An interventional study of Text Message -based Navigation Intervenion and Artificial Intelligence based Intervention in Hereditary Breast Carcinoma and Hereditary Malignant Neoplasm, sponsored by Roswell Park Cancer Institute. Not yet recruiting at 1 site in United States. Open to participants aged 18 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-10-21.
Sponsored by Roswell Park Cancer Institute · Not applicable, Interventional, and Screening
This clinical trial studies whether a chatbot can be used to help collect medical history and perform cancer risk assessment among patients undergoing cancer genetic counseling. With the improved cost of genetic testing and growing utilization of genetics in cancer care and risk assessment, there is growing pressure placed on certified genetic counselors. To address this issue, many have turned to artificial intelligence (the branch of computer science that deals with writing computer programs that can solve problems creatively) for practical solutions to re-distribute the workload of certified genetic counselors. The chatbot in this trial uses artificial intelligence technology to analyze information provided by the patient during a phone call. The chatbot then generates a family history summary, family tree (pedigree), and cancer risk related assessments, which may help redistribute the workload for the certified genetic counselor and ultimately make genetic counseling more accessible. Using a chatbot may be helpful in collecting medical history and determining cancer risk assessment among patients undergoing cancer genetic counseling.
PRIMARY OBJECTIVE:
I. To assess the sensitivity and specificity of a chatbot's determination of meeting National Comprehensive Cancer Network (NCCN) criteria for germline genetic testing compared to a certified genetic counselor's determination
SECONDAY OBJECTIVES:
I. To assess the reliability and accuracy of a chatbot-generated cancer-focused family pedigree as determined by a certified genetic counselor.
II. To determine the sensitivity and specificity of a chatbot-generated Tyrer-Cuzick determination of breast cancer risk.
III. To evaluate the proportion of patients in a genetic counseling clinic population with greater than 20% lifetime risk of breast cancer and/or criteria met for germline genetic testing.
IV. To evaluate patient satisfaction using a chatbot for family history collection and breast cancer risk assessment.
V. To evaluate provider satisfaction with use, accuracy, and clinical workflow of chatbot-derived data.
OUTLINE:
Patients receive a text message with chatbot phone number at baseline. Patients then complete a phone call with the chatbot over 10-20 minutes consisting of a structured, genetics-specific interview and receive a chatbot generated provider summary, pedigree/structured data, NCCN flag, and Tyler-Cuzick score, which are routed to clinical team up to 21 days before scheduled genetics appointment.
Roswell Park Cancer Institute is the lead sponsor of 417 studies on the registry; 64 are open to participants now.
Of its 38 completed or terminated interventional studies of FDA-regulated products, 21 (55%) have results posted.
Counted across the registry records on this site, refreshed daily.
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
Exclusion Criteria:
Patients receive a text message with chatbot phone number at baseline. Patients then complete a phone call with the chatbot over 10-20 minutes consisting of a structured, genetics-specific interview and receive a chatbot generated provider summary, pedigree/structured data, NCCN flag, and Tyler-Cuzick score, which are routed to clinical team up to 21 days before scheduled genetics appointment.
Other: Text Message -based Navigation Intervenion · Other: Artificial Intelligence based Intervention
Receive chatbot phone number text message
Complete chatbot phone call
Sensitivity and specificity of chatbot in determining if patient meets National Comprehensive Cancer Network (NCCN) criteria for germline genetic testing
Will assess the sensitivity of a chatbot in determining if a patient meets NCCN criteria for germline genetic testing compared to the gold standard of a certified genetic counselor's (CGC's) determination
Time frame: Up to 21 days before genetics appointment
Accuracy of chatbot generated family history pedigree
Graded by a CGC on a five point scale with 1 = entirely unreliable to 5 = no clinically meaning full errors.
Time frame: Up to 21 days before genetics appointment
chatbot generated Tyrer Cuzick determination of breast cancer risk
To assess chatbot's determination of whether patient's lifetime breast cancer risk is estimated at greater than 20% utilizing the Tyrer-Cuzick algorithm
Time frame: Up to 21 days before genetics appointment
Proportion of patients with greater than 20% lifetime breast cancer risk
Assessed by the Tyrer-Cuzick model
Time frame: Up to 21 days before genetics appointment
Patient satisfaction survey with using a chatbot
Self administered Patient survey assessing satisfaction of using chatbot with responses ranging from strongly agree to Strongly disagree
Time frame: Up to 7 days after genetics appointment
Start is estimated for Nov 2026; primary completion for Nov 2027, 12 months later.
How these figures are worked out, and which studies are left out of them.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is not yet recruiting, as verified in Oct 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Breast Cancer, Familial
Roswell Park Cancer Institute →