AI Tool for Cancer

(ACTIVATE Trial)

Overseen By Kenneth L Kehl, MD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Dana-Farber Cancer Institute

Disqualifiers: Pregnant, Prisoners, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial focuses on developing an AI tool called MatchMiner-AI to match cancer patients with suitable clinical trials by analyzing their electronic health records. The researchers aim to test whether AI-triggered notifications can better inform oncologists about trial options for patients with progressing cancer. The trial involves two groups: one where oncologists use the standard MatchMiner-AI website and another where they receive proactive email notifications about potential trials. Adults diagnosed with cancer and receiving care at Dana-Farber Cancer Institute (DFCI), identified through their health records as having progressive disease, are a good fit. As an unphased trial, this study offers patients the opportunity to contribute to innovative research that could enhance future cancer care.

Do I need to stop my current medications for this trial?

The trial information does not specify whether you need to stop taking your current medications. It seems the study is more focused on using electronic health records to match patients with trials rather than changing their treatment.

What prior data suggests that this AI tool is safe for use in clinical trial matching?

Research has shown that MatchMiner-AI and its automatic alerts are safe to use. Studies have found no safety issues or negative effects. MatchMiner-AI assists doctors in finding appropriate clinical trials for cancer patients by automatically matching them to trials, indicating its safety as a tool. The alerts notify doctors when the AI detects signs of a patient's condition worsening, aiding in the identification of suitable clinical trial options. Overall, these AI tools focus on analyzing data and providing information, not administering treatments, which supports their safety. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about the MatchMiner-AI tool because it leverages artificial intelligence to enhance decision-making in cancer treatment. Unlike traditional methods that rely on standard protocols, this AI tool provides oncologists with a dynamic list of clinical trial options, tailored to each patient's unique needs. In addition, an innovative feature of this tool is its proactive notification system, which alerts doctors via email when a patient's condition changes, suggesting timely clinical trial opportunities. This approach not only personalizes treatment options but also speeds up the process of identifying suitable trials, which could significantly improve outcomes for cancer patients.

What evidence suggests that this AI tool is effective for cancer trial matching?

Research has shown that AI-driven alerts can significantly aid in connecting cancer patients with clinical trials. A large study involving over 20,000 cancer patients found that AI alerts effectively identified disease progression and suggested suitable clinical trials. This method is faster and more accurate than traditional approaches. In this trial, participants will join one of two arms: the Standard MatchMiner-AI Workflow, where oncologists access the MatchMiner-AI frontend website for trial options, or the Proactive AI-Triggered Notifications arm, where oncologists receive email notifications with trial options when AI models detect disease progression. This technology could revolutionize the process of finding the right trials for patients, making it more efficient. ^{6 7 8 9 10}

Who Is on the Research Team?

Kenneth L Kehl, MD

Principal Investigator

Dana-Farber Cancer Institute

Are You a Good Fit for This Trial?

This trial is for individuals involved in clinical trials for cancer. It aims to develop a tool that uses health records to find suitable trial participants. There's no specific patient eligibility criteria provided as this study focuses on the development of an AI tool rather than direct patient interventions.

Inclusion Criteria

In 2024, there were approximately 593 oncologists who had outpatient appointments with at least one patient

Clinicians will constitute study participants as well, since they will have the opportunity to provide feedback on the pipeline to be analyzed by the study team

I am 18 or older with a cancer diagnosis and receiving care at DFCI.

Exclusion Criteria

The project will not have any mechanism for identifying, targeting, or excluding pregnant women or prisoners

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Retrospective Data Analysis

Retrospective analysis of data from approximately 70,000 participants to develop and validate the MatchMiner-AI pipeline

Not specified

Prospective Evaluation

Randomization of DFCI patients' MRNs into control and intervention groups with proactive notifications for the intervention group

1.5 years

Follow-up

Participants are monitored for the effect of TrialMatch notifications on clinical trial starts

4 weeks

What Are the Treatments Tested in This Trial?

Interventions

• MatchMiner-AI

Trial Overview The ACTIVATE study is testing MatchMiner-AI, an artificial intelligence tool designed to sift through electronic health records (EHRs) to identify and match eligible patients with appropriate clinical trials for cancer treatments.

How Is the Trial Designed?

Group I: Proactive AI-Triggered Notifications Experimental Treatment 1 Intervention

Oncologists receive email notifications containing a ranked list of potential clinical trial options when AI models detect progressive disease, in addition to standard MatchMiner-AI access.

Group II: Standard MatchMiner-AI Workflow Active Control 1 Intervention

Oncologists can access the MatchMiner-AI frontend website to obtain a list of clinical trial options for all participants.

Who Is Running the Clinical Trial?

Dana-Farber Cancer Institute

Lead Sponsor

Trials

1,128

Recruited

382,000+

National Cancer Institute (NCI)

Collaborator

Trials

14,080

Recruited

41,180,000+

Citations

1. pubmed.ncbi.nlm.nih.gov pubmed.ncbi.nlm.nih.gov/40257799/

Clinical Trial Notifications Triggered by Artificial Intelligence ... Computational tools have been developed to match patients to trials, but these tools are relevant only when patients need new treatment.

2. clinicaltrials.gov clinicaltrials.gov/study/NCT07232043?term=TREATMENt

ACTIVATE: AI-driven Clinical-trial Trial-Information and ... This study aims to develop and evaluate ACTIVATE, an AI-driven tool for clinical trial information and viability assessment using electronic ...

3. dcricollab.dcri.duke.edu dcricollab.dcri.duke.edu/sites/NIHKR/KR/GR-Slides-08-01-25.pdf?Mobile=1&Source=%2Fsites%2FNIHKR%2F%5Flayouts%2F15%2Fmobile%2Fviewa%2Easpx%3FList%3D0095518e%2D671d%2D407a%2Da6a8%2De84adfd1316e%26View%3D1a5349ff%2D8bd1%2D4f91%2Dbc2d%2Daeed6b34b504%26ViewMode%3DDetail%26wdFCCState%3D1

Clinical Trial Notifications Triggered by Artificial ... Artificial intelligence can accelerate clinical cancer research by rapidly identifying clinical trial options for patients. But impact requires integration ...

4. researchgate.net researchgate.net/publication/390980459_Clinical_Trial_Notifications_Triggered_by_Artificial_Intelligence-Detected_Cancer_Progression_A_Randomized_Trial

Clinical Trial Notifications Triggered by Artificial ... A recent RCT [98] involving more than 20,000 oncology patients found that AI-driven notifications to oncologists, identifying disease progression and suggesting ...

5. trialx.com trialx.com/how-is-ai-addressing-patient-recruitment-challenges-and-speeding-up-clinical-trial-timelines/

How is AI Addressing Patient Recruitment Challenges and ... AI is revolutionizing this process by matching patients to trials with speed and accuracy that manual screening can't match.

6. rethinkingclinicaltrials.org rethinkingclinicaltrials.org/news/july-29-2025-ai-triggered-notifications-of-cancer-progression-in-clinical-trials-in-this-weeks-rethinking-clinical-trials-grand-rounds/

July 29, 2025: AI-Triggered Notifications of Cancer ... July 29, 2025: AI-Triggered Notifications of Cancer Progression in Clinical Trials, in This Week's Rethinking Clinical Trials Grand Rounds.

7. clinicaltrials.gov clinicaltrials.gov/study/NCT06888089

Deep Clinical Trajectory Modeling to Optimize Accrual ... This study aims to evaluate the effectiveness of proactive notifications to treating oncologist to optimize participant accrual to clinical trials.

8. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12013351/

Clinical Trial Notifications Triggered by Artificial Intelligence ... This randomized trial examines whether notifying oncologists about genomically targeted clinical trials for eligible patients identified by artificial ...

9. innovations.dana-farber.org innovations.dana-farber.org/technology-in-translation/matchminer-using-ai-to-connect-cancer-patients-with-clinical-trials/

MatchMiner: Using AI to Connect Cancer Patients with ... MatchMiner automates and scales the trial-matching process, helping clinicians uncover more treatment testing opportunities for patients, particularly those ...

10. matchminer.org matchminer.org/

MatchMiner – An open source computational platform for ... MatchMiner is an open source computational platform developed by the Knowledge Systems Group at Dana-Farber Cancer Institute (DFCI) for matching patient- ...