Medical-AI trial: a chatbot to bring hereditary-cancer genetic testing to an underserved population — reducing health inequity (NCT05562778)
An interventional study comparing a chatbot that uses AI and natural language processing against usual care, to see whether it can raise the rate of recommending genetic testing among patients at elevated risk of a familial cancer syndrome, in an all-Medicaid gynecology clinic. It also evaluates drivers of inequity in access to testing. The primary outcome is the proportion recommended for genetic testing. 150 patients; recruiting.
Trial overview (primary data)
- StatusRecruiting
- ConditionsGynecologic Cancer, Hereditary Cancer Syndrome
- InterventionsOTHER: Chatbot
- SponsorWeill Medical College of Cornell University
- Target enrollment150 participants
- Period2023-01-15 〜 2027-12-01
Key points
- An interventional study comparing an AI/natural-language chatbot with usual care to raise genetic-testing recommendation rates among patients at elevated risk of familial cancer syndrome.
- The setting is an all-Medicaid gynecology clinic, an underserved population.
- It also evaluates drivers of inequity in access to and use of genetic testing.
- The primary outcome is the proportion of patients recommended for genetic testing. 150 patients; recruiting.
- It uses AI for access rather than accuracy; an evaluation of recommendation rates and access, not an establishment of counselor replacement or clinical-outcome improvement.
- AI is used as a tool for access rather than accuracy, measured by the share of patients recommended for genetic testing.
1Hereditary cancer syndromes and counseling
Some breast and ovarian cancers stem from hereditary (familial) cancer syndromes caused by changes in genes such as BRCA. Identifying this risk through genetic testing can guide prevention and early detection for the patient and precautions for the family. But genetic counseling and testing are limited by a shortage of specialists and do not reach underserved groups (such as low-income or public-assistance patients) well. This study tests whether an AI chatbot can close that gap.
2Chatbot versus usual care
Per the registry summary, it compares a chatbot using AI and natural language processing against usual care, to determine whether it can raise the rate of recommending genetic testing among patients at elevated risk of a familial cancer syndrome in an all-Medicaid gynecology clinic. It also evaluates drivers of inequity in access to and use of genetic testing.
The primary outcome is the proportion of patients recommended for genetic testing. The size is 150, and it is recruiting.
3What the AI is a tool for
Most medical AI research aims at raising the accuracy of a judgement. The point of this study lies elsewhere: widening access for those it has not reached.
Genetic counselling and testing are limited by specialist capacity and reach the medically underserved poorly. If a chatbot can standardise the time-consuming intake of genetic risk and handle it at volume, that gap might close. The study covers 150 cases at a gynaecology clinic serving Medicaid patients only.
Why it matters
Using AI for access rather than accuracy, with health equity front and center, this design could extend testing to groups previously missed if a chatbot can standardize and scale the intake specialists cannot keep up with (this study evaluates recommendation rates and access, not clinical-outcome improvement).
FAQ
Why does inequity in access to genetic testing matter?
Does the chatbot replace a genetic counselor?
Sources (primary)
Source: ClinicalTrials.gov (U.S. NIH/NLM, public domain). This site does not provide medical advice. Verify the latest and exact details with the official source. This site is not endorsed or certified by the NIH/NLM.
- ClinicalTrials.gov (study record, original)
- NCT ID: NCT05562778