Displaying 21-40 of 2310 results for

Case study: geospatial AI applied to public health in Essex County for disease mapping, resource allocation, and health equity.

Analysis of how AI could transform public health planning—including forecasting and resource allocation—while raising equity concerns.

Framework for integrating health equity considerations into AI design and deployment for public health applications.

Research on harnessing AI/ML to enhance public health surveillance: pathogen detection, outbreak forecasting, and data integration.

Review of AI applications in disease surveillance: real-time monitoring, predictive analytics, and early outbreak detection systems.

Overview of geospatial AI and its applications in GIS for public health mapping, environmental analysis, and decision support.

This resource highlights state-based program initiatives tailored to improving hypertensive disorders of pregnancy outcomes.

State firearm survey data can inform firearm injury prevention strategies—read recommendations for developing state firearm surveys and applying findings.

Learn key lessons from the DREAM Learning Community about addressing structural racism and driving systemic change, which can help achieve optimal health for all.

Defining Disease Forecasting and Modeling Disease forecasting, generated by disease models, helps the public health workforce understand potential future outbreaks. Learn more about disease forecasts and models. Disease forecasting is important in describing potential future outbreaks that will affect the population and demand for health services in a given geographic area. Forecasts pull input from various sources (e.g., disease models, demographic, mobility, and intervention impact data). Individual forecasts can also be part of an ensemble forecast to improve accuracy. Forecasts can cover any length of time, but most target a window of several weeks to a few months. A subset of forecasts, known as nowcasts, seek to estimate present conditions, or those expected to occur imminently. Disease models are mathematical tools that are foundational components of disease forecasts. They estimate quantifiable factors that are impossible or impractical to directly measure, (e.g., future hospitalizations from a given disease, or its infection count in a population). Although models can be useful for specific questions, they do not give as complete a picture as a forecast. There are four major disease model types: Mechanistic. Attempts to simulate biological and/or social processes of transmission based on assumptions from prior or experimental data. Statistical. Relies on past data (such as infections or death) to predict future trends and can incorporate some assumptions about intervention application and uptake. Quality and quantity of past data can be a major limitation, and some models may suggest biological improbabilities. Agent. Simulates individual risks and behaviors in a population. These are highly complex, computationally very expensive to develop and run and require vast amounts of data and strong assumptions. Ensemble. Like their forecasting counterparts, they compile models and outputs, mitigating the risk of relying on one data point. While raising the overall confidence in output, they require coordination of many models to be built and simulated, which can be complex and costly unless the models already exist (such as for COVID-19 case counts). Forecasts and Models Work Together While disease forecasts and models are often conflated, they are discrete concepts. Forecasts offer a general prediction, whereas models are the mathematical pieces forecasters use to create them. Weather forecasts are commonplace, and their weekly predictions are often reasonably accurate. In contrast, predicting a big storm’s individual factors (e.g., rainfall, wind speed, lightning strikes) fall to the job of models. Together, those models help meteorologists better understand the weather and generate a forecast. In a public health context, disease forecasting informs public health officials, health care providers, and policymakers about potential risks and guide decision-making regarding preventive measures, resource allocation, and response strategies. Meanwhile, disease models aim to simulate the behavior of infectious diseases under different scenarios, allowing researchers to explore and evaluate various factors that influence disease transmission. Considerations for Decision-Making Decision-makers should consider scope and limitations of forecasts and models. They may consider adding inputs—such as projections for economic and long-term impacts. Examples include economic impacts of school closures, costs of more staffing ahead of an outbreak, and supply chain shortage forecasts for personal protective equipment (PPE). Decision-makers at all levels should consider using modeling to answer more specific, practical questions rather than predicting overall trends. Forecasts can cover different geographic scales. Public health leaders will need granular, local data to most effectively inform decision-making and communications. Novel conditions and pathogens may not have readily available data to inform models or forecasts, which will affect their predictive ability. Health officials must effectively communicate these limitations to decision-makers and the public. Examples of Forecasts and Models CDC’s COVID-19 Forecast for Hospitalizations (ensemble forecast) shows the number of daily COVID-19 hospitalizations reported in the United States from the prior two months and projected daily COVID-19 hospitalizations over the coming four weeks. Information sources are independent teams meeting submission and data quality requirements. CDC’s FluSight (ensemble forecast) has many contributing teams and models that predicts the upcoming weekly laboratory confirmed influenza hospital admissions both nationally and by state. Johns Hopkins University’s Center for Systems Science and Engineering county-level risk model for COVID-19 in the United States. This model leverages epidemiological data, mobile phone data, demographic and socioeconomic information, and behavioral metrics. The Global Epidemic and Mobility Framework simulates the global spread of infectious diseases by mathematically representing infection dynamics, population geographies, and population mobility patterns. Additional Resources Disease modeling for public health: added value, challenges, and institutional constraints Predictive Models for Forecasting Public Health Scenarios: Practical Experiences Applied during the First Wave of the COVID-19 Pandemic Applying infectious disease forecasting to public health: a path forward using influenza forecasting examples Technology to advance infectious disease forecasting for outbreak management CDC-RFA-OT18-1802 2018-2024 article yes

Learn how health departments can focus their infectious disease prevention efforts in this brief.

States Partner Across Sectors to Address Lead Poisoning Kayley Humm, Kerry Wyss, Ali Aslam Learn in this brief how three states are using partnerships to improve lead testing and reduce cases of lead poisoning. ASTHO partnered with the National Center for Healthy Housing (NCHH) to provide technical assistance and capacity-building support for lead poisoning prevention efforts in three state health agencies: Maryland Department of Health, North Dakota Department of Health and Human Services, and Arkansas Department of Health. This brief highlights each agency’s strategies for collaborating across sectors along with accomplishments for strengthening lead poisoning prevention capacity in each jurisdiction. Many of these strategies align with those used in a health in all polices (HiAP) approach to lead poisoning prevention. State Examples Maryland Department of Health Maryland adopted a collaborative approach to prevent lead poisoning. The Maryland Department of Health (MDH) has an established lead poisoning prevention program that partners with the Maryland Department of the Environment. The Department of the Environment oversees the childhood lead registry and case management, while MDH focuses on lead testing regulations and Medicaid services. This partnership has been implemented across the 24 local health departments in the state. Maryland enhanced lead case management by providing staff support and tackling complex cases that require additional assistance. In addition to supporting an increase in lead case management activities and lead awareness, ASTHO funding also helped strengthen collaboration and coordination among local health departments, state agencies, and local health care providers. The MDH Environmental Health Bureau also improved efficiency by moving data from the lead registry to MDH for lead surveillance and case management. They also developed and launched sub-county lead testing data as part of their Environmental Public Health Tracking public portal. These activities align with HiAP strategies of developing and structuring cross-sector relationships, coordinating funding and investments, and synchronizing communications. North Dakota Department of Health and Human Services The North Dakota Department of Health and Human Services (NDHHS) made significant strides in building up the state lead program, which recently transitioned from the department of environmental quality to NDHHS. With support from ASTHO and NCHH, NDHHS developed a lead prevention website with a data dashboard, developed a lead screening questionnaire, and built collaborative partnerships. The activities in North Dakota align with the HiAP strategies of developing and structuring cross-sector relationships, synchronizing communications, and integrating research, evaluation, and data systems. Building collaborative partnerships is a key initiative for the NDHHS lead program. Already developed partnerships include stakeholders such as Health Tracks and WIC. Health Tracks developed a newsletter article for their provider network so physicians can stay up to date and aware of the lead program transition and lead testing changes, and WIC will host informational lunch and learns to raise awareness about lead testing within their network. North Dakota is also prioritizing building partnerships with tribal communities. A tribal communications plan was developed with the goal of establishing an effective communication plan between the state of North Dakota and each tribal government for lead-related events. Anticipated outcomes from the communication plan include testing for blood lead levels, conducting environmental assessments on tribal lands, and seeing if a tribal member or government is interested in hosting a lead screening event. Progress has been made with the Standing Rock Sioux Tribe, Turtle Mountain band of Chippewa, and NDHHS is hopeful to establish intertribal meetings with all four governmental tribal representatives. Arkansas Department of Health The Arkansas Department of Health established its lead program in 2011 to support abatement of lead-based paint in residential and commercial properties. With support from ASTHO and NCHH, Arkansas has been using a data-driven approach to gain a more comprehensive understanding of lead exposure burden in the state. These activities align with the HiAP strategy of incorporating health data into decision-making and integrating research, evaluation, and data systems. The Arkansas Department of Health conducts periodic audits on its data system to support access to timely and accurate data. To improve data quality and frequency of blood lead testing reports, the health department is establishing incentive programs to encourage facilities to report cases of elevated blood lead. In addition to conducting outreach to its partners, the Arkansas Department of Health has been working to improve lead case data access and data quality through data mining efforts, case report matching, and migration to a new lead surveillance system. Arkansas has been working to modernize the current reporting system to facilitate automation and promote overall efficiency of data analysis and case identification. Conclusion The collaborative efforts of Maryland, North Dakota, and Arkansas highlight the importance of multi-sector partnerships and data sharing in addressing lead poisoning prevention and align with many of the strategies used in a HiAP approach. Each state implemented tailored strategies that sought to grow collaboration in its unique context. These initiatives highlight the importance of cross-sector collaboration in public health initiatives and may serve as valuable models for other jurisdictions. article yes

Learn how boundary spanning leadership can help develop more robust and productive public health workplaces.

Disease Forecasting and Modeling Data for Public Health Action Disease Forecasting Benefits Public Health Planning Disease forecasting and modeling help prepare public health departments for future infectious disease outbreaks and epidemics. Disease forecasting and modeling data can be powerful tools for state and local health agencies (S/THAs) that respond to outbreaks, develop appropriate policies, and ensure interventions have maximum impact. Actions for which decision-makers can leverage such data include: Surveillance. Forecasts and modeling help public health agencies anticipate the spread of disease or outbreaks. This advance warning allows public health officials to inform public health recommendations, preparation, and response. Communication. Disease forecasts help relate the risk of disease outbreaks to various audiences accurately and quickly, which, in turn, can inform messages on important preventive measures and encourages compliance with recommended interventions. Resource allocation. Modeling data can help decision-makers better allocate resources by predicting where and when disease outbreaks are likely to intensify and create the greatest need. Evaluation. Forecasts and modeling can help make evaluating the effectiveness of public health policies and interventions more efficient by comparing predicted outcomes with observed data and adjusting as needed. Considerations Informed by S/THA Forecasting Jurisdictions with forecasting experience identified key indicators to monitor as part of outbreak forecasting, which fall into three main categories: Epidemic spread indicators (e.g., symptom monitoring, morbidity and mortality data, percent positivity, regional pictures of transmission). Health care system capacity (e.g., essential and/or surge personnel, available beds, ventilator usage, and supply of personal protective equipment. Public health capacity for testing capacity and contact tracing. Further considerations for S/THAs: Know your strengths. Identify the unique skillsets among partners in public health, academia, and the private sector and consider how they foster reciprocal relationships. Recognize capacity/expertise gaps. Consider leveraging partnerships for specific types of analytics expertise while exploring internal capacity building opportunities (e.g., job shadowing and resource-sharing programs on workflows and methodologies). Engage legal and compliance teams. Ensure policy and practice are aligned among partners. Explore data access/sharing pipelines. Connect public, private, academic partners, and their audiences. Start small. Identify discrete forecasting and modeling projects to demonstrate success. Identify decision-makers’ needs. Provide quick access to analyses, metrics, dashboards. Michigan Used Models and Forecasting for Hep C Cases In response to Hepatitis C virus (HCV) in young adults from 2010-2018, the Michigan Department of Health and Human Services (MDHHS) simulated how HCV treatment could significantly reduce HCV prevalence among young people who inject drugs, especially for those both previously or currently injecting drugs. MDHHS used several novel predictors to paint a local picture of probable HCV diagnoses among residents up to age 40. These predictors included measures related to a variety of population characteristics (e.g., access to transportation, college education, presence of non-family households) and public health indicators (e.g., heroin treatment admissions, newborns with neonatal abstinence syndrome, and sexually-transmitted infections). MDHHS also leveraged county-level assessments of HCV vulnerability to identify locations for new syringe services programs in the state. MDHHS has recognized several modeling and analytics use cases that benefitted their work during responses to HCV and COVID-19: Short-term forecasts (i.e., weeks) helped predict likely transmission patterns and potential ranges of projections. Longer-term forecasts (i.e., months) explored scenarios based on new recommendations and policy changes. Retrospective counterfactuals evaluated the impact of policies or other changes by examining “what-if” situations. MDHHS is considering using forecasts and models for COVID-19, influenza epidemics, tuberculosis vulnerability, and C. auris spread. Resource constraints require decision-makers and public health practitioners to consider how they are using available resources for the highest return on investment. Models generated momentum to respond to threats and evaluate whether interventions were successful. CDC-RFA-OT18-1802 2018-2024 article yes

Learn about how five jurisdictions approached self-measured blood pressure monitoring programs to reduce hypertension and uncover systemic barriers to care.

Partnering with Legislative Staff to Improve Long COVID Outcomes Partner with Legislators to Improve Long COVID Outcomes Amelia Poulin and Sidnie Christian Learn how health departments can secure legislative understanding and support for Long COVID recovery efforts. Long COVID challenges public health systems, impacting individuals’ health, workforce participation, and community well-being. State and territorial health departments are leading efforts to track, understand, and mitigate the health and economic effects through surveillance, education, and coordinated care initiatives.  To maintain and expand these efforts, health department programs can secure legislative understanding and support. This requires cultivating longstanding, trust-based relationships with legislators and their staff. Strategic engagement helps legislators view health departments as indispensable partners in addressing complex public health issues with broad social and economic implications. Build Longstanding Relationships with Legislative Staff Legislative staff are often the most consistent points of contact in a lawmaker’s office and play a central role in shaping policy advice. Regular engagement strengthens trust and visibility, helps maintain productive relationships, and ensures consistent communication with legislative offices. Health agencies can achieve this by: Engaging early and often: Identify key legislative staff for health department programs to brief on emerging Long COVID data, evolving needs, and program outcomes throughout the year. These conversations provide context and set the stage for trust before policy requests. Over time, they can lead to invitations for health department representatives to provide expert input. Positioning the program as a trusted, nonpartisan source: Health department leaders can provide timely, objective information about Long COVID’s impact on local hospitals, schools, and employers. Demonstrating responsiveness: Following up on constituent inquiries related to Long COVID testing or benefits shows legislators that the health department is directly addressing concerns in their districts.   Program staff can play a key role by developing briefing materials, success stories, and district-level data to share internally with leadership or policy offices for dissemination to legislators.   Note: Health department staff should align engagement with internal communication protocols. They may centralize outreach through a legislative or government affairs office that coordinates messaging and ensures compliance with statutes and lobbying restrictions. Identify Objectives and Tailoring Asks Before reaching out to legislative staff, health department leaders should clearly define their goals (e.g., funding for post-COVID clinics, data infrastructure, or research partnerships). When health departments align requests with legislative priorities, those proposals may seem more feasible or be more likely to gain support. Keys to doing so include: Understanding legislator priorities: Review voting history, public statements, and committee membership (e.g., health, workforce, budget). Identify shared interests such as workforce participation, economic productivity, or small business resilience. Choosing the right messenger: Personal narratives from constituents affected by Long COVID related to the sub-issue (e.g., a small business owner struggling to return to work, a teacher navigating disability benefits, or a parent managing caregiving responsibilities) can be effective. Consider pairing stories with district-specific data to illustrate scope. State health departments can also amplify impact by working with local health jurisdictions to paint a larger picture of how Long COVID impacts communities in the region. For example, drawing connections between workforce impacts across multiple counties can demonstrate to legislators that Long COVID affects the state’s overall economic resilience, not just isolated communities. This approach can help legislative staff see statewide trends and understand how targeted investments could yield system-wide benefits. Crafting the message: Use plain, non-technical language to describe Long COVID (e.g., “lingering symptoms after COVID infection” rather than “post-acute sequelae”). Consider emphasizing economic impacts (e.g., missed work or school days, productivity losses, and long-term disability claims) and framing the health department as a problem solver that helps businesses/families recover and navigate challenges, rather than a requester for resources. Communicate Effectively Legislators are often time constrained. Clear, concise, and locally relevant messages are most effective. To build an effective ask of a legislator’s office, health department staff can: Use their language: Translate public health concepts into legislative priorities (e.g., “economic competitiveness,” “community stability,” “health care access”). Incorporate local data: Share district-level statistics on Long COVID cases or workforce absences, as data allows (e.g., “in your district, an estimated 5,000 workers have missed more than two weeks of work due to Long COVID”). Combine data with moral resonance: Pair values-based appeals (e.g., “every resident and their family deserve the chance to live and work at their full potential”) with supporting evidence (“yet one in four adults in this district continue to experience symptoms six months after infection, limiting their ability to contribute to the workforce and community”). Leave behind resources: Provide one-page infographics or briefing sheets summarizing data and program activities. Follow up to reinforce conversations with updates, success stories, and progress metrics. Anticipate Policy Dynamics and Counterarguments Legislative discussions may surface alternative policy ideas or misconceptions about Long COVID and health agency program roles. Consider preparing for opportunities to: Answer questions: Public health leaders should be prepared to clearly explain the department’s legal authority, the evidence base for Long COVID programs, and the partnerships that support implementation. Consider explaining how scientific research, emerging epidemiologic data, and best practices inform Long Covid programs and how partnerships with hospitals, clinics, and community organizations help ensure effective service delivery. Clear, concise explanations help legislators understand the health department’s scope and role, build credibility, and preempt misconceptions that could undermine support for program priorities. Acknowledge unintended consequences: Demonstrate awareness of policy trade-offs and propose pragmatic solutions. For example: A proposal to expand Long COVID benefits might raise concerns about budget constraints. Health department leaders could suggest phased implementation or pilot programs in high burden areas. Understand alternatives: Be prepared to discuss other proposed interventions and show how the health department’s approach complements them. For example: If a legislator suggests employer-led sick leave policies as the primary solution to Long COVID, the health department could explain that monitoring Long COVID prevalence and providing patient support can help ensure workers’ safe return to their jobs, complementing workplace policies. Leverage rulemaking: When statutory change is limited, use administrative rulemaking and public comment to align implementation with public health intent.   Conclusion Building lasting, credible relationships with legislative staff allows health departments to move from reactive engagement to a proactive strategy. By pairing constituent stories with district-specific data, aligning messages with economic and moral values, and maintaining year-round communication, public health leaders can secure sustained support for Long COVID initiatives. These strategies not only advance Long COVID priorities but also strengthen the overall policy capacity and visibility of public health agencies, positioning them as trusted, solutions-oriented partners in state governance.   article yes

4-pillar epidemic intelligence framework adding AI decision support to respiratory disease surveillance, risk evaluation, and early warning.

How AI tools plus community engagement improve adolescent mental health in rural settings. Highlights digital literacy needs. Frontiers, 2025.

5 steps for public health leaders to use AI responsibly: build awareness, pilot uses, manage risk, invest in staff training.

Michigan DTMB guidelines for ethical AI adoption: data classification, human-in-the-loop oversight, and equitable access for state agencies.