AI-Powered Clinical Trial Matching in Breast Cancer: How Artificial Intelligence Can Help Patients Find Relevant Trials

Finding an appropriate clinical trial can be challenging. Patients and oncologists may need to evaluate hundreds or even thousands of studies while considering cancer subtype, stage, biomarkers, previous treatments, age, location and other eligibility requirements.

Artificial intelligence (AI) is emerging as a potential solution to this problem.

AI-powered clinical trial matching systems can analyze patient information and compare it with clinical trial eligibility criteria, helping identify studies that may deserve further review.

This does not mean that AI can determine whether a patient is eligible for a trial. Instead, AI can function as a research and decision-support tool that helps patients and healthcare professionals discover potentially relevant opportunities more efficiently.

A recent Susan G. Komen article highlighted the growing role of AI in searching for breast cancer clinical trials.

What Is AI-Powered Clinical Trial Matching?

Traditional clinical trial searches often require patients or healthcare professionals to manually review study descriptions and eligibility criteria.

An AI-based system can automate parts of this process.

Depending on the platform, an AI clinical trial matching tool may analyze information such as:

• Breast cancer subtype
• Tumor stage
• Estrogen receptor (ER) status
• Progesterone receptor (PR) status
• HER2 status
• Biomarker or genetic testing results
• Previous cancer treatments
• Age
• Medical history
• Geographic location
• Other eligibility-related information

The system can then compare these characteristics with available clinical trials and potentially rank or prioritize studies for further evaluation.

This approach can be particularly valuable in oncology because eligibility criteria can be highly specific.

Why Clinical Trial Matching Is Difficult in Oncology

Clinical trials are not simply categorized by the name of a cancer.

Two people diagnosed with breast cancer may have very different treatment histories, molecular characteristics and eligibility profiles.

For example, a clinical trial may require:

• A specific breast cancer subtype
• A particular disease stage
• A specific biomarker
• Previous treatment with a particular drug
• No previous exposure to another treatment
• A specific age range
• Adequate organ function
• A particular geographic location

Manually comparing all these variables across numerous studies can take significant time.

The National Cancer Institute (NCI) notes that clinical trial matching requires understanding details about a patient’s cancer, medical history and current health status and comparing them against eligibility criteria.

This is one area where AI and clinical informatics could potentially improve efficiency.

How AI Clinical Trial Matching Works

A simplified AI-powered matching workflow can look like this:

Patient information → Data extraction → Trial database search → Eligibility comparison → Ranking → Human review

1. Patient information is collected

The system may receive structured information such as diagnosis, stage, biomarkers and previous treatments.

Some advanced systems can also process unstructured clinical notes.

2. AI extracts relevant information

Natural language processing (NLP) and large language models can identify important medical concepts from clinical documentation.

For example, an AI system could identify:

HR-positive / HER2-negative breast cancer

from a longer clinical note.

3. Clinical trials are searched

The system searches a database containing clinical trial information.

ClinicalTrials.gov provides searchable information about clinical studies and allows users to filter studies by disease, intervention, location, study status and other criteria.

4. Patient characteristics are compared with eligibility criteria

The AI system evaluates whether the patient’s available information appears consistent with the study requirements.

5. Potential matches are ranked

Some systems can score or prioritize trials so that potentially relevant studies appear earlier in the results.

6. A healthcare professional verifies the result

This is the critical step.

An AI-generated match should not be treated as confirmation of eligibility.

The research team ultimately determines whether a person meets the study’s complete eligibility criteria.

Can AI Find Clinical Trials That Doctors Might Miss?

Potentially, yes.

One important advantage of AI is its ability to process large volumes of information quickly.

Healthcare professionals may not always have time to manually review every potentially relevant study. AI systems can help broaden the initial search and identify trials that may warrant further investigation.

The NCI has also investigated large language models for clinical trial matching. Its TrialGPT research demonstrated the potential for LLM-based systems to assist with trial retrieval, matching and ranking. The NCI reported that the approach reduced screening time in its pilot study.

More recent NCI work also highlights how improved informatics and AI can automate the extraction and comparison of patient information with clinical trial criteria.

AI Clinical Trial Matching Is Not the Same as Medical Advice

This distinction is extremely important.

An AI system may identify a study as a potential match, but that does not mean a patient is eligible.

AI systems can:

• Misinterpret clinical information
• Miss important eligibility criteria
• Use incomplete patient information
• Miss newly updated trial information
• Produce false-positive matches
• Fail to understand complex medical circumstances

For example, a patient may appear to meet the major eligibility criteria but fail a laboratory, medication, organ-function or previous-treatment requirement.

Therefore:

AI should support clinical trial discovery—not replace the clinical trial team or oncologist.

Protecting Patient Privacy When Using AI

Patients should also think carefully about the information they enter into AI tools.

Clinical information can contain highly sensitive personal data.

Before entering medical information into an AI platform, consider:

• Who operates the platform?
• What information does it collect?
• Is the information stored?
• How is the information used?
• Is the data shared with third parties?
• What privacy and security protections are provided?
• Is the platform intended for healthcare use?

Avoid entering identifiable medical records into an unknown AI chatbot simply because it claims to provide clinical trial matching.

When possible, use established clinical trial databases and healthcare-provider-supported tools.

AI Can Also Help Oncologists and Researchers

The impact of AI is not limited to patients.

Clinical trial matching can also help oncology teams and researchers.

Hospitals may use AI to analyze electronic health record (EHR) information and identify patients who could potentially qualify for research studies.

This could help address one of the major challenges in clinical research: finding and enrolling appropriate participants.

AI-assisted matching may potentially:

• Reduce manual screening workload
• Identify potential candidates earlier
• Improve trial recruitment
• Expand the number of trials considered
• Support research coordinators
• Improve access to clinical research

The NCI describes AI and informatics as tools that could make clinical trial matching more efficient and help broaden access to trial opportunities.

AI and Diversity in Clinical Trials

Another potential benefit is improving the identification of patients who may otherwise be overlooked.

Clinical trial participation does not always reflect the diversity of the population affected by cancer.

AI systems that systematically search large patient populations could potentially help research teams identify eligible participants across different communities.

However, technology alone cannot solve disparities in clinical research.

Access to transportation, healthcare, digital tools, language support, financial resources and trial locations can all affect participation.

Therefore, responsible AI development in oncology should focus not only on accuracy, but also on accessibility and health equity.

How Patients Can Search for Breast Cancer Clinical Trials

AI is only one option.

Patients can also use established clinical trial databases.

ClinicalTrials.gov

ClinicalTrials.gov is one of the largest publicly accessible databases of clinical studies.

You can search by:

• Cancer type
• Treatment
• Location
• Study status
• Trial ID
• Sponsor
• Investigator
• Other criteria

Search ClinicalTrials.gov

Its official search guidance explains how to narrow results using disease, treatment, location and study-status filters.

National Cancer Institute Clinical Trial Search

The NCI also provides a cancer-specific clinical trial search tool covering NCI-funded trials and trials at NCI-designated cancer centers.

Find Cancer Clinical Trials — NCI

Susan G. Komen Clinical Trial Resources

Susan G. Komen also provides breast cancer clinical trial resources and information about finding and participating in clinical trials.

Susan G. Komen Breast Cancer Clinical Trials

What Information Should You Have Before Searching?

A clinical trial search becomes much more useful when you have accurate information about your diagnosis.

Depending on the situation, useful information may include:

1. Breast cancer subtype
2. Stage of disease
3. ER status
4. PR status
5. HER2 status
6. Biomarker or genomic results
7. Previous treatments
8. Current medications
9. Relevant medical conditions
10. Age
11. Location and travel limitations

The NCI recommends gathering details about the cancer diagnosis and comparing those details with trial eligibility criteria.

Questions to Ask Your Oncologist About AI and Clinical Trials

If you’re considering an AI-assisted clinical trial search, consider asking:

• Could a clinical trial be appropriate for my cancer?
• What trials are currently available for my cancer subtype?
• Are there trials that match my biomarkers?
• Could an AI-based matching system help identify additional studies?
• How accurate is the matching tool?
• Who verifies the eligibility criteria?
• Where is the trial located?
• How frequently would I need to travel?
• What treatments and tests are involved?
• What costs might I have?
• What are the potential benefits and risks?
• How will my personal health information be protected?

The Future of AI in Clinical Trial Matching

AI-powered clinical trial matching is still an evolving area of oncology technology.

Future systems may combine:

• Electronic health records
• Natural language processing
• Large language models
• Genomic information
• Biomarker data
• Clinical trial databases
• Real-world data
• Interoperability standards

The goal is to move from simply searching for trials toward more intelligent, personalized and continuously updated trial matching.

NCI initiatives are also working toward standardized cancer-specific data elements and interoperability approaches that could support clinical trial matching between electronic health records and trial-matching services.

This could eventually make clinical research opportunities more discoverable for both patients and healthcare professionals.

Recommended Videos & Further Learning

🎥 AI and Breast Cancer Research

Susan G. Komen’s Real Pink podcast includes an episode titled “Leveraging AI in Breast Cancer Research,” providing additional discussion about AI and breast cancer research.

Listen to Komen’s Real Pink Podcast

🎥 Breast Cancer Educational Videos

Komen also provides educational videos covering breast cancer science, biomarkers, treatment and emerging technologies.

Komen Educational Videos

🎥 Komen YouTube Channel

Susan G. Komen — Official YouTube Channel

Follow Breast Cancer Research and AI Updates

For readers who want to follow developments in breast cancer research, AI and clinical trials, the following official channels are useful:

• Susan G. Komen on LinkedIn
• Susan G. Komen on YouTube
• Susan G. Komen website

Related Resources

Clinical Trial Resources

• How to Search for Clinical Studies — ClinicalTrials.gov
• Find Cancer Clinical Trials — NCI
• Steps to Find a Clinical Trial — NCI
• Susan G. Komen Clinical Trials

AI in Oncology

• NCI: Large Language Models Help Match Patients to Clinical Trials
• NCI: AI and Improved Clinical Trial Matching
• Nature Communications: TrialMatchAI

Key Takeaway

Artificial intelligence could make clinical trial discovery faster, more comprehensive and more personalized.

For breast cancer, AI-powered matching systems can potentially analyze patient characteristics and compare them with large numbers of clinical trial eligibility criteria. This may help patients and oncologists discover research opportunities that could otherwise be difficult to identify.

But AI is not a substitute for an oncologist, clinical trial investigator or research coordinator.

The safest approach is to use AI as a discovery and decision-support tool, verify potential matches using authoritative clinical trial databases, and discuss every potential trial with your healthcare team.

As AI and oncology continue to converge, smarter clinical trial matching could become an important part of precision cancer care and research.

Medical Disclaimer

This article is intended for educational and informational purposes only. AI-generated or AI-assisted clinical trial matches should not be considered medical advice or confirmation of eligibility. Clinical trial eligibility is determined by the study investigators according to the official study protocol. Patients should discuss clinical trial options with their oncologist or qualified healthcare professional before making healthcare decisions.

Original Source

This article was independently rewritten and expanded for OncoWiz based in part on the Susan G. Komen article, “Can AI (Artificial Intelligence) Help You Find the Right Breast Cancer Clinical Trial?”, published August 18, 2026.