GPT-Based Digital Assistant Support During Treatment for Induced Abortion or Missed Abortion

Key requirements

Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.

• Ages 18 years and older
• Women only
• No healthy volunteers
• Adult, Older adult

Trial locations and contacts

1 site in 1 country. Contact the study team or a site near you to ask about taking part.

About this study

Official title: Feasibility and Usability of a GPT-Based Digital Assistant for Patients Undergoing Treatment for Induced Abortion or Missed Abortion: A Prospective Single-Arm Interventional Study

Conditions

Missed Abortion, Early Pregnancy Loss, Abortion in First Trimester, Abortion, Medical

Being tested

GPT-Based Digital Assistant

Keywords

Medical abortion, Artificial Intelligence, GPT, Missed abortion, Early Pregnancy Loss, Digital Assistant, Chatbot, Feasibility Study, Patient Satisfaction

Medical subject headings

Abortion, Missed, Abortion, Spontaneous, Patient Satisfaction

What participants receive

What participants receive. In a randomised study each person is assigned to one group by chance.

• GPT-Based Digital AssistantOther

  a digital assistant based on GPT (Generative Pre-trained Transformer) technology, trained specifically to provide empathetic, medically accurate, and guideline-based responses in Hebrew, tailored to the clinical protocols used in our clinic. The assistant is designed to support patients throughout the medication abortion or missed abortion process, from the time of first medication until the follow-up visit. It offers culturally sensitive information in plain language, referring to the clinic or emergency care as needed.

What is being measured

The primary outcome is the main question the study is designed to answer.

1. Feasibility and usage rates of the digital assistant

   Feasibility will be assessed by the percentage of follow-up questionnaire respondents who report using the GPT-based digital assistant during the treatment process. Use will be assessed by a yes/no question in the study-specific, non-validated follow-up questionnaire. The number of respondents and the number of enrolled participants without follow-up data will also be reported.

   Measured: From enrollment to follow-up at 2 weeks

2. Frequency of digital assistant use

   Frequency of use will be assessed among participants who report using the GPT-based digital assistant, as assessed using the study-specific, non-validated follow-up questionnaire. Participants select one of four categories: once, 2-3 times, 4-5 times, or more than 5 times. The percentage of users in each category will be reported.

   Measured: From enrollment through follow-up at 2 weeks

3. Patient satisfaction, usability, and perceived usefulness

   Patient experience will be assessed among participants who used the GPT-based digital assistant, using three items in the study-specific, non-validated follow-up questionnaire: ease of use, perceived usefulness of the information, and overall satisfaction. Each item is rated from 1 (do not agree at all) to 5 (strongly agree). Higher scores indicate greater ease of use, usefulness, or satisfaction. Each item will be reported separately; no combined score will be calculated.

   Measured: at 2 weeks after enrollment

4. Patient-reported decision not to contact medical staff after using the assistant

   The percentage of assistant users who report an occasion when they considered contacting medical staff but felt that contact was unnecessary after receiving a response from the GPT-based digital assistant will be assessed using the study-specific, non-validated follow-up questionnaire. Response options are yes, no, and unsure. The distribution of responses will be reported.

   Measured: at 2 weeks after enrollment

5. Perceived support and availability of answers

   Perceived support will be assessed using two items in the study-specific, non-validated questionnaire: having sufficient support to cope with the process, and being able to obtain answers to questions when needed. Each item is rated from 1 (do not agree at all) to 5 (strongly agree), with higher scores indicating greater perceived support or availability of answers. Baseline and follow-up responses will be reported separately for each item.

   Measured: At baseline before first use and at 2 weeks after enrollment.

6. Self-reported comprehension of treatment instructions

   Self-reported comprehension will be assessed using three items in the study-specific, non-validated questionnaire addressing how and when to take medications, expected symptoms, and when to seek medical assistance. Each item is rated from 1 (do not agree at all) to 5 (strongly agree), with higher scores indicating greater perceived comprehension. Baseline and follow-up responses will be reported separately for each item.

   Measured: At baseline before first use and at 2 weeks after enrollment.

Timeline

From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.

1. First posted5 Oct 2026
2. Study start1 Oct 2026 (estimated)
3. Primary completion30 Jan 2027 (estimated)
4. Study completion30 Jan 2027 (estimated)

Resources

• Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
• Publications (6)Papers the sponsor has linked to this study.
• Other trials for Missed AbortionStudies of the same condition, open and under way.
• What the trial phases meanHow a treatment moves from first tests in people to approval.

More details

For doctors and researchers: how the study is designed, who runs it, and its registry IDs.