A new platform is being developed by several major universities with the aim of combating misinformation about public health and healthcare policies.
It is led by the University of Pittsburgh, University of Illinois Urbana-Champaign, UC Davis Center for Health Cloud Innovation and Amazon Web Services.
The platform called Project Heal will use machine learning, synthetic intelligence and predictive analytics to help public health officials move from reactive to proactive in their efforts to tackle health misinformation. Strong.
WHY IS IT IMPORTANT?
Misinformation has long been a challenge to public health, but the pandemic has brought that into sharper relief. For example, the U.S. Department of Health and Human Services estimates that COVID-19 vaccine misinformation cost $50 million to $300 million per day in 2021.
That figure is based in part on the cost of voluntarily refusing COVID-19 vaccination — including hospitalizations, deaths and long-term morbidity — estimated at $1 billion.
Furthermore, as such misinformation increases, efforts to combat it will exhaust public health officials, clinicians, and caregivers.
With the new open source toolkit, Project Heal’s creators aim to inform public health officials exactly when their clarifying communications are most needed to improve outcomes and empower for more individuals to make more informed decisions about their health.
The platform classifies and detects emerging misinformation before it can spread within the community.
As Project Heal contributors explain in an AWS blog post, trained machine learning models classify the likelihood of a statement being misleading and enable classification based on entities and context of the statement.
They then evaluate misleading claims to help assess the severity of the threat to human health.
To explain the unique cultural, historical, and linguistic nuances that influence how different demographic groups respond to misinformation that hinders health equity, and to inform responses remediation, the system also uses retrieval-augmented generation to optimize the output of large language models to create more personalized messages for community targeting.
Once developed and deployed on the AWS cloud, the platform will enable public health officials to manage workloads more effectively by shifting public education tasks from reactive to proactive. dynamic.
BIGGER TREND
Collaborators say that when testing the prototype, public health experts were enthusiastic that the system would be a source of support – especially when there is an intentional delineation between established data sources. verified and unverified.
Groups with low health literacy tend to be more susceptible to misinformation, said Denise Scannell, director of health behavior and social sciences at MITER.
“One of the things that doesn’t exist today – but we are looking at developing – is early warnings, so we can work with people in public health to vaccinate against disinformation and misinformation before it spreads in local communities.” in 2022. “It’s very important.”
Through its partnership with Florida International University, she said, MITER has helped identify COVID-19 vaccine misinformation and disinformation and supported its proactive interventions. community to counter these messages within the Haitian community.
“We’ve increased vaccination rates from almost zero when we started there to thousands.”
ON PROFILE
“It is clear that health misinformation remains a major threat to patient health in the United States and beyond,” said Project Heal collaborators.
Andrea Fox is a senior editor at Healthcare IT News.
Email: [email protected]
Healthcare IT News is a publication of HIMSS Media.
