Artificial Intelligence

Large language models can provide a big boost here for providers, says the CEO of Medicomp. But algorithms should be trained on hierarchical condition categories for risk adjustment – and challenges with data quality and bias need addressing.

There are a variety of applications of ChatGPT and LLMs in healthcare, and various uses that have the potential to help or harm patients. Dr. Srinivasan Suresh, VP, CIO and CMIO at UPMC Children's Hospital of Pittsburgh, digs into these tools.

The National Institutes of Health may seek as much as $200 million to acquire a new electronic health record that does not depend on institutional knowledge to maintain – and can handle continuous machine learning validation. 

Ram Rimal and Mike Plesh from UNC Health preview their HIMSS24 panel session, where they'll review how multiple stakeholders across UNC created a framework for adopting both vendor and in-house artificial intelligence applications.

And the tool deployed at Arizona-based SimonMed, which complements the work of subspecialty-trained radiologists, has a 96.9% to 100% sensitivity range per bone, research shows.

Artificial intelligence can help infusion centers lower patient wait times and reduce staff overtime, while supporting growth, says Ashely Joseph, vice president of infusion centers client services at LeanTaaS.

Dr. Howard Strasberg, Wolters Kluwer’s VP of informatics and an HL7 CDS working group chair, said the HIMSS24 session he is co-presenting will discuss a variety of FHIR-based standards, CDS Hooks and other tools that can help bring AI into workflows.  

Automation is helping staff save time and reducing the potential for keyboard errors, its CIDO says. Artificial intelligence is also enhancing medication history data for 81% of all available home medications so patient records contain fewer gaps.