ASCO Partners with Ryght AI to Accelerate Site Selection for Metastatic Breast Cancer CDK4/6 Inhibitor Trial
核心洞察
ASCO (搜索) has partnered with Ryght AI (搜索) to use artificial intelligence for accelerating site selection in the CDK Study, a clinical trial evaluating different starting doses of CDK4/6 inhibitors (搜索) in patients with metastatic breast cancer (搜索).
The AI Site Twin platform analyzes clinical research site data including investigator expertise, operational capacity, and patient populations to reduce traditional feasibility assessment delays from six months to 26 days.
The CDK Study specifically targets older adults with metastatic breast cancer (搜索), addressing an evidence gap in dose optimization for patients over 75 years who have been historically underrepresented in CDK4/6 (搜索) inhibitor trials.
The American Society of Clinical Oncology (ASCO (搜索)) has announced a collaboration with Ryght AI (搜索) to implement artificial intelligence-driven site selection for the CDK4/6 (搜索) Inhibitor Dosing Knowledge (CDK) Study, a clinical trial evaluating different starting doses of CDK4/6 inhibitors (搜索) in patients with metastatic breast cancer (搜索). The partnership aims to dramatically reduce study startup timelines and improve patient enrollment through advanced AI technology.
AI Platform Transforms Traditional Site Selection
ASCO (搜索) is deploying Ryght AI (搜索)'s proprietary AI Site Twin platform to analyze clinical research site data and identify centers best positioned to participate in the trial. The platform evaluates multiple factors including investigator expertise, operational capacity, prior research performance, and access to appropriate patient populations. According to the organizations, this approach is designed to reduce the administrative burden and delays typically associated with traditional feasibility assessments and site activation.
"Patients with metastatic breast cancer (搜索) cannot afford to wait for access to clinical trials," said Julie R. Gralow, MD, FACP, FASCO, Chief Medical Officer and Executive Vice President of ASCO (搜索). "This collaboration aims to activate the most suitable sites faster and reach more patient communities, helping us more quickly determine the most effective and tolerable doses of CDK4/6 (搜索) inhibitor therapies to improve patient outcomes."
The AI platform maintains a continuously updated database of research capacity across clinical sites worldwide. Trial protocols are analyzed against multiple variables to generate a ranked list of potential sites. The technology incorporates feasibility questionnaires and performance analytics while automating the assessment of historical trial performance, competing studies, regulatory history, and enrollment trends.
Dramatic Efficiency Improvements Demonstrated
Ryght AI (搜索)'s published results demonstrate significant operational improvements. A global CRO used the platform to complete an oncology site selection campaign in 26 days—a process that would normally take six months—and secured 43 qualified sites against a target of 13, exceeding their recruitment goal by 330%. The platform has also reported 91% cost savings and a 96% reduction in data acquisition time compared to legacy manual processes.
"Too many metastatic breast cancer (搜索) trials lose precious months in slow, manual, and error-prone site selection processes," said Chadi Nabhan, MD, MBA, FACP, Chief Medical Officer and Head of Strategy at Ryght AI (搜索). "Our mission at Ryght is to transform clinical trial timelines by giving research sponsors and networks like ASCO (搜索) an AI-driven platform that quickly surfaces the right sites for the right studies."
Addressing Critical Evidence Gaps in Older Adults
The CDK Study focuses specifically on dosing strategies for oral CDK4/6 inhibitors (搜索) in older adults with metastatic breast cancer (搜索). Investigators aim to address an important evidence gap related to dose optimization and individualization, particularly because older adults—especially those older than 75 years—have historically been underrepresented in CDK4/6 (搜索) inhibitor clinical trials despite bearing a substantial burden of disease.
ASCO (搜索) indicated that integrating the platform into its research infrastructure will enable the organization to evaluate scalable models for AI-enabled site selection. The effort is intended to improve operational efficiency and broaden access to high-quality evidence generation in oncology, with potential future application across other cancer trials.
Implementation Challenges at Site Level
While AI-driven site selection offers substantial efficiency gains, operational challenges remain at the clinical site level. The algorithm selects sites based on potential derived from published trial histories, investigator publication records, patient population proxies, and historical enrollment data. However, this approach cannot assess real-time factors such as coordinator capacity, pharmacy storage availability, or current competing protocol loads.
CDK4/6 (搜索) inhibitor trials in metastatic breast cancer (搜索) require coordinators who can manage complex eligibility screening, including prior treatment lines, performance status documentation, cardiac monitoring requirements, and concurrent medication reviews. Sites routinely report screen failure rates above 40% on initial enrollment waves, with the root cause typically being startup packages that did not account for actual protocol burden at the coordinator level.
Operational Considerations for Accelerated Timelines
The faster identification of sites through AI platforms creates new challenges for startup assumptions. When traditional manual processes take six months to build a site list, there is typically time for feasibility conversations between clinical operations and coordinators. Compressing this to 26 days produces algorithmically ranked sites but may not ensure sites have been adequately assessed for actual readiness.
As of late 2024, only 11% of sponsors and contract research organizations reported fully implementing AI and machine learning tools to support clinical trial activities, with another 22% reporting partial implementation. ASCO (搜索)'s deployment of Ryght AI (搜索) for a cooperative group oncology trial signals that adoption is moving beyond early pilots into mainstream activation strategy.
The trials that achieve first-patient-in within 45 days of site initiation visits share one operational feature: the feasibility questionnaire is treated as a contract instrument rather than a screening form, with every line item reconciled against the activation timeline before budget approval. When sites are selected by AI platforms and activation timelines are compressed to match the platform's speed, this reconciliation step often gets eliminated, potentially creating downstream operational challenges.