Large pre-trained models, also known as foundation models (FMs), are trained in a task-agnostic manner on large-scale data and can be adapted to a wide range of downstream tasks by fine-tuning, few-shot, or even zero-shot learning. Despite their successes in language and vision tasks, we have not yet seen an attempt to develop foundation models for geospatial artificial intelligence (GeoAI). In this work, we explore the promises and challenges of developing multimodal foundation models for GeoAI. We first investigate the potential of many existing FMs by testing their performances on seven tasks across multiple geospatial domains, including Geospatial Semantics, Health Geography, Urban Geography, and Remote Sensing. Our results indicate that on several geospatial tasks that only involve text modality, such as toponym recognition, location description recognition, and US state-level/county-level dementia time series forecasting, the task-agnostic large learning models (LLMs) can outperform task-specific fully supervised models in a zero-shot or few-shot learning setting. However, on other geospatial tasks, especially tasks that involve multiple data modalities (e.g., POI-based urban function classification, street view image–based urban noise intensity classification, and remote sensing image scene classification), existing FMs still underperform task-specific models. Based on these observations, we propose that one of the major challenges of developing an FM for GeoAI is to address the multimodal nature of geospatial tasks. After discussing the distinct challenges of each geospatial data modality, we suggest the possibility of a multimodal FM that can reason over various types of geospatial data through geospatial alignments. We conclude this article by discussing the unique risks and challenges to developing such a model for GeoAI.

Background: During the COVID-19 pandemic, infodemic spread even more rapidly than the pandemic itself. The COVID-19 vaccine hesitancy has been prevalent worldwide and hindered pandemic exiting strategies. Misinformation around COVID-19 vaccines is a vital contributor to vaccine hesitancy. However, no evidence systematically summarized COVID-19 vaccine misinformation. Objective: This review aims to synthesize the global evidence on misinformation related to COVID-19 vaccines, including its prevalence, features, influencing factors, impacts, and solutions for combating misinformation. Methods: We performed a systematic review by searching 5 peer-reviewed databases (PubMed, Embase, Web of Science, Scopus, and EBSCO). We included original articles that investigated misinformation related to COVID-19 vaccines and were published in English from January 1, 2020, to August 18, 2022. We excluded publications that did not cover or focus on COVID-19 vaccine misinformation. The Appraisal tool for Cross-Sectional Studies, version 2 of the Cochrane risk-of-bias tool for randomized trials (RoB 2), and Critical Appraisal Skills Programme Checklist were used to assess the study quality. The review was guided by PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) and registered with PROSPERO (CRD42021288929). Results: Of the 8864 studies identified, 91 observational studies and 11 interventional studies met the inclusion criteria. Misinformation around COVID-19 vaccines covered conspiracy, concerns on vaccine safety and efficacy, no need for vaccines, morality, liberty, and humor. Conspiracy and safety concerns were the most prevalent misinformation. There was a great variation in misinformation prevalence, noted among 2.5%-55.4% in the general population and 6.0%-96.7% in the antivaccine/vaccine hesitant groups from survey-based studies, and in 0.1%-41.3% on general online data and 0.5%-56% on antivaccine/vaccine hesitant data from internet-based studies. Younger age, lower education and economic status, right-wing and conservative ideology, and having psychological problems enhanced beliefs in misinformation. The content, format, and source of misinformation influenced its spread. A 5-step framework was proposed to address vaccine-related misinformation, including identifying misinformation, regulating producers and distributors, cutting production and distribution, supporting target audiences, and disseminating trustworthy information. The debunking messages/videos were found to be effective in several experimental studies. Conclusions: Our review provides comprehensive and up-to-date evidence on COVID-19 vaccine misinformation and helps responses to vaccine infodemic in future pandemics. Trial Registration: PROSPERO CRD42021288929; https://tinyurl.com/2prejtfa

Both health resources and access to these resources increased after China’s health care reform launched in 2009. However, it is not clear if the inequalities were reduced within rural China, which was one of the main targets in the reform. This study aims to examine the changes in inequalities in health resources and access following the reform. Data came from the routine report of rural counties in every other year from 2008 to 2014. Health professionals and hospital beds per 1000 population were used for measuring health resources, and the hospitalization rate was used for access. Descriptive analysis and the fixed effect model were used in this study. Health resources and access increased by about 50% between 2008 and 2014 in rural China. The counties in richer quintiles got more health resources and hospitalizations. As for health professionals, the absolute differences between the richer and the poorest quintile were significantly enlarging in 2014 when compared to 2008. Regarding the hospitalization rate, the differences between the richest and the poorest quintile showed no significant change after 2012. In sum, absolute inequalities of health resources were increased, while that of health utilization kept constant following China’s health care reform. The reform needs to continually recruit qualified health workers and appropriately allocate health infrastructures to strengthen the capacity of the health care system in the impoverished areas.

Background: Circulating omega-3 and omega-6 polyunsaturated fatty acids (PUFAs) have been associated with various chronic diseases and mortality, but results are conflicting. Few studies examined the role of omega-6/omega-3 ratio in mortality.Methods: We investigated plasma omega-3 and omega-6 PUFAs and their ratio in relation to all-cause and cause-specific mortality in a large prospective cohort, the UK Biobank. Of 85,425 participants who had complete information on circulating PUFAs, 6461 died during follow-up, including 2794 from cancer and 1668 from cardiovascular disease (CVD). Associations were estimated by multivariable Cox proportional hazards regression with adjustment for relevant risk factors.Results: Risk for all three mortality outcomes increased as the ratio of omega-6/omega-3 PUFAs increased (all P_trend <0.05). Comparing the highest to the lowest quintiles, individuals had 26% (95% CI, 15–38%) higher total mortality, 14% (95% CI, 0–31%) higher cancer mortality, and 31% (95% CI, 10–55%) higher CVD mortality. Moreover, omega-3 and omega-6 PUFAs in plasma were all inversely associated with all-cause, cancer, and CVD mortality, with omega-3 showing stronger effects.Conclusions: Using a population-based cohort in UK Biobank, our study revealed a strong association between the ratio of circulating omega-6/omega-3 PUFAs and the risk of all-cause, cancer, and CVD mortality.Funding: Research reported in this publication was supported by the National Institute of General Medical Sciences of the National Institute of Health under the award number R35GM143060 (KY). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

In this pioneering study, inspired by AutoGPT, the state-of-the-art open-source application based on the GPT-4 large language model, we develop a novel tool called AD-AutoGPT, which can conduct data collection, processing, and analysis about complex health narratives of Alzheimer’s Disease in an autonomous manner via users’ textual prompts. We collated comprehensive data from a variety of news sources, including the Alzheimer’s Association, BBC, Mayo Clinic, and the National Institute on Aging since June 2022, leading to the autonomous execution of robust trend analyses, intertopic distance map visualization, and identification of salient terms pertinent to Alzheimer’s Disease. This approach has yielded not only a quantifiable metric of relevant discourse but also valuable insights into public focus on Alzheimer’s Disease. This application of AD-AutoGPT in public health signifies the transformative potential of AI in facilitating a data-rich understanding of complex health narratives like Alzheimer’s Disease in an autonomous manner, setting the groundwork for future AI-driven investigations in global health landscapes. Code, a demo video, and other information are available at https://github.com/levyisthebest/AD-AutoGPT.

Background: Basic public health services for diabetes play an essential role in controlling glycemia in patients with diabetes. This study was conducted to understand the urban-rural disparities in the utilization of basic public health services for people with diabetes and the factors influencing them. Methods: The data were obtained from the 2018 China Health and Retirement Longitudinal Study (CHARLS) with 2976 diabetes patients. Chi-square tests were used to examine the disparities in the utilization of diabetes physical examination and health education between urban and rural areas. Logistic regression was performed to explore the factors associated with the utilization of diabetes public health services. Results: Among all participants, 8.4% used diabetes physical examination in the past year, and 28.4% used diabetes health education services. A significant association with age (OR = 0.64, 95% CI:0.49–0.85; P < 0.05) was found between patients’ use of health education services. Compared with diabetes patients living in an urban area, diabetes patients living in a rural area used less diabetes health education. (χ2= 92.39, P < 0.05). Patients’ self-reported health status (OR = 2.04, CI:1.24–3.35; P < 0.05) and the use of glucose control (OR = 9.33, CI:6.61–13.16; P < 0.05) were significantly positively associated with the utilization of diabetes physical examination. Patients with higher education levels were more likely to use various kinds of health education services than their peers with lower education levels (OR = 1.64, CI:1.21–2.22; P < 0.05). Conclusion: Overall, urban-rural disparities in the utilization of public health services existed. Vulnerable with diabetes, such as those in rural areas, are less available to use diabetes public health services. Providing convenient health service infrastructure facilitates the utilization of basic public health services for diabetes in older patients with diabetes, especially in rural areas.