Meet our team at HIMSS 2024 in Orlando, FL, March 11 - 15. Schedule a meeting.
was successfully added to your cart.

Generative AI in Healthcare

Quickly Deploy Accurate, Scalable, and Responsible Solutions That Put Large Language Models to Good Use

Build Patient Cohorts

Text-Prompted Patient Cohort Retrieval: Leveraging Generative Healthcare Models for Precision Population Health Management

For population health managers and care management teams, segmenting high-risk patients into cohorts based on their clinical characteristics and history is desirable.

This segmentation not only allows for a better understanding of risk patterns within an individual patient, it also contextualizes these patterns across the broader patient population. Insights from the segmentation could pave the way for crafting intervention strategies tailored to address the nuances of the population.

Using John Snow Lab’s Generative Healthcare models, the ClosedLoop platform enables users to retrieve cohorts using free-text prompts. Examples include: “Which patients are in the top 5% of risk for an unplanned admission and have chronic kidney disease of stage 3 or higher?” or “Which patients are in the top 5% risk for an admission, older than 72, and have not undergone an annual wellness checkup?”

Provide a Natural Language Query Interface for Asking About Patient Histories

Summarize Medical Records

Using Healthcare-Specific LLM’s for Data Discovery from Patient Notes & Stories
This session describes benchmarks and lessons learned from building such a pilot system on data from the US Department of Veterans Affairs, a health system which serves over 9 million veterans and their families. This collaboration with VA National Artificial Intelligence Institute (NAII), VA Innovations Unit (VAIU) and Office of Information Technology (OI&T) show that while out-of-the-box accuracy of current LLM’s on clinical notes is unacceptable, it can be significantly improved with pre-processing, for example by using John Snow Labs’ clinical text summarization models prior to feeding that as content to the LLM generative AI output. We will also review responsible and trustworthy AI practices that are critical to delivering these technology in a safe and secure manner.
Generative AI in healthcare for medical text summarization.

Tuned to summarize:

  • Radiology Reports
  • Biomedical Research
  • Clinical Guidelines
  • Patient Questions
  • Discharge Summaries in Laymen Terms

Accelerate Biomedical Research

Accelerating Biomedical Innovation by Combining NLP, LLM, and Knowledge Graphs
Biomedical research is hampered by the triple challenges of disjointed data, unstructured data explosion, and lack of accessibility. We demonstrate how combining new innovations in NLP and Graph Analytics can act as a potent remedy and accelerate biomedical research, by automatically building knowledge graphs from unstructured documents. We introduce three techniques to fuse disjointed datasets, analyze them as a whole, surface hidden patterns, and answer concrete research questions. Adding a Large Language Model (LLM) provides for a natural language query interface, enabling non-technical domain experts to ask questions in English.

How are Academic Medical Centers, Pharmaceuticals, and Health IT Companies deploying Generative AI Solutions Today?

Lessons Learned Applying Generative AI Models in Healthcare
Generative AI provides healthcare organizations a leap in capabilities on understanding medical language and context – from passing the US medical licensing exam to summarizing clinical notes. They also suffer from a wide range of issues – hallucinations, robustness, privacy, bias – blocking many use cases. This session shares currently deployed software, lessons learned, and best practices that John Snow Labs has learned while enabling the Healthcare AI community to deploy these solutions. It covers the generative AI use cases are being deploying today, the solution architecture used to deliver them, and current benchmarks for deciding between general-purpose versus healthcare-specific GPT models.
David Talby