Cleveland Clinic Deploys AI Platform to Accelerate Clinical Trial Recruitment Across Multiple Specialties
核心洞察
Cleveland Clinic has launched Dyania Health (搜索)'s Synapsis AI (搜索) platform across its clinical research enterprise following successful pilot programs in cardiology, oncology, and neurology.
The AI platform identified melanoma (搜索) trial patients in 2.5 minutes with 96% accuracy, dramatically outperforming specialized nurses who required over 400 minutes for similar accuracy.
For a rare heart disease trial, the system screened 1.2 million records and identified 30 eligible participants in one week, compared to 14 patients found through routine methods over 90 days.
Cleveland Clinic has rolled out Dyania Health (搜索)'s Synapsis AI (搜索) platform across its entire clinical research enterprise, marking a significant advancement in addressing the persistent challenge of clinical trial recruitment. The deployment follows successful pilot programs in cardiology, oncology, and neurology that demonstrated the technology's ability to dramatically accelerate patient identification for research studies.
The collaboration aims to tackle one of medicine's most stubborn bottlenecks: approximately 80% of clinical trials fail to meet enrollment timelines, and 50% of trial sites cannot recruit any patients at all. By automating chart review through medically trained large language models, the platform promises to expand patient access to potentially life-saving therapies.
Remarkable Speed and Accuracy in Oncology
The platform's capabilities were rigorously tested in a melanoma (搜索) trial led by Aaron Gerds, M.D., M.S., Deputy Director for Clinical Research at Cleveland Clinic's Cancer Institute. The results, presented at the American Society of Clinical Oncology annual meeting, revealed striking performance differences.
Synapsis AI (搜索) identified appropriate trial patients in an average of 2.5 minutes with 96% accuracy. In comparison, a melanoma (搜索)-specialized nurse achieved 95% accuracy but required 427 minutes, while an oncology research nurse reached 88% accuracy in 540 minutes. This represents a more than 170-fold improvement in speed while maintaining clinical-grade accuracy.
"The future of medicine depends on building research systems that are precise, efficient, fair, and deeply connected to patient care," said Lara Jehi, M.D., Chief Research Information Officer at Cleveland Clinic. "Through our innovative work with Dyania Health (搜索), we are creating an AI-driven foundation that helps identify the right patients for the right trials at the right time."
Transforming Rare Disease Trial Recruitment
The platform's impact proved equally dramatic in cardiology applications. For the DepleTTR-CM trial, a Phase 3 study examining transthyretin amyloid cardiomyopathy (搜索) (ATTR-CM (搜索)) - a rare, progressive, potentially fatal heart muscle disease - the system demonstrated unprecedented screening capabilities.
The AI analyzed more than 1.2 million patient records, reviewing 1,476 in just one week and correctly identifying 30 eligible participants. This compared favorably to routine recruitment methods that yielded only 14 patients over 90 days. The results were presented at the American College of Cardiology meeting by Trejeeve Martyn, M.D., Director of Heart Failure Population Health at Cleveland Clinic.
Beyond speed, the platform expanded recruitment reach by identifying patients from a broader range of clinical sites within the health system, widening patient representation and community engagement compared to typical processes that usually limit trials to main hospital campuses.
Advanced Technology Integration
Synapsis AI (搜索) employs medically trained large language models to abstract and interpret diverse data sources including clinical notes, medical records, imaging, and pathology reports. The system combines this information with additional factors such as organ function and age to draw accurate medical conclusions.
The platform integrates directly with electronic medical records and operates through tech-enabled workflows. By converting medical records into structured, searchable data, it enables real-time, precision-matched patient identification based on complex, trial-specific eligibility criteria. Importantly, the system generates understandable justifications for inclusion or exclusion criteria, a critical requirement for trial coordinators.
Expanding Into Neurology
Cleveland Clinic and Dyania Health (搜索) are currently validating and deploying new applications in neurology, including movement disorders (搜索) and other neurodegenerative conditions (搜索). The teams have annotated de-identified medical records to benchmark accuracy and improve patient identification for complex neurological conditions, with the goal of accelerating access to both care and clinical trials.
"Academic medical centers like Cleveland Clinic are home to some of the most advanced clinical research in the world, yet they often face significant challenges when trying to connect patients to trials – challenges rooted in complexity, time and fragmented data," said Eirini Schlosser, founder and CEO of Dyania Health (搜索). "Through our collaboration with Cleveland Clinic, we are creating a new standard where AI enables faster connections between patients and potentially life-changing trials."