05 Jun ASCO24: Icahn Mt Sinai Researchers Develop Streamlined Cancer Trial Recruitment to Broaden Access to Diverse Groups
MedicalResearch.com Interview with:
Dr. Bickell
Nina Bickell, MD, MPH
Associate Director of Community Engaged and Equity Research
Co-Leader of the Cancer Prevention and Control Program
Co-Director of the Center for Health Equity and
Community Engaged Research
The Tisch Cancer Institute
Icahn School of Medicine at Mount Sinai
MedicalResearch.com: What is the background for this study?
Response: Recruiting diverse patients to clinical trials is essential to advance cancer treatments, yet accrual remains low. Efficient recruitment requires the ability identify patients at treatment decision points and determine eligibility for open clinical trials – a time and personnel intensive undertaking. We developed an automated Regular Expressions technology to identify, classify and match patients to clinical trials and overcome the limitations of more resource-intensive technologies like Natural Language Processing (NLP).
We created a screener, parser and matcher to: use the electronic health record to identify patients at treatment decision points based on progress notes and imaging reports and classify their cancer type, stage and receptor status; extract and categorize breast, liver and lung cancer trial data based on cancer type, stage, and receptor status from the National Cancer Institute’s ClinicalTrials.gov database; pair eligible patients with relevant trials based on stage and receptor status.
MedicalResearch.com: What are the main findings?
Response: Prospective automated algorithmic review of 18,287 patients with upcoming appointments found 1,866 (10%) were at treatment decision points. Of these, the True Negative rate = 92%. The algorithm reduced the need for manual review by 83%. Among 18,287 breast, liver and lung cancer patients at treatment decision points, stage accuracy varied from 69-95% and receptor accuracy from 76-86%.
MedicalResearch.com: What should readers take away from your report?
Response: Automated informatics platforms can reduce manual review and streamline cancer clinical trial recruitment to foster broader access to novel therapies. Using RegEx provides a simpler, less resource-demanding approach compared to manual and traditional NLP and can be a more accessible approach for community hospitals and smaller cancer centers. Although there are limitations in detecting nuanced patient data, this approach marks a significant step towards more efficient clinical trial processes.
MedicalResearch.com: What recommendations do you have for future research as a results of this study?
Response: Potential future integration of artificial intelligence and large language models could enhance the robustness and adaptability of this method. With further development and integration of advanced technologies, this approach could be adapted for wider use, improving the accuracy and personalization of patient-trial matching in oncology.
MedicalResearch.com: Is there anything else you would like to add? Any disclosures?
Response: No disclosures.
Potential future integration of artificial intelligence and large language models could enhance the robustness and adaptability of this method. With further development and integration of advanced technologies, this approach could be adapted for wider use, improving the accuracy and personalization of patient-trial matching in oncology.
Citation: ASCO 2024 Abstract
Disrupting how we recruit to cancer clinical trials
Nina A. Bickell, Benjamin May, Ihor Havrylchuk, Jimmy John, Sylvia Lin, Radhi Yagnik, Ariana Tao, Grace C. Hillyer, Bruce Rapkin, Nicholas Tatonetti
https://meetings.asco.org/abstracts-presentations/233225
The information on MedicalResearch.com is provided for educational purposes only, and is in no way intended to diagnose, cure, or treat any medical or other condition.
Some links may be sponsored. Products are not endorsed.
Always seek the advice of your physician or other qualified health and ask your doctor any questions you may have regarding a medical condition. In addition to all other limitations and disclaimers in this agreement, service provider and its third party providers disclaim any liability or loss in connection with the content provided on this website.
Last Updated on June 5, 2024 by Marie Benz MD FAAD