Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews.

BACKGROUND: Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people's health. It is necessary to assess the current status on the application of AI towards the improvement of people's health in the domains defined by WHO's Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges. OBJECTIVE: To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people's health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality. METHODS: A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO's PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist. RESULTS: The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews. CONCLUSION: Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

Digital Data Sources and Their Impact on People's Health: A Systematic Review of Systematic Reviews.

Background: Digital data sources have become ubiquitous in modern culture in the era of digital technology but often tend to be under-researched because of restricted access to data sources due to fragmentation, privacy issues, or industry ownership, and the methodological complexity of demonstrating their measurable impact on human health. Even though new big data sources have shown unprecedented potential for disease diagnosis and outbreak detection, we need to investigate results in the existing literature to gain a comprehensive understanding of their impact on and benefits to human health. Objective: A systematic review of systematic reviews on identifying digital data sources and their impact area on people's health, including challenges, opportunities, and good practices. Methods: A multidatabase search was performed. Peer-reviewed papers published between January 2010 and November 2020 relevant to digital data sources on health were extracted, assessed, and reviewed. Results: The 64 reviews are covered by three domains, that is, universal health coverage (UHC), public health emergencies, and healthier populations, defined in WHO's General Programme of Work, 2019-2023, and the European Programme of Work, 2020-2025. In all three categories, social media platforms are the most popular digital data source, accounting for 47% (N = 8), 84% (N = 11), and 76% (N = 26) of studies, respectively. The second most utilized data source are electronic health records (EHRs) (N = 13), followed by websites (N = 7) and mass media (N = 5). In all three categories, the most studied impact of digital data sources is on prevention, management, and intervention of diseases (N = 40), and as a tool, there are also many studies (N = 10) on early warning systems for infectious diseases. However, they could also pose health hazards (N = 13), for instance, by exacerbating mental health issues and promoting smoking and drinking behavior among young people. Conclusions: The digital data sources presented are essential for collecting and mining information about human health. The key impact of social media, electronic health records, and websites is in the area of infectious diseases and early warning systems, and in the area of personal health, that is, on mental health and smoking and drinking prevention. However, further research is required to address privacy, trust, transparency, and interoperability to leverage the potential of data held in multiple datastores and systems. This study also identified the apparent gap in systematic reviews investigating the novel big data streams, Internet of Things (IoT) data streams, and sensor, mobile, and GPS data researched using artificial intelligence, complex network, and other computer science methods, as in this domain systematic reviews are not common.

Impact of Big Data Analytics on People's Health: Overview of Systematic Reviews and Recommendations for Future Studies.

BACKGROUND: Although the potential of big data analytics for health care is well recognized, evidence is lacking on its effects on public health. OBJECTIVE: The aim of this study was to assess the impact of the use of big data analytics on people's health based on the health indicators and core priorities in the World Health Organization (WHO) General Programme of Work 2019/2023 and the European Programme of Work (EPW), approved and adopted by its Member States, in addition to SARS-CoV-2-related studies. Furthermore, we sought to identify the most relevant challenges and opportunities of these tools with respect to people's health. METHODS: Six databases (MEDLINE, Embase, Cochrane Database of Systematic Reviews via Cochrane Library, Web of Science, Scopus, and Epistemonikos) were searched from the inception date to September 21, 2020. Systematic reviews assessing the effects of big data analytics on health indicators were included. Two authors independently performed screening, selection, data extraction, and quality assessment using the AMSTAR-2 (A Measurement Tool to Assess Systematic Reviews 2) checklist. RESULTS: The literature search initially yielded 185 records, 35 of which met the inclusion criteria, involving more than 5,000,000 patients. Most of the included studies used patient data collected from electronic health records, hospital information systems, private patient databases, and imaging datasets, and involved the use of big data analytics for noncommunicable diseases. "Probability of dying from any of cardiovascular, cancer, diabetes or chronic renal disease" and "suicide mortality rate" were the most commonly assessed health indicators and core priorities within the WHO General Programme of Work 2019/2023 and the EPW 2020/2025. Big data analytics have shown moderate to high accuracy for the diagnosis and prediction of complications of diabetes mellitus as well as for the diagnosis and classification of mental disorders; prediction of suicide attempts and behaviors; and the diagnosis, treatment, and prediction of important clinical outcomes of several chronic diseases. Confidence in the results was rated as "critically low" for 25 reviews, as "low" for 7 reviews, and as "moderate" for 3 reviews. The most frequently identified challenges were establishment of a well-designed and structured data source, and a secure, transparent, and standardized database for patient data. CONCLUSIONS: Although the overall quality of included studies was limited, big data analytics has shown moderate to high accuracy for the diagnosis of certain diseases, improvement in managing chronic diseases, and support for prompt and real-time analyses of large sets of varied input data to diagnose and predict disease outcomes. TRIAL REGISTRATION: International Prospective Register of Systematic Reviews (PROSPERO) CRD42020214048; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=214048.

The Impact of mHealth Interventions: Systematic Review of Systematic Reviews.

BACKGROUND: Mobile phone usage has been rapidly increasing worldwide. mHealth could efficiently deliver high-quality health care, but the evidence supporting its current effectiveness is still mixed. OBJECTIVE: We performed a systematic review of systematic reviews to assess the impact or effectiveness of mobile health (mHealth) interventions in different health conditions and in the processes of health care service delivery. METHODS: We used a common search strategy of five major scientific databases, restricting the search by publication date, language, and parameters in methodology and content. Methodological quality was evaluated using the Measurement Tool to Assess Systematic Reviews (AMSTAR) checklist. RESULTS: The searches resulted in a total of 10,689 articles. Of these, 23 systematic reviews (371 studies; more than 79,665 patients) were included. Seventeen reviews included studies performed in low- and middle-income countries. The studies used diverse mHealth interventions, most frequently text messaging (short message service, SMS) applied to different purposes (reminder, alert, education, motivation, prevention). Ten reviews were rated as low quality (AMSTAR score 0-4), seven were rated as moderate quality (AMSTAR score 5-8), and six were categorized as high quality (AMSTAR score 9-11). A beneficial impact of mHealth was observed in chronic disease management, showing improvement in symptoms and peak flow variability in asthma patients, reducing hospitalizations and improving forced expiratory volume in 1 second; improving chronic pulmonary diseases symptoms; improving heart failure symptoms, reducing deaths and hospitalization; improving glycemic control in diabetes patients; improving blood pressure in hypertensive patients; and reducing weight in overweight and obese patients. Studies also showed a positive impact of SMS reminders in improving attendance rates, with a similar impact to phone call reminders at reduced cost, and improved adherence to tuberculosis and human immunodeficiency virus therapy in some scenarios, with evidence of decrease of viral load. CONCLUSIONS: Although mHealth is growing in popularity, the evidence for efficacy is still limited. In general, the methodological quality of the studies included in the systematic reviews is low. For some fields, its impact is not evident, the results are mixed, or no long-term studies exist. Exceptions include the moderate quality evidence of improvement in asthma patients, attendance rates, and increased smoking abstinence rates. Most studies were performed in high-income countries, implying that mHealth is still at an early stage of development in low-income countries.

Availability of information in Public Health on the Internet: An analysis of national health authorities in the Spanish-speaking Latin American and Caribbean countries.

INTRODUCTION: Access to reliable and quality health information and appropriate medical advice can contribute to a dramatic reduction in the mortality figures of countries. The governments of the Americas are faced with the opportunity to continue working on this challenge, and their institutional presence on their websites should play a key role in this task. In a setting where the access to information is essential to both health professionals and citizens, it is relevant to analyze the role of national health authorities. Given that search engines play such a key role in the access to health information, it is important to specifically know - in connection to national health authorities - whether health information offered is easily available to the population, and whether this information is well-ranked in search engines. METHODS: Quantitative methods were used to gather data on the institutional presence of national health authorities on the web. An exploratory and descriptive research served to analyze and interpret data and information obtained quantitatively from different perspectives, including an analysis by country, and also by leading causes of death. A total of 18 web pages were analyzed. Information on leading causes of death was searched on websites of national health authorities in the week of August 10-14, 2015. RESULTS: The probability of finding information of national health authorities on the 10 leading causes of death in a country, among the top 10 results on Google, is 6.66%. Additionally, ten out the 18 countries under study (55%) do not have information ranked among the top results in Google when searching for the selected terms. Additionally, a total of 33 websites represent the sources of information with the highest visibility for all the search strategies in each country on Google for the ten leading causes of death in a country. Two websites, the National Library of Medicine and Wikipedia, occur as a result with visibility in the total of eighteen countries of the sample. CONCLUSIONS: Taking into consideration that providing reliable and quality information on these topics to the population should be one of the priorities of national health authorities, these results suggest that national health authorities need to take measures to try to better position their contents.

Social media in public health: an analysis of national health authorities and leading causes of death in Spanish-speaking Latin American and Caribbean countries.

BACKGROUND: Information and communications technologies, like social media, have the potential to reduce some barriers in disease prevention and control in the Americas. National health authorities can use these technologies to provide access to reliable and quality health information. A study was conducted to analyze availability of information about the leading causes of death on social media channels of national health authorities in 18 Spanish-speaking Latin American and Caribbean countries. METHODS: We gathered data of national health authorities's institutional presence in social media. Exploratory-descriptive research was useful for analysis and interpretation of the data collected. An analysis was carried out for 6 months, from April 1 to September 30, 2015. RESULTS: Sixteen of the 18 countries studied have institutional presences on social media. National health authorities have a presence in an average of almost three platforms (2.8%). An average of 1% of the populations with Internet access across the 18 countries in this study follows national health authorities on social media (approximately, an average of 0.3% of the total population of the countries under study). On average, information on 3.2 of the 10 leading causes of death was posted on the national health authorities' Facebook pages, and information on 2.9 of the 10 leading causes of death was posted on their Twitter profiles. Additionally, regarding public health expenditures and the possibility of retrieving information on the leading causes of death, an apparent negative correlation exists in the case of Facebook, r(13) = -.54, P = .03 and a weak negative correlation in the case of Twitter, r(14) = -.26, P = .31, for the countries with presences in those networks. CONCLUSIONS: National health authorities can improve their role in participating in conversations on social media regarding the leading causes of death affecting their countries. Taking into account Internet accessibility levels in the countries under study and the high rates of people using social networks in even the poorest countries, further research is needed to provide evidence that more dedication to health promotion interventions through social media could significantly improve the impact and reach of public health messages and initiatives.

Infoxicación en salud. La sobrecarga de información sobre salud en la web y el riesgo de que lo importante se haga invisible / Infoxication in health. Health information overload on the Internet and the risk of important information becoming invisible / Infoxicação em saúde. A sobrecarga de informação em saúde na internet e o risco de ficar invisível o que é importante

RESUMEN Objetivo Este estudio tiene como objetivos 1) crear conciencia del volumen de información en salud existente en la web de calidad, 2) explorar la percepción de profesionales de la información con relación al uso de fuentes cualificadas en la toma de decisiones en salud, y 3) presentar recomendaciones que permitan fortalecer las capacidades de los trabajadores de la salud y las competencias institucionales relacionadas con la alfabetización digital. Métodos Se realizó un estudio no experimental descriptivo transversal con una muestra no probabilística de 32 profesionales de la información de nueve países. Se recopiló información de internet sobre el volumen de contenidos existentes en herramientas web, redes sociales y fuentes de información en salud. Se realizaron búsquedas en inglés y en español utilizando las palabras clave Ebola, Zika, Dengue, Chikungunya, Safe food, Health equity, Safe sex, y Obesit. Por último, se obtuvo información sobre la oferta de formación formal en temas de alfabetización digital, gestión de información y otros relacionados. Resultados Seleccionando sólo cuatro enfermedades de alto impacto en salud pública en mayo de 2016 y promediando un tiempo de revisión mínimo de cada producto de información, se tardaría más de 50 años seguidos sin dormir para consultar todo lo publicado en línea sobre Dengue, Zika, Ebola y Chikungunja. Conclusión Se concluye que la salud pública se beneficiaría con instituciones de salud que implementaran estrategias formales de gestión del conocimiento, con instituciones académicas de ciencias de la salud que incorporaran programas formales de alfabetización digital y con trabajadores de la salud cuyo desarrollo profesional sea responsable y funcional en la sociedad de la información.

ABSTRACT Objective The objectives of this study were to: 1) raise awareness of the volume of quality health information on the Internet; 2) explore perceptions of information professionals with regard to the use of qualified sources for health decision-making; and 3) make recommendations that facilitate strengthening health worker capacities and institutional competencies related to digital literacy. Methods A non-experimental, descriptive cross-sectional study was conducted with a non-probability sample of 32 information professionals from nine countries. Internet information was compiled on the volume of content in Internet tools, social networks, and health information sources. Searches in English and Spanish were carried out using the keywords Ebola, Zika, dengue, chikungunya, safe food, health equity, safe sex, and obesity. Finally, information was obtained on opportunities for formal education on the subjects of digital literacy, information management, and other related topics. Results Selecting only four diseases with a high impact on public health in May 2016 and averaging minimum review time for each information product, it would take more than 50 years without sleeping to consult everything that is published online about dengue, Zika, Ebola, and chikungunya. Conclusion We conclude that public health would benefit from: health institutions implementing formal knowledge management strategies; academic health sciences institutions incorporating formal digital literacy programs; and having health workers who are professionally responsible and functional in the information society.

RESUMO Objetivos 1) Conscientizar sobre o volume de informação em saúde de qualidade existente na internet, 2) explorar a percepção dos profissionais da informação sobre o uso de fontes qualificadas na tomada de decisão em saúde e 3) fazer recomendações para reforçar o preparo dos profissionais de saúde e as competências institucionais quanto à alfabetização digital. Métodos Foi realizado estudo transversal descritivo não experimental em uma amostra não probabilística com 32 profissionais da informação de nove países. Foi coletada informação da internet sobre o volume de conteúdos existentes sobre ferramentas de internet, redes sociais e fontes de informação em saúde. Foram realizadas buscas em inglês e espanhol utilizando as palavras-chave Ebola, Zika, Dengue, Chikungunya, Safe food, Health equity, Safe sex, e Obesity. E foi obtida informação sobre a oferta de cursos de formação em alfabetização digital, gestão da informação e outros tópicos relacionados. Resultados Com a seleção de apenas quatro doenças de alto impacto em saúde pública em maio de 2016, com tempo de revisão médio mínimo para cada produto de informação, seriam necessários mais de 50 anos contínuos, sem intervalo para dormir, para consultar todo o conteúdo publicado online sobre dengue, zika, Ebola e chikungunya. Conclusão Conclui-se que existiria benefício para a saúde pública se as instituições de saúde implementassem estratégias formais de gestão do conhecimento, as instituições acadêmicas de ciências da saúde incorporassem programas formais de alfabetização digital e os profissionais de saúde investissem em desenvolvimento profissional responsável e prático na sociedade da informação.