KS Health System Unveils Generative AI Partnership

The University of Kansas Health System announced a partnership with health technology company Abridge to deploy generative artificial intelligence (AI) technology across over 140 provider locations.

The partnership aims to save clinicians time by optimizing patient-provider communication and reducing time spent on clinical documentation, the press release states. Clinicians at the University of Kansas Health system reportedly spend 130 minutes per day outside of work hours on documentation, in addition to time spent answering questions from patients about the information shared during a previous visit.

To combat these administrative burdens, which contribute to the ongoing problem of clinician burnout, the University of Kansas Health System will deploy Abridge’s generative AI solution in a phased rollout across its network.

The tool is designed to identify key points from provider-patient conversations and create summaries in clinicians’ preferred formats, which can then be used to assist clinicians with completing documentation once a patient visit concludes. The technology integrates into EHR workflows to help streamline the process further.

“With Abridge, we have found a powerful solution that addresses the biggest challenge facing our providers — excessive time spent on documentation including non-traditional hours,” said Gregory Ator, MD, chief medical information officer and head and neck surgeon at The University of Kansas Health System, in the press release. “This cutting-edge technology will not only close the documentation cycle in real-time but also improve the overall quality and consistency of our clinical notes. Our partnership with Abridge represents a major step forward in reducing burnout, improving provider satisfaction, and ultimately enhancing the delivery of patient care.”

The press release calls the partnership “the most significant rollout to date of generative AI in healthcare,” highlighting the increased interest in the technology following recent hype about tools such as OpenAI’s ChatGPT.

According to McKinsey & Company, generative AI algorithms, such as ChatGPT, can be used to create new content using existing data, such as audio, videos, images, text, code, and simulations. While the potential applications of this technology in various industries are being debated, its usefulness in healthcare and clinical research has shown some promise.

A recent article published in the Future Healthcare Journal, a publication of the Royal College of Physicians, indicates that generative AI, and its ability to create synthetic data based on real-world data, may be useful for medical education and protecting patient privacy.

In this vein, a study published last month by researchers from Massachusetts General Hospital (MGH) and AnsibleHealth revealed that ChatGPT could pass the United States Medical Licensing Exam (USMLE).

The tool’s responses showed that ChatGPT displayed understandable reasoning and valid clinical insights, which led to increased confidence in trust and explainability. These findings indicate the technology’s potential to advance AI-assisted medical education, the research team concluded.