Research ethics and artificial intelligence for global health: perspectives from the global forum on bioethics in research.

BACKGROUND: The ethical governance of Artificial Intelligence (AI) in health care and public health continues to be an urgent issue for attention in policy, research, and practice. In this paper we report on central themes related to challenges and strategies for promoting ethics in research involving AI in global health, arising from the Global Forum on Bioethics in Research (GFBR), held in Cape Town, South Africa in November 2022. METHODS: The GFBR is an annual meeting organized by the World Health Organization and supported by the Wellcome Trust, the US National Institutes of Health, the UK Medical Research Council (MRC) and the South African MRC. The forum aims to bring together ethicists, researchers, policymakers, research ethics committee members and other actors to engage with challenges and opportunities specifically related to research ethics. In 2022 the focus of the GFBR was "Ethics of AI in Global Health Research". The forum consisted of 6 case study presentations, 16 governance presentations, and a series of small group and large group discussions. A total of 87 participants attended the forum from 31 countries around the world, representing disciplines of bioethics, AI, health policy, health professional practice, research funding, and bioinformatics. In this paper, we highlight central insights arising from GFBR 2022. RESULTS: We describe the significance of four thematic insights arising from the forum: (1) Appropriateness of building AI, (2) Transferability of AI systems, (3) Accountability for AI decision-making and outcomes, and (4) Individual consent. We then describe eight recommendations for governance leaders to enhance the ethical governance of AI in global health research, addressing issues such as AI impact assessments, environmental values, and fair partnerships. CONCLUSIONS: The 2022 Global Forum on Bioethics in Research illustrated several innovations in ethical governance of AI for global health research, as well as several areas in need of urgent attention internationally. This summary is intended to inform international and domestic efforts to strengthen research ethics and support the evolution of governance leadership to meet the demands of AI in global health research.

Impact of tiered measures on social contact and mixing patterns of in Italy during the second wave of COVID-19.

BACKGROUND: Most countries around the world enforced non-pharmaceutical interventions against COVID-19. Italy was one of the first countries to be affected by the pandemic, imposing a hard lockdown, in the first epidemic wave. During the second wave, the country implemented progressively restrictive tiers at the regional level according to weekly epidemiological risk assessments. This paper quantifies the impact of these restrictions on contacts and on the reproduction number. METHODS: Representative (with respect to age, sex, and region of residence) longitudinal surveys of the Italian population were undertaken during the second epidemic wave. Epidemiologically relevant contact patterns were measured and compared with pre-pandemic levels and according to the level of interventions experienced by the participants. Contact matrices were used to quantify the reduction in the number of contacts by age group and contact setting. The reproduction number was estimated to evaluate the impact of restrictions on the spread of COVID-19. RESULTS: The comparison with the pre-pandemic baseline shows a significant decrease in the number of contacts, independently from the age group or contact settings. This decrease in the number of contacts significantly depends on the strictness of the non-pharmaceutical interventions. For all levels of strictness considered, the reduction in social mixing results in a reproduction number smaller than one. In particular, the impact of the restriction on the number of contacts decreases with the severity of the interventions. CONCLUSIONS: The progressive restriction tiers implemented in Italy reduced the reproduction number, with stricter interventions associated with higher reductions. Readily collected contact data can inform the implementation of mitigation measures at the national level in epidemic emergencies to come.

Behavioral Changes Associated With COVID-19 Vaccination: Cross-National Online Survey.

BACKGROUND: During the initial phases of the vaccination campaign worldwide, nonpharmaceutical interventions (NPIs) remained pivotal in the fight against the COVID-19 pandemic. In this context, it is important to understand how the arrival of vaccines affected the adoption of NPIs. Indeed, some individuals might have seen the start of mass vaccination campaigns as the end of the emergency and, as a result, relaxed their COVID-safe behaviors, facilitating the spread of the virus in a delicate epidemic phase such as the initial rollout. OBJECTIVE: The aim of this study was to collect information about the possible relaxation of protective behaviors following key events of the vaccination campaign in four countries and to analyze possible associations of these behavioral tendencies with the sociodemographic characteristics of participants. METHODS: We developed an online survey named "COVID-19 Prevention and Behavior Survey" that was conducted between November 26 and December 22, 2021. Participants were recruited using targeted ads on Facebook in four different countries: Brazil, Italy, South Africa, and the United Kingdom. We measured the onset of relaxation of protective measures in response to key events of the vaccination campaign, namely personal vaccination and vaccination of the most vulnerable population. Through calculation of odds ratios (ORs) and regression analysis, we assessed the strength of association between compliance with NPIs and sociodemographic characteristics of participants. RESULTS: We received 2263 questionnaires from the four countries. Participants reported the most significant changes in social activities such as going to a restaurant or the cinema and visiting relatives and friends. This is in good agreement with validated psychological models of health-related behavioral change such as the Health Belief Model, according to which activities with higher costs and perceived barriers (eg, social activities) are more prone to early relaxation. Multivariate analysis using a generalized linear model showed that the two main determinants of the drop of social NPIs were (1) having previously tested positive for COVID-19 (after the second vaccine dose: OR 2.46, 95% CI 1.73-3.49) and (2) living with people at risk (after the second vaccine dose: OR 1.57, 95% CI 1.22-2.03). CONCLUSIONS: This work shows that particular caution has to be taken during vaccination campaigns. Indeed, people might relax their safe behaviors regardless of the dynamics of the epidemic. For this reason, it is crucial to maintain high compliance with NPIs to avoid hindering the beneficial effects of the vaccine.

Detecting adherence to the recommended childhood vaccination schedule from user-generated content in a US parenting forum.

Vaccine hesitancy is considered as one of the leading causes for the resurgence of vaccine preventable diseases. A non-negligible minority of parents does not fully adhere to the recommended vaccination schedule, leading their children to be partially immunized and at higher risk of contracting vaccine preventable diseases. Here, we leverage more than one million comments of 201,986 users posted from March 2008 to April 2019 on the public online forum BabyCenter US to learn more about such parents. For 32% with geographic location, we find the number of mapped users for each US state resembling the census population distribution with good agreement. We employ Natural Language Processing to identify 6884 and 10,131 users expressing their intention of following the recommended and alternative vaccination schedule, respectively RSUs and ASUs. From the analysis of their activity on the forum we find that ASUs have distinctly different interests and previous experiences with vaccination than RSUs. In particular, ASUs are more likely to follow groups focused on alternative medicine, are two times more likely to have experienced adverse events following immunization, and to mention more serious adverse reactions such as seizure or developmental regression. Content analysis of comments shows that the resources most frequently shared by both groups point to governmental domains (.gov). Finally, network analysis shows that RSUs and ASUs communicate between each other (indicating the absence of echo chambers), however with the latter group being more endogamic and favoring interactions with other ASUs. While our findings are limited to the specific platform analyzed, our approach may provide additional insights for the development of campaigns targeting parents on digital platforms.

The impact of news exposure on collective attention in the United States during the 2016 Zika epidemic.

In recent years, many studies have drawn attention to the important role of collective awareness and human behaviour during epidemic outbreaks. A number of modelling efforts have investigated the interaction between the disease transmission dynamics and human behaviour change mediated by news coverage and by information spreading in the population. Yet, given the scarcity of data on public awareness during an epidemic, few studies have relied on empirical data. Here, we use fine-grained, geo-referenced data from three online sources-Wikipedia, the GDELT Project and the Internet Archive-to quantify population-scale information seeking about the 2016 Zika virus epidemic in the U.S., explicitly linking such behavioural signal to epidemiological data. Geo-localized Wikipedia pageview data reveal that visiting patterns of Zika-related pages in Wikipedia were highly synchronized across the United States and largely explained by exposure to national television broadcast. Contrary to the assumption of some theoretical epidemic models, news volume and Wikipedia visiting patterns were not significantly correlated with the magnitude or the extent of the epidemic. Attention to Zika, in terms of Zika-related Wikipedia pageviews, was high at the beginning of the outbreak, when public health agencies raised an international alert and triggered media coverage, but subsequently exhibited an activity profile that suggests nonlinear dependencies and memory effects in the relation between information seeking, media pressure, and disease dynamics. This calls for a new and more general modelling framework to describe the interaction between media exposure, public awareness and disease dynamics during epidemic outbreaks.

Towards a data-driven characterization of behavioral changes induced by the seasonal flu.

In this work, we aim to determine the main factors driving self-initiated behavioral changes during the seasonal flu. To this end, we designed and deployed a questionnaire via Influweb, a Web platform for participatory surveillance in Italy, during the 2017 - 18 and 2018 - 19 seasons. We collected 599 surveys completed by 434 users. The data provide socio-demographic information, level of concerns about the flu, past experience with illnesses, and the type of behavioral changes voluntarily implemented by each participant. We describe each response with a set of features and divide them in three target categories. These describe those that report i) no (26%), ii) only moderately (36%), iii) significant (38%) changes in behaviors. In these settings, we adopt machine learning algorithms to investigate the extent to which target variables can be predicted by looking only at the set of features. Notably, 66% of the samples in the category describing more significant changes in behaviors are correctly classified through Gradient Boosted Trees. Furthermore, we investigate the importance of each feature in the classification task and uncover complex relationships between individuals' characteristics and their attitude towards behavioral change. We find that intensity, recency of past illnesses, perceived susceptibility to and perceived severity of an infection are the most significant features in the classification task and are associated to significant changes in behaviors. Overall, the research contributes to the small set of empirical studies devoted to the data-driven characterization of behavioral changes induced by infectious diseases.

Risk factors associated with the incidence of self-reported COVID-19-like illness: data from a web-based syndromic surveillance system in the Netherlands.

During the first wave of the severe acute respiratory syndrome-coronavirus-2 epidemic in the Netherlands, notifications consisted mostly of patients with relatively severe disease. To enable real-time monitoring of the incidence of mild coronavirus disease 2019 (COVID-19) - for which medical consultation might not be required - the Infectieradar web-based syndromic surveillance system was launched in mid-March 2020. Our aim was to quantify associations between Infectieradar participant characteristics and the incidence of self-reported COVID-19-like illness. Recruitment for this cohort study was via a web announcement. After registering, participants completed weekly questionnaires, reporting the occurrence of a set of symptoms. The incidence rate of COVID-19-like illness was estimated and multivariable Poisson regression used to estimate the relative risks associated with sociodemographic variables, lifestyle factors and pre-existing medical conditions. Between 17 March and 24 May 2020, 25 663 active participants were identified, who reported 7060 episodes of COVID-19-like illness over 131 404 person-weeks of follow-up. The incidence rate declined over the analysis period, consistent with the decline in notified cases. Male sex, age 65+ years and higher education were associated with a significantly lower COVID-19-like illness incidence rate (adjusted rate ratios (RRs) of 0.80 (95% CI 0.76-0.84), 0.77 (0.70-0.85), 0.84 (0.80-0.88), respectively) and the baseline characteristics ever-smoker, asthma, allergies, diabetes, chronic lung disease, cardiovascular disease and children in the household were associated with a higher incidence (RRs of 1.11 (1.04-1.19) to 1.69 (1.50-1.90)). Web-based syndromic surveillance has proven useful for monitoring the temporal trends in, and risk factors associated with, the incidence of mild disease. Increased relative risks observed for several patient factors could reflect a combination of exposure risk, susceptibility to infection and propensity to report symptoms.

A computational framework for modeling and studying pertussis epidemiology and vaccination.

BACKGROUND: Emerging and re-emerging infectious diseases such as Zika, SARS, ncovid19 and Pertussis, pose a compelling challenge for epidemiologists due to their significant impact on global public health. In this context, computational models and computer simulations are one of the available research tools that epidemiologists can exploit to better understand the spreading characteristics of these diseases and to decide on vaccination policies, human interaction controls, and other social measures to counter, mitigate or simply delay the spread of the infectious diseases. Nevertheless, the construction of mathematical models for these diseases and their solutions remain a challenging tasks due to the fact that little effort has been devoted to the definition of a general framework easily accessible even by researchers without advanced modelling and mathematical skills. RESULTS: In this paper we describe a new general modeling framework to study epidemiological systems, whose novelties and strengths are: (1) the use of a graphical formalism to simplify the model creation phase; (2) the implementation of an R package providing a friendly interface to access the analysis techniques implemented in the framework; (3) a high level of portability and reproducibility granted by the containerization of all analysis techniques implemented in the framework; (4) a well-defined schema and related infrastructure to allow users to easily integrate their own analysis workflow in the framework. Then, the effectiveness of this framework is showed through a case of study in which we investigate the pertussis epidemiology in Italy. CONCLUSIONS: We propose a new general modeling framework for the analysis of epidemiological systems, which exploits Petri Net graphical formalism, R environment, and Docker containerization to derive a tool easily accessible by any researcher even without advanced mathematical and computational skills. Moreover, the framework was implemented following the guidelines defined by Reproducible Bioinformatics Project so it guarantees reproducible analysis and makes simple the developed of new user-defined workflows.

Spatial heterogeneity and socioeconomic determinants of opioid prescribing in England between 2015 and 2018.

BACKGROUND: Opioid overdoses have had a serious impact on the public health systems and socioeconomic welfare of several countries. Within this broader context, we focus our study on primary care opioid prescribing in England from 2015 to 2018, particularly the patterns of spatial variations at the community level and the socioeconomic and environmental factors that drive consumption. METHODS: Leveraging open data sources, we combine prescription records with aggregated data on patient provenance and build highly granular maps of Oral Morphine Equivalent (OME) prescribing rates for Lower Layer Super Output Areas (LSOA). We quantify the strength of spatial associations by means of the Empirical Bayes Index (EBI) that accounts for geographical variations in population density. We explore the interplay between socioeconomic and environmental determinants and prescribing rates by implementing a multivariate logistic regression model across different temporal snapshots and spatial scales. RESULTS: We observe, across time and geographical resolutions, a significant spatial association with the presence of localized hot and cold spots that group neighboring areas with homogeneous prescribing rates (e.g., EBI = 0.727 at LSOA level for 2018). Accounting for spatial dependency effects, we find that LSOA with both higher employment deprivation (OR = 62.6, CI 52.8-74.3) and a higher percentage of ethnically white (OR = 30.1, CI 25.4-35.7) inhabitants correspond to higher prescribing rates. Looking at educational attainment, we find LSOA with the prevalent degree of education being apprenticeship (OR = 2.33, CI 1.96-2.76) a risk factor and those with level 4+ (OR = 0.41, CI 0.35-0.48) a protective factor. Focusing on environmental determinants, housing (OR = 0.18, CI 0.15-0.21) and outdoor environment deprivation (OR = 0.62, CI 0.53-0.72) indices capture the bi-modal behavior observed in the literature concerning rural/urban areas. The results are consistent across time and spatial aggregations. CONCLUSIONS: Failing to account for local variations in opioid prescribing rates smooths out spatial dependency effects that result in underestimating/overestimating the impact on public health policies at the community level. Our study suggests a novel approach to inform more targeted interventions toward the most vulnerable population strata.

Unsupervised extraction of epidemic syndromes from participatory influenza surveillance self-reported symptoms.

Seasonal influenza surveillance is usually carried out by sentinel general practitioners (GPs) who compile weekly reports based on the number of influenza-like illness (ILI) clinical cases observed among visited patients. This traditional practice for surveillance generally presents several issues, such as a delay of one week or more in releasing reports, population biases in the health-seeking behaviour, and the lack of a common definition of ILI case. On the other hand, the availability of novel data streams has recently led to the emergence of non-traditional approaches for disease surveillance that can alleviate these issues. In Europe, a participatory web-based surveillance system called Influenzanet represents a powerful tool for monitoring seasonal influenza epidemics thanks to aid of self-selected volunteers from the general population who monitor and report their health status through Internet-based surveys, thus allowing a real-time estimate of the level of influenza circulating in the population. In this work, we propose an unsupervised probabilistic framework that combines time series analysis of self-reported symptoms collected by the Influenzanet platforms and performs an algorithmic detection of groups of symptoms, called syndromes. The aim of this study is to show that participatory web-based surveillance systems are capable of detecting the temporal trends of influenza-like illness even without relying on a specific case definition. The methodology was applied to data collected by Influenzanet platforms over the course of six influenza seasons, from 2011-2012 to 2016-2017, with an average of 34,000 participants per season. Results show that our framework is capable of selecting temporal trends of syndromes that closely follow the ILI incidence rates reported by the traditional surveillance systems in the various countries (Pearson correlations ranging from 0.69 for Italy to 0.88 for the Netherlands, with the sole exception of Ireland with a correlation of 0.38). The proposed framework was able to forecast quite accurately the ILI trend of the forthcoming influenza season (2016-2017) based only on the available information of the previous years (2011-2016). Furthermore, to broaden the scope of our approach, we applied it both in a forecasting fashion to predict the ILI trend of the 2016-2017 influenza season (Pearson correlations ranging from 0.60 for Ireland and UK, and 0.85 for the Netherlands) and also to detect gastrointestinal syndrome in France (Pearson correlation of 0.66). The final result is a near-real-time flexible surveillance framework not constrained by any specific case definition and capable of capturing the heterogeneity in symptoms circulation during influenza epidemics in the various European countries.