AI Chatbot for Prenatal Nutrition Guidance, Diabetes, Gestational, Pre-eclampsia
Conditions
Keywords
AI chatbot, prenatal nutrition, gestational diabetes, pre-eclampsia, feasibility, usability, technology acceptance, mixed methods
Brief summary
Background: Pregnancy imposes significant physical demands, with complications like gestational diabetes (GDM) and pre-eclampsia posing serious risks. Nutrition is crucial for mitigation, but accessing reliable guidance remains challenging. This study evaluates the feasibility of an AI chatbot providing nutritional guidance for managing these conditions. Methods: In a quasi-experimental design, 100 pregnant women will self-select into either the intervention group (n=50, using an AI chatbot) or control group (n=50, receiving standard care). The primary outcome is usability measured by the System Usability Scale (SUS) at 12 weeks, with an expected mean difference of ≥13 points. Secondary outcomes include technology acceptance (Technology Acceptance Model), user engagement, information accuracy, and changes in dietary knowledge/behaviors. Quantitative data will be analyzed using intention-to-treat and t-tests. Semi-structured interviews with 20 participants will explore user experiences through thematic analysis. Expected Results: The AI chatbot is anticipated to demonstrate superior usability and high user acceptance (TAM \>5.0/7), with improvements in dietary knowledge and behavior. Qualitative findings will provide insights into benefits, barriers, and engagement factors. Conclusion: This study will establish an evidence base on AI chatbot feasibility and acceptance for prenatal nutrition, informing tool optimization and future large-scale trials.
Detailed description
Objectives: This study primarily aims to evaluate the usability of a nutrition AI chatbot for pregnant women by comparing System Usability Scale (SUS) scores between intervention and control groups. Secondary objectives include assessing technology acceptance (Technology Acceptance Model), engagement patterns, information quality (accuracy, comprehensibility, consistency), and changes in nutritional knowledge. Design: A quasi-experimental design with two parallel groups (n=50 each) will be employed. Using self-selection, participants will choose to enroll in the intervention group (access to an AI chatbot plus routine care) or the control group (access to a standardized WeChat information service plus routine care). Routine care for all participants includes standard prenatal clinic visits and printed nutritional materials. The WeChat service for the control group will be operated by a trained research assistant using a pre-defined script during two scheduled windows daily, providing information quoted from the official nutritional leaflets. This isolates the mode of information delivery (AI versus human-facilitated messaging) as the primary variable. Participants: Inclusion criteria: pregnant women aged ≥18 years, able to consent, owning a smartphone with internet access. Exclusion criteria: enrollment in other nutrition interventions or severe mental health conditions impairing technology use. A purposive subsample of 20 participants (10 per group) will complete qualitative interviews. Sample Size: Based on an expected mean SUS score of 78 (SD=12) in the intervention group and 65 (SD=15) in the control group (Cohen's d=0.95), 23 participants per group are required for 90% power at alpha=0.05. Accounting for 50% attrition, 50 participants per group will be recruited. Propensity score matching will be applied to reduce selection bias using variables including age, gestational age, parity, education, and baseline technology use. Measurements: The primary outcome, usability, will be measured using the System Usability Scale (SUS) and the Chatbot Usability Questionnaire (CUQ) at 12 weeks. Technology acceptance will be assessed using the Technology Acceptance Model (TAM). Nutritional knowledge will be evaluated at baseline and 12 weeks using a 15-item questionnaire and the FIGO Nutrition Checklist. Information accuracy and consistency will be assessed by an expert panel rating 150 chatbot responses and repeated submission of 20 test questions. Engagement will be analyzed via application usage logs measuring adherence, intensity, and persistence. Semi-structured interviews will explore user experiences in depth. Data Analysis: Quantitative data will be analyzed using intention-to-treat principles. Primary analysis will compare mean SUS scores between groups using independent samples t-tests, with effect sizes calculated as Cohen's d. Secondary outcomes will be analyzed using similar approaches, with chi-square tests for proportions and linear mixed models for nutritional knowledge change scores. Missing data will be addressed through multiple imputation. Qualitative interview transcripts will be analyzed using thematic analysis with dual independent coding. Study Timeline: Participants will be enrolled over a 6-month period, with each participant completing a 12-week intervention and follow-up period.
Interventions
BEHAVIORALa culturally tailored nutrition AI chatbot for pregnant women
A culturally tailored nutrition AI chatbot for pregnant women , and the AI chatbot support will be available 24/7
Sponsors
Hong Kong Metropolitan University
Study design
Allocation
NON_RANDOMIZED
Intervention model
PARALLEL
Primary purpose
SUPPORTIVE_CARE
Masking
NONE
Intervention model description
A quasi-experimental design will be employed with two groups of 50 pregnant women. The intervention group will access the AI chatbot in addition to routine care, while the control group will receive routine care along with access to a standardized WeChat information service.
Eligibility
Sex/Gender
FEMALE
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Pregnant women aged 18 years or older * Able to provide informed consent in the study language * Own a smartphone with internet access and the WeChat application
Exclusion criteria
* Current enrollment in other nutrition intervention studies * Severe mental health conditions that may impair technology use or ability to provide informed consent
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| System Usability Scale (SUS) | 12weeks | Usability will be assessed using the System Usability Scale (SUS), a 10-item questionnaire with five-point Likert responses. SUS yields a total score ranging from 0 to 100, with higher scores indicating better perceived usability. Scores will be compared between groups at 12 weeks. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Mean Score on the Technology Acceptance Model (TAM) Questionnaire | 12 weeks | Technology acceptance will be assessed using the Technology Acceptance Model (TAM) questionnaire. This 12-item instrument measures two domains: perceived usefulness (6 items) and perceived ease of use (6 items). Each item is rated on a 7-point Likert scale ranging from 1 (strongly disagree) to 7 (strongly agree). Domain scores are calculated as the mean of items within each domain, with higher scores indicating greater perceived usefulness or ease of use. |
| Proportion of Participants Achieving Adequate Engagement Adherence | 12 weeks | Engagement adherence will be measured using application usage logs. Adequate adherence is defined as using the platform at least 3 days per week for at least 10 out of the 12-week intervention period. The proportion of participants meeting this threshold will be reported. |
| Mean Number of Platform Logins per Week | 12 weeks | Engagement intensity will be measured using application usage logs. The average number of logins per week over the 12-week intervention period will be calculated for each participant and reported as a group mean. |
| Mean Number of Queries Submitted per Participant | 12 weeks | Engagement intensity will also be assessed by the total number of queries (questions or requests) submitted by each participant to the platform over the 12-week intervention period, reported as a group mean. |
| Proportion of Chatbot Responses Rated as Accurate by Clinical Expert Panel | 12 weeks | A panel of clinical experts will rate a sample of 150 chatbot responses for accuracy. Responses will be rated as accurate or inaccurate based on alignment with current clinical guidelines. The proportion of responses rated as accurate will be reported. |
Countries
Hong Kong
Contacts
CONTACTBronya Luk, DHSc
PRINCIPAL_INVESTIGATORBronya Luk, DHSc
School of Nursing and Health Sciences, Hong Kong Metropolitan University
Outcome results
None listed