Developing an AI Pharmacy Chatbot for the Population of Hong Kong
Trial statusRecruiting
Trial phaseNot applicable
Trial typeInterventional
Biological sexAll
Age18+
SponsorThe University of Hong Kong
About this trial
The primary objective of this study is to is to develop a conversational AI service (chatbot) in Hong Kong to assist patients and caregivers with inquires related to Hospital Authority (HA)-prescribed medications, and to evaluate its effectiveness in answering medication-related questions. The main questions it aims to answer are:
1. How satisfied are the patients and caregivers with this pharmacy chatbot? 2. How will the pharmacy chatbot impact eligible patients or caregivers on their (or the patient they are caring for) medication adherence, knowledge, and the consultation time with HA pharmacists?
There will be an intervention group and a control group:
1. The intervention group will be invited to use the AI Pharmacy Chatbot online for 7 days through WhatsApp, a commonly used social media platform in Hong Kong. They can inquire about their medications prescribed under HA and get instant, validated answers from the chatbot. 2. The control group will not use the chatbot during the intervention period.
To evaluate the chatbot's usability, researchers will measure patient satisfaction through usability questionnaires issued to the intervention group after their intervention period. Differences in medication adherence, medication knowledge, and HA pharmacist consultation time will also be measured between the intervention and control groups after the intervention period, to determine the chatbot's impact.
Eligibility criteria
This trial accepts healthy volunteersQualifiers
Patients aged 18 years or older diagnosed with either hyperglycaemia, hypertension, or hyperlipidaemia, and currently receiving medication prescribed by the Hospital Authority in Hong Kong.
Caregivers aged 18 years or older for patients described above.
Disqualifiers
There is no exclusion criterion, but they should meet the inclusion criteria above.
Trial design
Design model
Parallel
Treatments tested in this trial
An AI pharmacy chatbot offering information related to HA-prescribed medication for hyperglycaemia, hypertension, and hyperlipidaemia
Other interventionIt is a chatbot for HA-prescribed medication used for treating hyperglycaemia, hypertension, and hyperlipidaemia, available through WhatsApp. All the responses will be extracted from a database, in which the content was obtained from and validated by pharmacists from the Chief Pharmacist's Office of the Hospital Authority in Hong Kong. The intervention period will last for 7 days.
Treatment groups
280 Participants
are divided into 2 treatment groupsGroup A: Pharmacy chatbot intervention groupExperimental treatment 1 intervention
Group B: Control groupNo intervention 0 interventions
Trial outcomes
Primary outcomes
1
Medical knowledge
Before the intervention period, all participants will be asked whether they disagree or agree with the following statements on a 5-point Likert scale (Strongly agree, Agree, Neutral, Disagree and Strongly disagree): 1. I understand the main indications of my medications (or the medications of the patient I care for). 2. I understand the potential side effects of my medications (or the medications of the patient I care for). 3. I know how to take my medications (or administer the medications of the patient I care), including the dosage and frequency, thereby promoting my medication adherence. 4. I have concerns or worries about my medications (or the medications of the patient I care for). 5. I can obtain medication-related information efficiently and easily. After the 7-day intervention period, they will be asked again the same questions.
Time frame
1 week2
Medical adherence
Before the intervention period, all participants will be asked whether they disagree or agree with the following statement on a 5-point Likert scale (Strongly agree, Agree, Neutral, Disagree and Strongly disagree): I know how to take my medications (or administer the medications of the patient I care), including the dosage and frequency, thereby promoting my medication adherence. After the 7-day intervention period, they will be asked again the same questions.
Time frame
1 weekSecondary outcomes
1
Response time
We will calculate from the backend the chatbot's response time when responding to user's input (text, image and voice).
Time frame
1 week2
User satisfaction
Participants in the intervention group will be asked whether they disagree or agree to the following statements on a 5-point Likert scale (Strongly disagree, Disagree, Neutral, Agree and Strongly agree): 1. The chatbot is simple to use and user-friendly. 2. The chatbot understands my queries and is able to address them. 3. The chatbot's responses are relevant and sufficient. Moreover, they will also be asked to rate their overall experience with the chatbot on a 5-point Likert scale (Very Good, Good, Moderate, Poor, and Very Poor), and whether they will use the chatbot again in the future and whether they would recommend others to use the chatbot.
Time frame
1 week3
Consultation with pharmacists
Before the intervention period, we will ask all participants their frequency and consultation time with pharmacists. After the 7-days intervention period, we will ask them again whether they have visited any pharmacists during the time, and if so, the frequency and consultation time.
Time frame
1 weekSponsors and contacts
Click on the lead sponsor to view all of their trials.
The University of Hong Kong
Lead sponsor
Laboratory of Data Discovery for Health
Collaborator
Hospital Authority, Hong Kong
Collaborator
Source ClinicalTrials.gov