Human-AI Collaboration in the Pharmacy: A Cluster Randomized Controlled Trial of Generative AI for Medication Counselling and Adherence
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 发起方
- 入组人数
- 136
- 试验地点
- 1
- 主要终点
- Percentage of Applicable Counseling Domains Provided Correctly
研究概览
简要总结
Medication counseling within community pharmacies is crucial for managing chronic diseases, yet significant challenges regarding correctness and completeness remain in Jordan. Although generative artificial intelligence (AI) can be utilized for patient education, there is a lack of research on clinical impact and safety of AI in medication counseling conducted by pharmacists in real-world practice. The aim of this study is to evaluate the effect of pharmacist-supervised AI-assisted medication counseling on the correctness and completeness of counseling information and 30-day medication adherence among patients in Jordanian community pharmacies.
详细描述
Materials and Methods
This pragmatic, two-arm cluster randomized controlled trial enrolled 136 adult patients across 16 community pharmacies in Jordan (8 clusters per arm). Pharmacists in the intervention arm used a standardized prompt strategy with ChatGPT® to generate counseling drafts, which were then verified and edited before delivery. The control arm provided usual counseling. Co-primary outcomes were correctness and completeness of counseling information (percentage scores based on blinded transcript analysis). Secondary outcomes included 30-day medication adherence (General Medication Adherence Scale [GMAS]), immediate patient understanding, and satisfaction. Data were analyzed using mixed-effects linear and logistic regression models.
研究设计
- 研究类型
- Interventional
- 分配方式
- Randomized
- 干预模型
- Parallel
- 主要目的
- Other
- 盲法
- Quadruple (Participant, Care Provider, Investigator, Outcomes Assessor)
盲法说明
Blinding of pharmacists was not possible because they knew whether they were using the AI-assisted workflow. However, the following layers of blinding were implemented: transcript scorers for correctness and completeness were blinded to group allocation; the statistician analyzed a masked dataset with anonymized arm labels where feasible; patients were not explicitly told the trial hypothesis comparing AI-assisted with usual counselling, only that the study evaluated medication-counselling processes. These procedures are important because cluster trials involving provider behavior are particularly vulnerable to performance and detection biases if blinding is not addressed carefully (Campbell et al., 2012; Hemming et al., 2017).
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 是
入选标准
- •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.
排除标准
- •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.
研究组 & 干预措施
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.
干预措施: pharmacist-supervised AI-assisted medication counseling (Other)
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.
结局指标
主要结局
Percentage of Applicable Counseling Domains Provided Correctly
时间窗: 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
Percentage of Essential Counseling Domains Addressed
时间窗: 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.
次要结局
- Number of Counseling Deficiencies Categorized by Clinical Severity(Day 0)
- Score on the General Medication Adherence Scale (GMAS)(30 Days Post-Encounter)
- Number of Participants Achieving Good Adherence(30 Days Post-Encounter)
- Total Score on the Immediate Patient Understanding (Teach-Back) Assessment(Day 0)
- Total Score on the Patient Satisfaction Questionnaire(Day 0)
- Time Spent on Face-to-Face Counseling(Day 0)
- Number of Encounters Based on AI Output Acceptance Level(Day 0)
- Number of AI-Related Discrepancies Identified(Day 0)
- Number of Clinical Near Misses and Safety Incidents(Day 0)
研究者
Derar H. Abdel-Qader
Clinical Professor
University of Petra