Health TrialsbyHealthPanel

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

ConditionsMissed AbortionEarly Pregnancy LossAbortion in First TrimesterAbortion, Medical
Trial statusNot yet recruiting
Trial phaseNot applicable
Trial typeInterventional
Biological sexFemale
Age18+
SponsorWolfson Medical Center

About this trial

We have developed 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 goal of this interventional study is to learn about the feasibility, usability, and acceptability of a GPT-based digital assistant for patients undergoing medication abortion or treatment for missed abortion.

The study aims to assess use of the digital assistant, patient-reported usability, usefulness and satisfaction, perceived support, comprehension of treatment instructions, and decisions about contacting medical staff.

Participants already receiving standard care for medication abortion or missed abortion at the clinic will be offered access to the digital assistant immediately after enrollment. They may use the assistant freely at home throughout their treatment process and will complete baseline and follow-up surveys about their experience, emotional state, and any additional contacts with the clinic.

Eligibility criteria

This trial does not accept healthy volunteers

Qualifiers

Undergoing medical abortion (up to 9 weeks gestation) or treatment for missed abortion (up to 12 weeks gestation)

Hebrew-speaking

Signed informed consent

Disqualifiers

No access to a smartphone or internet at home

Non-Hebrew speakers

Trial design

Design model

Single group

Treatments tested in this trial

  • GPT-Based Digital Assistant

    Other intervention

    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.

Treatment groups

100 Participants
are divided into 1 treatment group
Group A: GPT-Based Digital Assistant SupportExperimental treatment 1 intervention

Trial outcomes

Primary outcomes

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.

Time frame
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.

Time frame
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.

Time frame
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.

Time frame
at 2 weeks after enrollment

Secondary outcomes

1

Participant suggestions for improvement

Suggestions for improvement will be collected using the open-ended follow-up question asking participants what one thing they would change or improve in the GPT-based digital assistant. Responses will be summarized qualitatively and grouped into recurring themes.

Time frame
at 2 weeks after enrollment
2

Insights into integration into reproductive care

An exploratory qualitative synthesis of participant suggestions for improvement will identify themes potentially relevant to integrating the digital assistant into routine reproductive care. This assessment will use responses to the open-ended follow-up question asking what participants would change or improve in the assistant and will not generate a numerical score.

Time frame
at 2 weeks after enrollment

Other outcomes

Locations

1

Map coordinates are unavailable for these locations. Locations are shown below instead.

Edith Wolfson Medical Center Status unavailable Holon, Central DistrictIsraelIsrael

Sponsors and contacts

Click on the lead sponsor to view all of their trials.

Wolfson Medical Center

Lead sponsor

Source ClinicalTrials.gov

This trial is not recruiting at the moment. You can still explore other options: