Public health departments across the United States are experiencing a profound technological transformation as artificial intelligence reshapes how communities protect and improve population health. From sophisticated algorithms predicting restaurant health code violations in Chicago to machine learning systems preventing suicides in tribal communities throughout the Southwest, AI technology is fundamentally changing how public health professionals detect threats, allocate resources, and serve their communities.
This technological revolution arrives at a critical juncture for American public health infrastructure. With approximately 60% of the public health workforce expected to retire or leave the field in coming years, and looming federal funding reductions threatening essential services, health departments face unprecedented operational challenges. Meanwhile, emerging health threats continue demanding robust responses from already-strained systems.
The Promise of Predictive Public Health
Public health leaders increasingly view artificial intelligence as the solution to amplifying human expertise while detecting problems before they escalate into full-scale crises. This fundamental shift from reactive to predictive public health represents more than mere technological advancement—it offers transformative potential to save lives, optimize scarce resources, and address persistent health disparities with unprecedented precision and effectiveness.
“AI differentiates from other technologies because it’s really based on not telling a machine or computer what to do; it tells the computer how to learn,” explained Tatiana Lin, MA, director of business strategy and innovation at the Kansas Health Institute. “It uses those learnings to improve itself and make predictions based on all the information it’s learned.”
Growing Demand for AI Training
Amid severe public health staffing shortages and budget constraints, appetite for learning AI applications has grown dramatically. Since 2023, Lin and her colleagues have conducted more than 30 specialized trainings nationwide, introducing artificial intelligence concepts and applications to public health workers. These comprehensive sessions cover everything from defining AI in accessible terms to exploring practical applications in disease surveillance and epidemiological research. As technology matures rapidly and new tools emerge almost daily, these educational efforts continue intensifying.
Federal Leadership in AI Adoption
Real-world AI applications stepped into the public health spotlight during the COVID-19 pandemic’s early years when the U.S. Centers for Disease Control and Prevention deployed natural language processing to analyze massive volumes of unstructured text data. The system processed social media posts, COVID-19 policy documents, symptom reports, and misinformation campaigns, enabling researchers to assess public sentiment, identify emerging threats, and review thousands of policy articles in record time. Tasks that would have required months using traditional manual methods were completed within days.
Local Innovation: Food Safety and Beyond
Chicago’s Restaurant Inspection Revolution
At the municipal level, AI is transforming critical operations like food safety monitoring and restaurant inspections. The Chicago Department of Health leveraged more than a decade of historical data, utilizing SAS’s Viya 4.0 platform—a comprehensive system for data analytics, management, and visualization—to review and analyze 92,000 free-form statements extracted from 11,000 restaurant inspection reports.
This groundbreaking project enabled inspectors to prioritize visits to higher-risk establishments and focus attention on likely violations with remarkable precision. According to SAS principal solutions architect Tom Sabo, who presented the project’s success story at APHA’s 2023 Annual Meeting and Expo, manually reviewing the same reports to identify primary issues would have consumed approximately 7,700 hours—equivalent to four full-time employees working for one entire year, compared to just one week using AI.
COVID-19 Response in California
In California, the Contra Costa Public Health department near San Francisco partnered with Stanford University in 2022 to develop COVID Fast Fax, an innovative tool that flags the most urgent incoming faxes using sophisticated machine learning algorithms. As the health department was inundated with faxes during the pandemic’s height, the system successfully processed and categorized thousands of handwritten case reports, allowing overwhelmed workers to quickly triage high-risk cases requiring immediate attention. The development team has since released the complete code and methodology for researchers and health departments interested in replicating this valuable tool.
Health departments are also exploring specialized platforms like Prepper AI, designed specifically for emergency preparedness and disaster recovery. Built with a public health lens, the platform supports comprehensive planning and strategic resource allocation in response to increasing natural and human-made disasters.
AI in Tribal Public Health
Tribal public health programs are benefiting significantly from AI tools, particularly when paired with culturally grounded strategies and community-centered approaches. One of the most notable examples comes from the White Mountain Apache Tribe in Arizona, where collaboration with Johns Hopkins Bloomberg School of Public Health’s Center for Indigenous Health led to developing an AI-driven suicide risk identification model.
By analyzing electronic health records, the system successfully flags individuals at high risk for suicide-related events including suicidal ideation, self-harm behaviors, or substance abuse crises. Once identified, these patients receive prompt followup from community-based mental health teams trained in culturally appropriate intervention strategies.
“We found that it not only continued to be valid and add benefit in terms of identifying the highest risk people, but also helped ensure that those at highest risk were reached with care,” explained Emily Haroz, PhD, MHS, MA, associate professor in international and mental health at the center. “And then, also among those at highest risk, we saw a reduced risk for another suicide-related event.”
This remarkable success prompted expansion into three Indian Health Service clinics, where research teams are now conducting rigorous clinical trials to further validate and refine the approach.
HIV Prevention Through Machine Learning
Researchers in Georgia analyzed a decade of sexually transmitted infection data from Fulton County, training sophisticated algorithms to identify key risk factors associated with HIV diagnosis. The model examines multiple variables including the number of previous STIs, diagnostic locations, patient age demographics, and social vulnerability indices. This comprehensive analysis enables public health officials to predict who faces highest risk of acquiring HIV and prioritize targeted health interventions accordingly.
“There is a big interest in the larger scientific community for these tools,” said Carlos Saldana, MD, an assistant professor of medicine at Emory University who specializes in HIV and STI implementation science. Working in partnership with the Georgia Department of Public Health’s Division of HIV surveillance, Saldana’s team created an innovative machine learning tool that could revolutionize HIV prevention strategies.
“We have understaffed public health workers and contact tracers, so how can we use this technology to help us prioritize who to reach and who to offer testing?” Saldana explained.
Ethical Considerations and Community Engagement
Addressing Bias and Equity
Implementing AI in public health surveillance raises crucial considerations about algorithmic bias and meaningful community engagement. AI systems can perpetuate existing biases present in historical data. For example, inadequate data collection on transgender populations limits model applicability to these communities, requiring intentional efforts to address significant gaps.
Public health strategist and educator Ashley S. Love, DrPH, DHSc, cautioned about risks including AI bias and “hallucinations,” where systems generate fabricated facts. While the pandemic accelerated AI adoption in public health, governance frameworks have not kept pace with technological advancement.
“We need to make sure that public health professionals have enough AI literacy so that we can be at the table to make policies,” Love emphasized. “If public health isn’t at the table, there will be selection bias, and not all perspectives, views and scenarios could be thought of.”
Educational Applications
Love, a biostatistics and epidemiology professor who formerly served as Delaware’s state epidemiologist, sees tremendous value in using generative AI to help personalize education around artificial intelligence for professionals lacking resources. She has successfully used AI tools like ChatGPT, Claude, and Canva AI to help students and public health professionals bridge critical knowledge gaps.
Global Mortality Surveillance
Abraham Flaxman, PhD, associate professor of global health at the Institute for Health Metrics and Evaluation at the University of Washington, has pioneered AI applications addressing one of global public health’s most persistent challenges: the lack of reliable information about how people die.
Globally, nearly half of all deaths occur without official death certificates, creating massive data gaps that hinder health planning, disease prevention, and effective resource allocation. While many countries rely on medical examiners and pathologists to review and certify causes of death, such systems prove expensive and logistically unfeasible in many world regions.
Flaxman’s work focuses on automating “verbal autopsies”—a method existing for more than 50 years where interviewers ask family members structured questions about deceased individuals’ symptoms and circumstances. Previously requiring trained physicians, this process can now be automated through generative AI, dramatically improving scalability and accessibility.
Looking Forward
Artificial intelligence tools are evolving so rapidly that researchers must constantly reassess which platforms best suit their work. Lin and Love are among many public health professionals presenting on AI applications during APHA’s 2025 Annual Meeting and Expo in November, addressing topics including wastewater surveillance, police bias, pesticide use, cancer screenings, digital health literacy in adults, and much more.
As AI technology continues advancing, public health’s challenge lies in ensuring ethical implementation, maintaining community trust, and developing workforce capacity to leverage these powerful tools while preserving the human judgment and compassion that remain irreplaceable in protecting population health.
