Clinical informatics: Refining medical research with clinical AI

At ISPOR 2024, IMO Health’s Life Sciences team showcased AI’s power to enhance health decision making, advancing the field of clinical informatics.

IMO Health’s Life Sciences team, headed by Xiaoyan Wang, PhD, shared its latest findings in leveraging artificial intelligence (AI) within the realm of clinical informatics and healthcare research at ISPOR 2024.

The International Society for Pharmacoeconomics and Outcomes Research (ISPOR) is a leading global professional organization for health economics and outcomes research (HEOR) with a mission to improve health decision making around the world.

At the May conference, Wang and her team presented results from two studies – one conducted internally and one in conjunction with Merck & Co., Inc. Wang also participated in two AI-focused sessions, demonstrating technology’s power to understand and improve healthcare outcomes.

Below, your 5-minute recap:

Presentation: “Optimizing Systematic Literature Reviews in Endometrial Cancer: Leveraging AI for Real-Time Article Screening and Data Extraction in Clinical Trials”

To tackle the slow and resource-intensive process of gathering scientific data through traditional systematic literature review (SLR) methodologies, IMO Health researchers and Merck developed a new AI system with Generative Pre-Trained Transformer 4 (GPT-4) technology. The tool is designed to screen articles and extract relevant data from clinical trials, helping to address the rapidly growing volume of medical content quickly and efficiently. The system positively identified the majority (94%) of eligible articles in a fraction of the time required for manual identification, illustrating AI’s ability to streamline review processes and offer precise, timely insights.

Presentation: “Profiling Adverse Events in Multiple Myeloma: Insights from Clinical Trials Via Large Language Models”

Multiple Myeloma’s notable relapse rate and evolving treatment landscape prompted Wang’s team to develop an LLM capable of comprehensively analyzing its adverse effects. Based on an information extraction model, the tool is designed to conduct timely and large-scale analysis of myeloma treatment studies. The study effectively demonstrated AI’s versatility in conducting thorough dataset analysis not only for Multiple Myeloma studies but other therapeutic areas as well, furthering the field of HEOR.

Panel Workshop: “Bridging Real-World Data and Regulatory Decision-Making: The Role of AI in External Control Arm Development”

Wang participated in this workshop about the potential benefits of integrating generative AI to bolster the use and efficacy of Real-World Data (RWD) in External Control Arm (ECA) development. ECA is a clinical trial approach that involves using existing study data or RWD as the control, or comparison, group – as opposed to recruiting a whole new set of live patients who will not gain access to potentially revolutionary treatments in the name of medical research.

Panel Session: “The Future of Data-Driven HEOR Decision-Making Powered by Generative AI: How Soon is Now?”

Wang participated as a speaker in this panel about the opportunities and challenges of generating clinical insights via AI, focusing on its reliability for informed decision-making. In the session, Wang discussed findings from the aforementioned studies, showcasing the vast capabilities of generative AI and LLMs.

Didn’t connect with us at this year’s ISPOR conference? No worries. IMO Health attends, exhibits, and demos at industry events throughout the year. Click here to learn where you can find us next – and don’t be shy!

Ideas are meant for sharing.

Sign up today and have Ideas delivered straight to your inbox.

Latest Ideas​

A lack of specificity in clinical documentation can negatively impact reimbursement, billing, and more. Read on to learn how to protect your
By leveraging IMO Health technology, CyncHealth has scaled data standardization and enriched patient diagnoses in their data warehouses.
Let's explore how better HCC capture can improve payer-provider collaboration, leading to enhanced data quality and more efficient workflows in healthcare.