Related Experiment Video
Updated: Apr 19, 2026
Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
Published on: December 23, 2025
A multi-cohort evaluation of a curriculum-aligned, oncology-focused chatbot in pharmacy education
Zachery Halford1, Nathan Heitz2
1Union University College of Pharmacy, 1050 Union University Drive, Jackson, TN 38305, United States.
Introduction:
Pharmacy students increasingly rely on generative artificial intelligence (AI) for learning support, yet most available tools remain general-purpose models without domain-specific clinical oversight. This multi-cohort study evaluated whether exposure to an expert-reviewed, curriculum-aligned chatbot influenced pharmacy students' confidence, comfort, and attitudes toward AI-assisted learning.
Methods:
A pre-post intervention survey was conducted across two consecutive cohorts with third-year pharmacy students enrolled in an oncology pharmacotherapy course. The intervention consisted of "Chemosabe," a custom GPT chatbot configured with course-aligned content and evaluated through structured pre-deployment review by a panel of oncology-trained clinical pharmacists and fourth-year pharmacy students with prior oncology coursework and practice experience. Anonymous pre- and post-intervention surveys captured AI use and perceptions. Seven attitudinal measures, assessed with 5-point Likert-type scales, were common to both surveys and served as the primary pre-post comparison.
Results:
Across cohorts, 40 pre-intervention and 42 post-intervention surveys were analyzed. In pooled analyses, six of seven attitudinal measures improved from pre to post, with large effects observed for trust in AI accuracy, comfort with AI, and confidence in evaluating AI. Differences were also observed for AI enhancing learning, helping with complex topics, and openness to AI integration. Students reported infrequent experiences with incorrect, misleading, or fabricated information, with 98% encountering such experiences rarely or never. Ninety-three percent would recommend the chatbot to future cohorts.
Conclusions:
An oncology-focused AI chatbot was associated with replicable improvements in pharmacy students' confidence, comfort, and trust in AI as an educational tool, supporting the potential value of clinician-curated, course-specific tools for strategic AI integration into pharmacy education.
More Related Videos
06:28E-Patient Counseling Trial E-PACO: Computer Based Education versus Nurse Counseling for Patients to Prepare for Colonoscopy
Published on: August 1, 2019
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
Related Concept Videos
02:50Combination Therapies and Personalized Medicine
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...
02:50Combination Therapies and Personalized Medicine
01:27Nursing Clinical Information System
A Nursing Clinical Information System (NCIS) is a specialized type of healthcare information system tailored to meet the unique needs of nursing practice. It incorporates the principles of nursing informatics to streamline information management and improve the quality of care delivery.
Critical attributes of NCIS include:
01:21Cancer Survival Analysis
01:26Drug Administration and Therapy Phases: Overview
The pharmaceutical phase focuses on leveraging the physicochemical properties of the drug to design and manufacture an effective product. Variants include orally administered tablets or capsules, topical creams or ointments, and parenteral-delivery solutions or emulsions.
The pharmacokinetic phase...
01:28Biopharmaceutics and Pharmacokinetics: Overview