Generative AI for Medication Counselling and Adherence in Community Pharmacies
Human-AI Collaboration in the Pharmacy: A Cluster Randomized Controlled Trial of Generative AI for Medication Counselling and Adherence
調査の概要
状態
詳細な説明
研究の種類
入学 (実際)
段階
- 適用できない
連絡先と場所
研究場所
-
-
-
Amman、ヨルダン
- Petra University
-
-
参加基準
適格基準
就学可能な年齢
- 大人
- 高齢者
健康ボランティアの受け入れ
説明
Patient Eligibility Criteria
Inclusion Criteria:
Adults aged 18 years or older. Presenting with a new prescription or a refill for a chronic medication requiring counseling within one of the following classes: antihypertensives, oral antidiabetics, lipid-lowering agents, anticoagulants, or inhaled maintenance therapies.
Willing and able to provide informed consent.
Exclusion Criteria:
Presence of acute infections. Diagnosis of psychiatric disorders or oncological conditions. Presence of severe acute illness requiring urgent medical referral. Cognitive impairment precluding informed consent. Hearing or communication barriers that prevent interview completion without the presence of a caregiver.
Inability to provide a follow-up phone number for the 30-day adherence assessment.
Pharmacy and Pharmacist (Cluster) Eligibility Criteria
Inclusion Criteria:
Pharmacies legally registered in Jordan, providing routine prescription dispensing services, having at least one licensed pharmacist available during recruitment hours, and agreeing to participate for the full trial period.
Licensed pharmacists with a minimum of 2 years of clinical experience, working in participating pharmacies, providing direct patient counseling, and consenting to take part in the study.
Exclusion Criteria:
Pharmacies that are already using structured AI-assisted counseling tools as part of their routine practice.
Pharmacists on temporary placement for less than one month. Pharmacists not involved in patient-facing counseling.
研究計画
研究はどのように設計されていますか？
デザインの詳細
- 主な目的：他の
- 割り当て：ランダム化
- 介入モデル：並列代入
- マスキング：4倍
武器と介入
参加者グループ / アーム |
介入・治療 |
|---|---|
|
アクティブコンパレータ：Intervention arm procedures
For all eligible patients in the intervention arm, the pharmacist performed the standard patient assessment and determined which medicine(s) needed counselling.
Then, the pharmacist input a prompt in a de-identified format into ChatGPT®.
The prompt was a request for an easy-to-understand counselling document with information regarding the indications for the medication, dosage, schedule, route, course, missed doses, possible side effects, important precautions, storage, and advice on taking the medicine as prescribed (Appendix A).
The pharmacist ensured that the content generated by the AI was accurate and clear, making corrections where necessary, and then gave verbal counselling to the patient.
|
For all eligible patients in the intervention arm, the pharmacist performed the standard patient assessment and determined which medicine(s) needed counselling. Then, the pharmacist input a prompt in a de-identified format into ChatGPT®. The prompt was a request for an easy-to-understand counselling document with information regarding the indications for the medication, dosage, schedule, route, course, missed doses, possible side effects, important precautions, storage, and advice on taking the medicine as prescribed (Appendix A). The pharmacist ensured that the content generated by the AI was accurate and clear, making corrections where necessary, and then gave verbal counselling to the patient. The AI output was never provided to the patients without pharmacist evaluation. It is worth noting that pharmacists could also reject the AI output as inaccurate, insufficient, hazardous, and inappropriate altogether. Reproducibility was ensured through documenting the date and time, prompt te
他の名前：
|
|
介入なし：Control arm procedures
Pharmacies randomized to the control arm continued to provide usual medication counselling according to their standard routine practice, without access to the AI prompt templates or study AI workflow.
Control pharmacists used their usual professional references, as would occur in routine care, but they were not trained in or asked to use ChatGPT® during the trial period.
|
この研究は何を測定していますか？
主要な結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Percentage of Applicable Counseling Domains Provided Correctly
時間枠：day 0
|
Defined as the proportion of clinically applicable counseling domains communicated accurately during the encounter, compared with a medication-specific reference sheet.
Scored on a 0-100 scale, calculated as (Number of applicable domains correctly informed / Total number of applicable domains) x 100.Correctness score= (Number of applicable domains
|
day 0
|
|
Percentage of Essential Counseling Domains Addressed
時間枠：Day 0
|
Defined as the proportion of essential counseling domains that were addressed during the encounter.
Scored on a 0-100 scale, calculated as (Number of applicable domains addressed / Total number of applicable domains) x 100.
|
Day 0
|
二次結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Number of Counseling Deficiencies Categorized by Clinical Severity
時間枠：Day 0
|
The frequency of omitted or incorrect counseling information, independently assessed by a panel of pharmacists using a 3-point scale: Low Severity (minor wording issues), Moderate Severity (errors leading to sub-therapeutic effects), and High Severity (errors with high potential for significant patient harm).
|
Day 0
|
|
Score on the General Medication Adherence Scale (GMAS)
時間枠：30 Days Post-Encounter
|
Medication adherence assessed via telephone follow-up using the continuous total score from the General Medication Adherence Scale (GMAS).
Higher scores indicate better medication adherence.
|
30 Days Post-Encounter
|
|
Number of Participants Achieving Good Adherence
時間枠：30 Days Post-Encounter
|
The number of participants meeting the validated threshold for "good adherence" based on their GMAS survey responses.
|
30 Days Post-Encounter
|
|
Total Score on the Immediate Patient Understanding (Teach-Back) Assessment
時間枠：Day 0
|
A brief interviewer-administered understanding assessment based on teach-back principles.
Scores range from 0 to 4, with higher scores indicating a better understanding of the medication.
|
Day 0
|
|
Total Score on the Patient Satisfaction Questionnaire
時間枠：Day 0
|
A questionnaire covering clarity, usefulness, confidence, and overall satisfaction.
Total scores range from 5 to 25, with higher scores indicating greater patient satisfaction.
|
Day 0
|
|
Time Spent on Face-to-Face Counseling
時間枠：Day 0
|
Total face-to-face counseling time measured in minutes using audio timestamps from the start of counseling to completion.
|
Day 0
|
|
Number of Encounters Based on AI Output Acceptance Level
時間枠：Day 0
|
The proportion of encounters in which the AI-generated counseling output was fully accepted, edited before delivery, or rejected outright by the pharmacist.
|
Day 0
|
|
Number of AI-Related Discrepancies Identified
時間枠：Day 0
|
The frequency of detected AI inaccuracies prior to counseling, such as omitted counseling points, overly technical wording, or incomplete missed-dose advice.
|
Day 0
|
|
Number of Clinical Near Misses and Safety Incidents
時間枠：Day 0
|
The number of encounters featuring a "near miss" (an AI error identified and corrected by the pharmacist before reaching the patient) or an "incident" (inaccurate information that actually reached the patient).
|
Day 0
|
協力者と研究者
スポンサー
出版物と役立つリンク
一般刊行物
- Abdel-Qader, D. H., Al Meslamani, A. Z., Lewis, P. J., & Hamadi, S. (2021). Incidence, nature, severity, and causes of dispensing errors in community pharmacies in Jordan. International journal of clinical pharmacy, 43(1), 165-173. https://doi.org/10.1007/s11096-020-01126-w Abdel-Qader, D. H., et al. (2024). A comprehensive analysis of public satisfaction: Community pharmacists' pandemic preparedness in Jordan. Journal of Applied Pharmaceutical Science, 14(8), 160-168. Abdel-Qader, D. H., et al. (2025). Drug-Drug interaction management among pharmacists in Jordan: A national comparative survey. Pharmacy, 137. https://doi.org/10.3390/pharmacy13050137 Abu Hammour, K., et al. (2023). ChatGPT in pharmacy practice: A cross-sectional exploration of Jordanian pharmacists' perception, practice, and concerns. Journal of Pharmaceutical Policy and Practice, 16(1), 115. Ali, S., Shimels, T., & Bilal, A. I. (2019). Assessment of patient counseling on dispensing of medicines in outpatient pharmacy of Tikur-Anbessa Specialized Hospital, Ethiopia. Ethiopian journal of health sciences, 29(6), 727. Campbell, M. K., et al. (2012). Consort 2010 statement: Extension to cluster randomised trials. BMJ, 345. Chan, A.-W., et al. (2015). SPIRIT 2013 Statement: Defining standard protocol items for clinical trials. Revista Panamericana de Salud Pública, 38, 506-514. Elayeh, E. R., et al. (2019). Use of secret simulated patient followed by workshop based education to assess and improve inhaler counseling in community pharmacy in Jordan. Pharmacy Practice (Granada), 17(4). Fattah, F. H., et al. (2025). Comparative analysis of ChatGPT and Gemini (Bard) in medical inquiry: A scoping review. Frontiers in digital health, 7, 1482712. FIP, I. P. F. (2021). Medication review and medicines use review: A toolkit for pharmacists Colophon. FIP, I. P. F. (2025). An artificial intelligence toolkit for pharmacy: An introduction and resource guide for pharmacists. (March). Hammad, E. A., et al. (2022). Feasibi
研究記録日
主要日程の研究
研究開始 (実際)
一次修了 (実際)
研究の完了 (実際)
試験登録日
最初に提出
QC基準を満たした最初の提出物
最初の投稿 (実際)
学習記録の更新
投稿された最後の更新 (実際)
QC基準を満たした最後の更新が送信されました
最終確認日
詳しくは
本研究に関する用語
追加の関連 MeSH 用語
その他の研究ID番号
- Petrauniversity
個々の参加者データ (IPD) の計画
個々の参加者データ (IPD) を共有する予定はありますか?
医薬品およびデバイス情報、研究文書
米国FDA規制医薬品の研究
米国FDA規制機器製品の研究
この情報は、Web サイト clinicaltrials.gov から変更なしで直接取得したものです。研究の詳細を変更、削除、または更新するリクエストがある場合は、register@clinicaltrials.gov。 までご連絡ください。 clinicaltrials.gov に変更が加えられるとすぐに、ウェブサイトでも自動的に更新されます。