Slashing Costs at the Cutting Edge of Medicine
In a groundbreaking study from Mass General Brigham, GenAI has shown the potential to dramatically enhance the efficiency and reduce the costs of clinical trials. The study, published in NEJM AI, introduces the RAG-Enabled Clinical Trial Infrastructure for Inclusion Exclusion Review (RECTIFIER), a Gen AI process designed to screen patients for clinical trial eligibility with unprecedented accuracy and speed.
Samuel (Sandy) Aronson, the study's co-senior author and Executive Director of IT and AI Solutions, emphasized the transformative potential of large language models (LLMs) in clinical trial screening. "We saw that LLMs hold the potential to fundamentally improve clinical trial screening. Now the difficult work begins to determine how to integrate this capability into real world trial workflows in a manner that simultaneously delivers improved effectiveness, safety, and equity."
Clinical trials depend on enrolling participants who meet specific criteria, such as age, diagnoses, and health indicators, to ensure that the results are reliable and applicable. Traditionally, this screening process is labor-intensive, error-prone, and costly. As co-lead author Ozan Unlu, MD, noted, "Screening of participants is one of the most time-consuming, labor-intensive, and error-prone tasks in a clinical trial."
The research team tested RECTIFIER's ability to identify eligible patients for the Co-Operative Program for Implementation of Optimal Therapy in Heart Failure (COPILOT-HF) trial. This trial focuses on recruiting patients with symptomatic heart failure using electronic health record (EHR) data. The researchers crafted 13 prompts to assess clinical trial eligibility, initially testing these prompts on a small group of patients before scaling up to a dataset of 1,894 patients, each with an average of 120 notes.
The results were astounding. RECTIFIER's accuracy ranged from 97.9% to 100%, aligning closely with expert clinicians' assessments. In contrast, human study staff had slightly lower accuracy rates, between 91.7% and 100%. Most notably, the AI model cost approximately $0.11 per patient screened, a significant reduction in costs Vs traditional methods. Co-senior author Alexander Blood, MD, highlighted the broader implications of these findings. "If we can accelerate the clinical trial process, and make trials cheaper and more equitable without sacrificing safety, we can get drugs to patients faster and ensure they are helping a broad population".
Now, consider the transformative cost savings and operational efficiency that might be achieved in the context of your asset management firm. How do business-wide cost reductions of > 10% sound?
We're on an exciting path to redefine what success looks like in the finance world, and we'd love for you to join us. Reach out, let’s start a conversation, and explore how we can work together.
#ai
#artificialintelligence
#machinelearning
