that may be related to HIV. A Bayesian network consists of nodes representing variables, and edges representing the conditional dependencies between variables. We analysed data from Demographic and Health Surveys conducted in 29 SSA countries between 2010 and 2016. We predefined and dichotomized 12 variables, including factors related to age, literacy, HIV knowledge, HIV testing, domestic violence, sexual activity and women's empowerment. We analysed data on men and women for each country separately and then summarized the results across the countries. We conducted a second analysis including also the individual HIV status in a subset of 23 countries where this information was available. We presented summary graphs showing associations that were present in at least six countries (five in the analysis with HIV status). Results: We analysed data from 190,273 men (range across countries 2295 to 17,359) and 420,198 women (6621 to 38,948). The two variables with the highest total number of edges in the summary graphs were literacy and rural/urban location. Literacy was negatively associated with false beliefs about AIDS and, for women, early sexual initiation, in most countries. Literacy was also positively associated with ever being tested for HIV and the belief that women have the right to ask their husband to use condoms if he has a sexually transmitted infection. Rural location was positively associated with false beliefs about HIV and the belief that beating one's wife is justified, and negatively associated with having been tested for HIV. In the analysis including HIV status, being HIV positive was associated with female-headed household, older age and rural location among women, and with no variables among men. Conclusions: Literacy and urbanity were strongly associated with several factors that are important for HIV acquisition. Since literacy is one of the few variables that can be improved by interventions, this makes it a promising intervention target. Keywords: HIV epidemiology; risk factors; Africa; Bayesian network; graphical model; demographic and health surveys (DHS); socio-behavioural factors, 1 | INTRODUCTION In sub-Saharan Africa, about 26 million people were living with HIV in 2018 [1]. HIV prevalence is high overall, but very heterogeneous between countries, ranging from under [...]

Background: Female sex workers (FSWs) are at high risk for HIV infection and face unique barriers to receiving and adhering to testing and treatment. Early viral suppression and consistent viral load testing are critical to optimizing health and reducing transmission in this population. However, the factors associated with testing and successful viral suppression among FSWs are poorly understood, especially in Sub-Saharan Africa. Our study aimed to examine factors, including social, demographic, and clinical characteristics, associated with viral load testing and suppression among female sex workers initiating antiretroviral therapy in Nigeria. Methods: In this retrospective study, we analyzed routine programmatic data from FSWs enrolled in the National HIV Key Populations (KP) program in Nigeria. We included FSWs who were newly diagnosed with HIV and registered between January 2016 and January 2022. Primary outcomes of interest were a), receiving a viral load test at any point after treatment initiation and b), viral suppression (<1000 copies/ml) at the test closest to 6 months after treatment initiation. To identify factors associated with the outcomes of interest, we used univariable and multivariable logistic regression, with random intercepts for care facilities, and multiple imputation for missing values. Findings: Out of 34,976 FSWs, 97.1% (n = 33,945) received at least one viral load test, with 94.5% (n = 32,092) indicating viral suppression. The odds of receiving at least one viral load test were higher for those who entered treatment in more recent years, those with formal education and those with advanced HIV stages at baseline (adjusted odds ratios [aOR]: 1.17 [1.14–1.19] for those who entered treatment in 2020 vs. 2016; 1.02 [1.01–1.03] for post-secondary vs. no education; and 1.05 [1.01–1.10] for WHO clinical stage 3/4 vs. stage 1 respectively). The odds of successful viral suppression were higher for those who entered treatment in more recent years, but lower for those with advanced HIV stages at baseline (aOR: 1.13 [1.09–1.18] for 2022 vs. 2016; and 0.92 [0.87–0.98] for WHO clinical stage 3/4 vs. stage 1 respectively). Conclusions: The study underscored the relevance of timely diagnosis and ART initiation for optimal outcomes among HIV-positive FSWs in Nigeria. We also observed significant improvements in the likelihood of early viral load testing and suppression over the study period, reflecting advancements in the KP program. Further research should clarify factors driving these trends to further strengthen the HIV care pipeline for female sex workers. [ABSTRACT FROM AUTHOR]

Objective To analyse the epidemiological trends of tuberculosis in the Siberian and Far Eastern federal districts, the areas with the highest disease burden in the Russian Federation. Methods We applied principal coordinate analysis to study a total of 68 relevant variables on tuberculosis epidemiology, prevention and control. Data on these variables were collected over 2003-2016 in all 21 regions of the Siberian federal district and Far Eastern federal district (total population: 25.5 million) through the federal and departmental reporting system. We identified the regions with a favourable or unfavourable tuberculosis epidemiological profile and ranked them as low or high priority for specific interventions. Findings The median number of tuberculosis notifications in the regions was 123.3 per 100 000 population (range: 54.5-265.7) in 2003, decreasing to 82.3 per 100 000 (range: 52.9-178.3) in 2016. We found large variations in the tuberculosis epidemiological profile across different regions. The principal coordinate analysis revealed that three aggregated indicators accounted for 55% of the variation. The first coordinate corresponded to tuberculosis prevalence and case notifications in the regions; the second to the severity of the disease among patients; and the third to the percentage of multidrug-resistant tuberculosis among tuberculosis patients. The regions where intervention was most urgently needed were Chukotka Autonomous Okrug, Jewish Autonomous Oblast and Tyva Republic. Conclusion The variability in tuberculosis epidemiology across regions was likely due to differences in the quality of antituberculosis services. Precision in defining necessary interventions, as determined through the principal coordinate analysis approach, can guide focused tuberculosis control efforts. Objectif Analyser les tendances epidemiologiques de la tuberculose dans le district federal siberien et le district federal extreme-oriental, qui presentent la charge de morbidite la plus elevee au sein de la Federation de Russie. Methodes Nous avons applique une analyse en coordonnees principales pour etudier un total de 68 variables pertinentes sur l'epidemiologie, la prevention et le controle de la tuberculose. Des donnees sur ces variables ont ete collectees entre 2003 et 2016 dans les 21 regions du district federal siberien et du district federal extreme-oriental (population totale: 25,5 millions) a l'aide du systeme de notification federal et ministeriel. Nous avons determine les regions presentant un profil epidemiologique de la tuberculose favorable ou defavorable, puis nous les avons assimilees a un degre de priorite faible ou eleve concernant des interventions specifiques. Resultats Le nombre median de notifications de cas de tuberculose dans les regions considerees s'elevait a 123,3 pour 100 000 habitants (etendue: 54,5-265,7) en 2003, puis diminuait pour atteindre 82,3 pour 100 000 habitants (etendue: 52,9-178,3) en 2016. Nous avons constate d'importantes variations du profil epidemiologique de la tuberculose entre les differentes regions. L'analyse en coordonnees principales a revele que trois indicateurs agreges contribuaient pour 55% aux variations. La premiere coordonnee correspondait a la prevalence et aux notifications de cas de tuberculose dans les regions considerees; la deuxieme correspondait a la gravite de la maladie chez les patients atteints; et la troisieme correspondait au pourcentage de tuberculose multiresistante chez les patients atteints. Les regions ou les interventions etaient les plus urgentes etaient le district autonome de Tchoukotka, l'oblast autonome juif et la Republique de Touva. Conclusion La variability de l'epidemiologie de la tuberculose entre les regions etait probablement due a des differences dans la qualite des services antituberculeux. Il peut etre utile de definir precisement les interventions necessaires, comme determine a l'aide de la methode d'analyse en coordonnees principales, pour orienter les efforts de lutte contre la tuberculose. Objetivo Analizar las tendencias epidemiologicas de la tuberculosis en los distritos federales de Siberia y Extremo Oriente, las zonas con mayor carga de morbilidad de la Federacion de Rusia. Metodos Se aplico el analisis de coordenadas principales para estudiar un total de 68 variables relevantes en epidemiologia, prevencion y control de la tuberculosis. Los datos sobre estas variables se recopilaron entre 2003 y 2016 en las 21 regiones del distrito federal de Siberia y del distrito federal del Extremo Oriente (poblacion total: 25,5 millones) a traves del sistema de presentacion de informes federal y departamental. Se identificaron las regiones con un perfil epidemiologico favorable o desfavorable de la tuberculosis y se clasificaron como de baja o alta prioridad para intervenciones especificas. Resultados El numero promedio de notificaciones de tuberculosis en las regiones fue de 123,3 por cada 100 000 habitantes (rango: 54,5265,7) en 2003, disminuyendo a 82,3 por cada 100 000 habitantes (rango: 52,9-178,3) en 2016. Se encontraron notables variaciones en el perfil epidemiologico de la tuberculosis entre las diferentes regiones. El analisis de las coordenadas principales revelo que tres indicadores agregados representaban el 55 % de la variacion. La primera coordenada correspondia a la prevalencia de la tuberculosis y las notificaciones de casos en las regiones; la segunda a la gravedad de la enfermedad entre los pacientes; y la tercera al porcentaje de tuberculosis multirresistente entre los pacientes con tuberculosis. Las regiones en las que la intervencion era mas urgente eran el Distrito Autonomo de Chukotka, la Provincia Autonoma Hebrea y la Republica de Tyva. Conclusion La variabilidad en la epidemiologia de la tuberculosis entre regiones se debio probablemente a las diferencias den la calidad de los servicios de tratamiento antituberculoso. La precision en la definicion de las intervenciones necesarias, determinada a traves del enfoque de analisis de coordenadas principales, puede guiar los esfuerzos focalizados de control de la tuberculosis., Introduction During the 1990s the tuberculosis epidemic in the Russian Federation worsened due to an economic recession in the country at that time. National tuberculosis case notifications reached a peak [...]

Introduction: With limited funds available, meeting global health targets requires countries to both mobilize and prioritize their health spending. Within this context, countries have recognized the importance of allocating funds for HIV as efficiently as possible to maximize impact. Over the past six years, the governments of 23 countries in Africa, Asia, Eastern Europe and Latin America have used the Optima HIV tool to estimate the optimal allocation of HIV resources. Methods: Each study commenced with a request by the national government for technical assistance in conducting an HIV allocative efficiency study using Optima HIV. Each study team validated the required data, calibrated the Optima HIV epidemic model to produce HIV epidemic projections, agreed on cost functions for interventions, and used the model to calculate the optimal allocation of available funds to best address national strategic plan targets. From a review and analysis of these 23 country studies, we extract common themes around the optimal allocation of HIV funding in different epidemiological contexts. Results and discussion: The optimal distribution of HIV resources depends on the amount of funding available and the characteristics of each country's epidemic, response and targets. Universally, the modelling results indicated that scaling up treatment coverage is an efficient use of resources. There is scope for efficiency gains by targeting the HIV response towards the populations and geographical regions where HIV incidence is highest. Across a range of countries, the model results indicate that a more efficient allocation of HIV resources could reduce cumulative new HIV infections by an average of 18% over the years to 2020 and 25% over the years to 2030, along with an approximately 25% reduction in deaths for both timelines. However, in most countries this would still not be sufficient to meet the targets of the national strategic plan, with modelling results indicating that budget increases of up to 185% would be required. Conclusions: Greater epidemiological impact would be possible through better targeting of existing resources, but additional resources would still be required to meet targets. Allocative efficiency models have proven valuable in improving the HIV planning and budgeting process. Keywords: HIV modeling; allocative efficiency; cost-effectiveness; optimal HIV investment; resource allocation; resource needs, 1 | INTRODUCTION If decisions on the allocation of health resources were guided by the principals of health economics alone, funds would be allocated in ways intended to lead to [...]