Chatbot for Hereditary Cancer Risk Assessment

Recruiting at 3 trial locations

Overseen By Julia Cron, MD, FACOG

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Weill Medical College of Cornell University

Disqualifiers: Under 18, Prior genetic testing, others

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

Approved in 1 Jurisdiction This treatment is already approved in other countries

Compensation: Varies

Number of Visits: Unknown

150 Participants Needed

Trial Summary

What is the purpose of this trial?

In this study, the investigators aim to compare a mobile health platform, known as a 'chatbot,' that leverages artificial intelligence and natural language processing to scale communication, to 'usual care' that patients would receive. This comparison will enable the investigators to determine if the chatbot system can improve rates of recommendation for genetic testing among patients at elevated risk of harboring a familial cancer syndrome in an all-Medicaid gynecology clinic. Furthermore, the investigators aim to evaluate facilitators of inequity in regard to patient access to and utilization of genetic testing services.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What data supports the effectiveness of the treatment Chatbot for Hereditary Cancer Risk Assessment?

Research shows that chatbots, which are computer programs that simulate conversation, are promising tools for genetic cancer risk assessment and counseling. They have been found acceptable for moderately complex tasks and can help manage the demand for genetics services by providing high-quality information to patients. ^{1 2 3 4 5}

Is the Chatbot for Hereditary Cancer Risk Assessment safe to use?

The research on chatbots for hereditary cancer risk assessment shows they are generally considered safe and acceptable by users, with participants expressing willingness to use them for sharing genetic information and interacting with healthcare providers. ^{1 2 3 4 6}

How does the chatbot treatment for hereditary cancer risk assessment differ from other treatments?

The chatbot treatment for hereditary cancer risk assessment is unique because it uses artificial intelligence to simulate conversation and automate the collection of personal and family cancer history, making it a scalable and accessible tool for genetic counseling. Unlike traditional methods that require in-person consultations, this approach allows for remote and efficient risk assessment, potentially reaching more individuals who may be unaware of their genetic risk. ^{1 2 3 6 7}

Research Team

Melissa K Frey, MD

Principal Investigator

Weill Medical College of Cornell University

Eligibility Criteria

This trial is for individuals aged 18 or older who are new patients at a gynecology clinic, speak and read English, and have access to text messaging on a phone. They should not have had genetic testing for hereditary cancer syndromes before.

Inclusion Criteria

Scheduled for a New Patient appointment in the gynecology clinic

Speaks and reads in English

Access to a telephone with texting capacity

Exclusion Criteria

I have undergone genetic testing for cancer syndromes.

Does not have access to a phone with texting capabilities

I cannot read or speak English.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Intervention

Participants receive either the chatbot intervention or usual care to assess genetic risk and facilitate genetic testing

2 years

Follow-up

Participants are monitored for the utilization of genetic testing services and barriers to testing

2 years

Treatment Details

Interventions

• Chatbot

Trial Overview The study tests if a chatbot using artificial intelligence can increase recommendations for genetic testing in patients at high risk of familial cancer syndromes compared to the usual care in an all-Medicaid gynecology clinic.

Participant Groups

Group I: Chatbot Experimental Treatment 1 Intervention

Subjects will receive a text message initiating a chatbot conversation that relies on natural language processing to gather personal and family cancer. Subjects are identified by the chatbot as meeting National Comprehensive Cancer Network (NCCN) high-risk criteria. Next, subjects undergo pre-test genetic counseling via the chatbot and then clinicians are notified (via the chatbot portal) that the subject meets high-risk criteria. For subjects meeting high-risk criteria (based on the chatbot evaluation), the clinician will complete genetic counseling and recommend genetic testing during the visit. For subjects interested in genetic testing, the clinician will order genetic testing.

Group II: Usual Care Active Control 1 Intervention

Personal and family cancer history will be collected by the clinician during the subject's visit. Clinicians will evaluate the patient's personal/family history according to National Comprehensive Cancer Network (NCCN) high-risk criteria. For subjects recognized by the clinician as meeting NCCN criteria, the clinician will complete genetic counseling and recommend genetic testing. For subjects interested in genetic testing, the clinician will order genetic testing.

Who Is Running the Clinical Trial?

Weill Medical College of Cornell University

Lead Sponsor

Trials

1,103

Recruited

1,157,000+

Findings from Research

Participants in focus groups found chatbots to be an engaging and acceptable method for consenting to genomic research and managing follow-up actions after receiving genetic results, indicating potential for broader use in healthcare.

Despite limited prior experience with chatbots, most participants expressed willingness to use them for sharing genetic information with relatives, suggesting that these technology-based tools could effectively facilitate communication in genetic counseling.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Patient assessment of chatbots for the scalable delivery of genetic counseling. Schmidlen, T., Schwartz, M., DiLoreto, K., et al.[2020]

Chatbots have been evaluated in seven studies for their effectiveness in genetic cancer risk assessment and counseling, showing a pooled completion rate of 36.7% for risk assessments, indicating they can help streamline the process.

While chatbots show promise in making genetic services more accessible, there is a lack of comprehensive data on user characteristics and their effectiveness compared to traditional care methods.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Chatbot Artificial Intelligence for Genetic Cancer Risk Assessment and Counseling: A Systematic Review and Meta-Analysis. Webster, EM., Ahsan, MD., Perez, L., et al.[2023]

In a study involving 95,166 patients, 64.2% engaged with a clinical chatbot designed to assess hereditary cancer risk, with 89.4% completing the risk assessment, indicating high acceptability and usability of the tool.

The chatbot identified that 25% of users met the criteria for genetic testing for hereditary cancer syndromes, and among those tested, 5.6% had a pathogenic variant, demonstrating its effectiveness in triaging high-risk patients for further evaluation.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Hereditary Cancer Risk Using a Genetic Chatbot Before Routine Care Visits. Nazareth, S., Hayward, L., Simmons, E., et al.[2023]

A qualitative study involving 30 participants revealed that while chatbots are seen as useful for moderately complex tasks in the genetic testing process, they are considered inefficient for very simple or very complex tasks.

Participants expressed a preference for chatbots to complement traditional care rather than replace it, emphasizing the need for access to a clinician as a 'safety net' for more complex inquiries.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Finding the sweet spot: a qualitative study exploring patients' acceptability of chatbots in genetic service delivery. Luca, S., Clausen, M., Shaw, A., et al.[2023]

In a feasibility study involving 103 primary care patients eligible for cancer genetic evaluation, 70% of those who completed a chat with a conversational agent expressed a desire to proceed with genetic testing, indicating the agent's effectiveness in providing pretest education.

The study revealed that while most users found the information sufficient to make a decision, a subset of participants who were unsure about testing spent more time interacting with the agent and requested additional information, suggesting that some patients may still need more personalized support.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Patient Interactions With an Automated Conversational Agent Delivering Pretest Genetics Education: Descriptive Study. Chavez-Yenter, D., Kimball, KE., Kohlmann, W., et al.[2023]

The web-based chatbot ItRunsInMyFamily successfully engaged 14,140 users during a campaign, with 3,204 completing a full family health history assessment, indicating strong interest in hereditary cancer awareness.

The tool identified a wide range of cancers reported by users and their families, highlighting the potential for population-level data collection on family health history and the need for further enhancements to improve user experience.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Using a Chatbot to Assess Hereditary Cancer Risk. Welch, BM., Allen, CG., Ritchie, JB., et al.[2022]

The study demonstrated that using an AI-based chatbot to screen for hereditary colorectal cancer (HCRC) risk factors was feasible, with 11.9% of patients initiating the chat and 96.2% completing it, indicating strong engagement.

Of the participants who screened positive for HCRC risk, 71.3% consented to genetic testing, and 9.3% were found to have a germline pathogenic variant, highlighting the chatbot's potential to enhance genetic screening and identify at-risk individuals.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Using chatbots to screen for heritable cancer syndromes in patients undergoing routine colonoscopy. Heald, B., Keel, E., Marquard, J., et al.[2022]

References

1. United States pubmed.ncbi.nlm.nih.gov

Patient assessment of chatbots for the scalable delivery of genetic counseling. [2020]

2. United States pubmed.ncbi.nlm.nih.gov

Chatbot Artificial Intelligence for Genetic Cancer Risk Assessment and Counseling: A Systematic Review and Meta-Analysis. [2023]

3. United States pubmed.ncbi.nlm.nih.gov

Hereditary Cancer Risk Using a Genetic Chatbot Before Routine Care Visits. [2023]

4. Germany pubmed.ncbi.nlm.nih.gov

Finding the sweet spot: a qualitative study exploring patients' acceptability of chatbots in genetic service delivery. [2023]

5. Canada pubmed.ncbi.nlm.nih.gov

Patient Interactions With an Automated Conversational Agent Delivering Pretest Genetics Education: Descriptive Study. [2023]

6. United States pubmed.ncbi.nlm.nih.gov

Using a Chatbot to Assess Hereditary Cancer Risk. [2022]

7. England pubmed.ncbi.nlm.nih.gov

Using chatbots to screen for heritable cancer syndromes in patients undergoing routine colonoscopy. [2022]