Cloud-based AI services can help combat health misinformation
A new platform is being developed by several major universities with the aim of combating misinformation about healthcare and public health policy.
It is led by the University of Pittsburgh, the University of Illinois Urbana-Champaign, the University of California Davis Health Cloud Innovation Center and Amazon Web Services.
The platform, called Project Heal, will use machine learning, generative artificial intelligence and predictive analytics to help public health officials shift from reactivity to proactiveness in their efforts to tackle health misinformation.
WHY IT MATTERS
Misinformation has long been a public health challenge, but the pandemic has provided a major relief. For example, the U.S. Department of Health and Human Services estimates the costs of misinformation about the COVID-19 vaccine $50 million to $300 million per day during 2021.
That figure was based on a portion of the cost of voluntarily refusing a COVID-19 vaccination — including hospitalizations, a valuation of lives lost and long-term morbidity — estimated at $1 billion.
Furthermore, as such misinformation spreads, efforts to combat it are causing burnout among public health officials, physicians, and healthcare providers.
With their new open source toolkit, the creators of Project Heal aim to inform public health officials exactly when their insightful communications are most needed to improve outcomes and empower more individuals to make more informed decisions about their health.
The platform classifies and detects emerging disinformation before it can go viral in communities.
As Project Heal staff explain in an AWS blog postTrained machine learning models classify the likelihood that a statement has misleading content and enable categorization based on the statement entities and context.
They then evaluate misleading statements to help assess the severity of the threat to human health.
To account for unique cultural, historical, and linguistic nuances that influence how different demographic groups respond to misinformed rumors that hinder health equity and corrective countermessages, the system also uses retrieval-augmented generation to generate the output of large Optimize language models to generate more personalized messages for targeted communications. communities.
Once the platform is developed and deployed in the AWS cloud, public health officials can manage workloads more efficiently by shifting community education tasks from reactivity to proactivity.
THE BIG TREND
Combating healthcare misinformation trends could help more people make more informed decisions about their health, Project Heal leaders say.
In testing the prototype, public health experts were enthusiastic that the system would be a source of support — especially if there is an intentional delineation between verified and unverified data sources, the employees said.
Groups with low health literacy tend to be more sensitive to misinformation, says Denise Scannell, division manager of health behavior and social sciences at MITER.
“One of the things that doesn’t exist today – but we want to develop – is early warnings, so that together with public health people we can inoculate against misinformation and disinformation before it spreads within the local community,” she said. in 2022. “That is critical.”
Through a partnership with Florida International University, MITER has helped identify misinformation and misinformation about COVID vaccines and supported active community interventions to counter them in the Haitian community, she said.
“We’ve increased the vaccination rate from almost zero when we started there, to somewhere in the thousands.”
ON THE RECORD
“It is clear that healthcare misinformation remains a major threat to patient well-being in the US and abroad,” Project Heal officials said.
Andrea Fox is editor-in-chief of Healthcare IT News.
Email: afox@himss.org
Healthcare IT News is a HIMSS Media publication.