A multi-modal wildfire prediction and early-warning system based on a novel machine learning framework.

Wildfires are increasingly impacting the environment and human health. Among the top 20 California wildfires, those in 2020-2021 burned more acres than the last century combined. Lack of an adequate early warning system impacts the health and safety of vulnerable populations disproportionately and widens the inequality gap. In this project, a multi-modal wildfire prediction and early warning system has been developed based on a novel spatio-temporal machine learning architecture. A comprehensive wildfire database with over 37 million data points was created, including the historical wildfires, environmental and meteorological sensor data from the Environmental Protection Agency, and geological data. The data was augmented into 2.53 km × 2.53 km square grids to overcome the sensor network coverage limitations. Leading and trailing indicators for the wildfires are proposed, classified, and tested. The leading indicators are correlated to the risks of wildfire conception, whereas the trailing indicators are correlated to the byproducts of the wildfires. Additionally, geological data was incorporated to provide additional information for better assessment on wildfire risks and propagation. Next, a novel U-Convolutional Long Short-Term Memory (ULSTM) neural network was developed to extract key spatial and temporal features of the dataset, specifically to address the spatial nature of the location of the wildfire and time-progression temporal nature of the wildfire evolution. Through iterative improvements and optimization, the final ULSTM network architecture, trained with data from 2012 to 2017, achieved >97% accuracy for predicting wildfires in 2018, as compared to ∼76% using traditional Convolutional Neural Network (CNN) techniques. The final model was applied to conduct a retrospective study for the 2018-2022 wildfire seasons, and successfully predicted 85.7% of wildfires >300 K acres in size. This technique could enable fire departments to anticipate and prevent wildfires before they strike and provide early warnings for at-risk individuals for better preparation, thereby saving lives, protecting the environment, and avoiding economic damages.

Climate change and public health: The effects of global warming on the risk of allergies and autoimmune diseases: The effects of global warming on the risk of allergies and autoimmune diseases.

Global climate change and extreme weather events are associated with epigenetic modifications in immune cells, leading to the possible increased risk and prevalence of allergies and autoimmune diseases.

Characterization and regulation of microplastic pollution for protecting planetary and human health.

Microplastics are plastic particles <5 mm in diameter. Since the 1950s, there has been an exponential increase in the production of plastics. As of 2015, it is estimated that approximately 6300 million metric tons of plastic waste had been generated of which 79% has accumulated in landfills or the natural environment. Further, it is estimated that if current trends continue, roughly 12,000 million metric tons of plastic waste will accumulate by 2050. Plastics and microplastics are now found ubiquitously-in the air, water, and soil. Microplastics are small enough to enter the tissues of plants and animals and have been detected in human lungs, stools, placentas, and blood. Their presence in human tissues and the food chain is a cause for concern. While direct clinical evidence or epidemiological studies on the adverse effects of microplastic on human health are lacking, in vitro cellular and tissue studies and in vivo animal studies suggest potential adverse effects. With the ever-increasing presence of plastic waste in our environment, it is critical to understand their effects on our environment and on human health. The use of plastic additives, many of which have known toxic effects are also of concern. This review provides a brief overview of microplastics and the extent of the microplastic problem. There have been a few inroads in regulating plastics but currently these are insufficient to adequately mitigate plastic pollution. We also review recent advances in microplastic testing methodologies, which should support management and regulation of plastic wastes. Significant efforts to reduce, reuse, and recycle plastics are needed at the individual, community, national, and international levels to meet the challenge. In particular, significant reductions in plastic production must occur to curb the impacts of plastic on human and worldwide health, given the fact that plastic is not truly recyclable.

Using predicted marginal effects to assess the impact of rurality and free and reduced lunch eligibility on a school-based nutrition intervention.

PURPOSE: To estimate the impact of a school-based nutrition education intervention in rural schools and schools with high free and reduced lunch (FRL) eligibility rates. METHODS: As part of the evaluation of the Healthy Schools Healthy Students intervention, 20 schools were randomized to control and intervention conditions. Pre (October 2017) and posttest (April 2018) data were analyzed using multi-level linear regression models to estimate the intervention effect for multiple outcomes controlling for school-level demographic characteristics. We report the predicted marginal effect overall and specifically for rural; high FRL; and rural, high-FRL schools. RESULTS: We observed at least one significant intervention effect for food group knowledge, liking to eat fruit, beliefs about how healthy fruits are, non-taste test fruit preferences, liking to eat vegetables, beliefs about how healthy vegetables are, and taste test vegetable preferences. We observed differential intervention effects for all outcomes except taste test vegetable preferences based on rural and high-FRL status. CONCLUSIONS: Interventions do not necessarily have the same impact on all participants. Sub-analyses can reveal these important differential effects, as they have important implications for policymakers, program implementers, and evaluators. Resources and interventions should be allocated where they will have the greatest impact.

A protocol to inject ocular drug implants into mouse eyes.

Ocular drug implants (ODIs) are beneficial for treating ocular diseases. However, the lack of a robust injection approach for small-eyed model organisms has been a major technical limitation in developing ODIs. Here, we present a cost-effective, minimally invasive protocol to deliver ODIs into the mouse vitreous called Mouse Implant Intravitreal Injection (MI3). MI3 provides two alternative surgical approaches (air-pressure or plunger) to deliver micro-scaled ODIs into milli-scaled eyes, and expands the preclinical platforms to determine ODIs' efficacy, toxicity, and pharmacokinetics. For complete details on the use and execution of this protocol, please refer to Sun et al. (2021).

An intravitreal implant injection method for sustained drug delivery into mouse eyes.

Using small molecule drugs to treat eye diseases carries benefits of specificity, scalability, and transportability, but their efficacy is significantly limited by a fast intraocular clearance rate. Ocular drug implants (ODIs) present a compelling means for the slow and sustained release of small molecule drugs inside the eye. However, methods are needed to inject small molecule ODIs into animals with small eyes, such as mice, which are the primary genetic models for most human ocular diseases. Consequently, it has not been possible to fully investigate efficacy and ocular pharmacokinetics of ODIs. Here, we present a robust, cost-effective, and minimally invasive method called "mouse implant intravitreal injection" (MI3) to deliver ODIs into mouse eyes. This method will expand ODI research to cover the breadth of human eye diseases modeled in mice.

Implementation and outcome evaluation of a team nutrition intervention: increasing knowledge, attitudes, and preferences.

Low-income, rural children are at a greater risk for poor dietary intake. Schools offer a venue to deliver appropriate interventions. Our aim was to evaluate the implementation and effectiveness of Healthy Schools, Healthy Students (HSHS). We conducted a mixed-methods evaluation using a cluster-randomized trial design with 20 schools in a rural, Midwestern state. HSHS included education sessions, cafeteria coaching and taste testing. We interviewed implementers (n = 13) and nutrition educators (n = 8), conducted six focus groups with cafeteria coaches, and surveyed fourth graders (n = 1057) about their nutrition knowledge, attitudes toward and preferences for fruits and vegetables (F&V), F&V consumption and MyPlate awareness. We used multi-level linear models to estimate the intervention effect and qualitative data were coded. There were very few challenges to implementation. HSHS participation was positively associated with knowledge, attitudes toward F&V, preferences for vegetables from the taste tests, MyPlate awareness and vegetable consumption. HSHS was viewed as beneficial and easy to deliver, suggesting this type of intervention could be widely implemented. Improving knowledge and attitudes through nutrition education and preferences through taste testing have the potential to improve dietary intake among rural students. Low-cost nutrition interventions can be successfully implemented in rural elementary schools with positive outcomes.

Implementation Matters: Lessons From Iowa Medicaid's Healthy Behaviors Program.

Iowa's Medicaid expansion includes the Healthy Behaviors Program (HBP), which incentivizes enrollees to receive a wellness exam and complete a health risk assessment annually to waive a monthly premium. We conducted a telephone survey with enrollees to examine their awareness and understanding of the HBP, and we then merged the survey data with claims data to examine factors associated with the completion of program requirements. As found in previous research, awareness of the HBP remains low, with approximately half of respondents unaware of the program or the premium requirement. Our results suggest that four years after the program was implemented, requirements are not being effectively communicated to enrollees. When designing and implementing such programs, policy makers should note that they are unlikely to succeed without consideration of how the program is structured and promoted. Limited program awareness is likely to result in low participation and consequences related to paying premiums or being disenrolled.

Iowa's Medicaid Healthy Behaviors Program Associated With Reduced Hospital-Based Care But Higher Spending, 2012-17.

Health behavior incentive programs are increasingly common in Medicaid programs nationwide. Iowa's Healthy Behaviors Program (HBP) requires Medicaid expansion enrollees to complete an annual wellness exam and health risk assessment or pay monthly premiums to avoid disenrollment. The extent to which the program reduces the use of hospital-based care and lowers health care spending is unknown. Using data for 2012-17 from Medicaid and for 2014-17 from HBP, we evaluated changes in use and spending associated with HBP participation. Compared to nonparticipants, HBP participants were less likely to have an emergency department visit or be hospitalized (by 9.6 percentage points and 2.8 percentage points, respectively) but had higher total health care spending ($1,594). Meanwhile, Iowa's Medicaid expansion was associated with increased use and spending independent of HBP participation-that is, applying to both participants and nonparticipants. Overall, our findings suggest that the HBP was associated with substantial reductions in hospital-based care but increased health care spending.