Clinical Research Directory

The Effect of Two Different Generative AI Tools on Nursing Students' Patient Counseling Skills and Motivation Regarding Instructional Materials

The goal of this parallel-group randomized controlled trial is to compare the effects of two different generative artificial intelligence (AI) tools (a video/audio interactive AI avatar versus a written AI learning assistant (chatbot)) on patient counseling skills self-assessment levels and instructional materials motivation in undergraduate nursing students. The main questions it aims to answer are: * Is there a difference in health services counseling skills self-assessment scores between nursing students using an interactive AI avatar and those using a written AI chatbot? * Is there a difference in instructional materials motivation scores between nursing students using an interactive AI avatar and those using a written AI chatbot? Researchers will compare Intervention Group 1 (students interacting asynchronously with a video and audio interactive AI avatar) to Intervention Group 2 (students interacting asynchronously with a written AI chatbot) to see if the AI interaction channel (video/audio avatar vs. text chatbot) significantly impacts student counseling self-efficacy and learning motivation. Participants will: * Complete baseline pre-test questionnaires, including a Demographic Information Form, the Generative Artificial Intelligence Usage and Competence Scale, and the Counseling Skills Self-Assessment Scale. * Conduct patient education and counseling practice over at least 2 to 3 asynchronous sessions using their assigned AI tool on a standardized clinical case scenario. * Complete post-intervention questionnaires, including the Counseling Skills Self-Assessment Scale, the Instructional Materials Motivation Scale, and an Application Feedback Form.

GENERATİVE AI-SUPPORTED NURSİNG PROCESS EDUCATİON AND NURSİNG STUDENTS' LEARNİNG OUTCOMES

This randomized controlled trial evaluated the effect of generative artificial intelligence (AI)-supported education in teaching the nursing process on nursing students' learning outcomes. The study was conducted with undergraduate nursing students enrolled in the Nursing Process course for the first time at a foundation university in Istanbul, Türkiye. After a 7-week instructor-centered theoretical course, students were randomly assigned to an intervention or control group using computer-based simple randomization. Over three consecutive weeks, the intervention group worked on three patient case scenarios using a generative AI platform (Gemini), guided by pre-defined themes and prompts covering data collection, nursing diagnosis, planning, and implementation. The accuracy, consistency, and alignment of AI-generated responses with the nursing process steps were then discussed in class. During the same period, the control group completed three different case studies using the instructor's standard care plan template. Nursing process knowledge, self-efficacy in clinical performance, and clinical decision-making confidence and anxiety were measured before and after the intervention, and attitudes toward artificial intelligence and the course were measured after the intervention. A total of 173 eligible students were randomized (intervention n = 85; control n = 88), and the study was completed with 140 students (intervention n = 68; control n = 72). Students who were repeating the course or were horizontal or vertical transfer students were excluded. The primary outcome was nursing process knowledge, measured with a researcher-developed Nursing Process Knowledge Test. Secondary outcomes were measured with the Self-Efficacy in Clinical Performance Scale, the Nursing Anxiety and Self-Confidence with Clinical Decision Making Scale, and the Attitude Toward Artificial Intelligence and Its Course Scale. Data were collected through electronic forms and analyzed using IBM SPSS 22.0.

Impact of Generative AI on University Students' Learning Processes and Critical Thinking

This study is a randomized, controlled trial with a pre-test/post-test design, conducted to determine the effects of Generative AI (GenAI)-supported learning on academic achievement, learning efficiency, and critical thinking within a university setting. The study population consists of students from the Dialysis Program at Bingöl University's Vocational School of Health Services; the sample comprises 100 volunteer students who met the inclusion criteria and were randomly assigned to either an experimental group (n=50) or a control group (n=50). The experimental group will participate in a "Generative AI-Supported Learning Program" over the course of one month-meeting two days a week for a total of eight 60-minute sessions-covering topics ranging from effective prompting techniques to case analysis and academic ethics; meanwhile, the control group will continue with their routine educational activities. Data will be collected using a Demographic Information Form, the Academic Achievement Inventory, the Critical Thinking Disposition Scale, and the Artificial Intelligence Dependency Scale, and will be analyzed using biostatistical methods (t-tests, ANCOVA, and effect size calculations).

AI-Driven Video Avatars vs. Customized GPTs: Professional English Learning Among Nursing Students

The goal of this study is to evaluate and compare the effectiveness of two generative artificial intelligence technologies (an interactive AI video avatar vs. a personalized GPT) in enhancing professional English learning, overall tool satisfaction, and attitudes toward generative AI. The study will be conducted in undergraduate third-year nursing students enrolled in a professional English course at a university health sciences faculty in Türkiye. The main questions it aims to answer are: * Is there a significant difference in professional English knowledge test scores between nursing students using an interactive AI video avatar and those using a personalized GPT? * Is there a significant difference in attitudes toward generative AI in English learning between students using the interactive AI video avatar and those using the personalized GPT? * Is there a significant difference in satisfaction levels regarding the assigned AI educational tool between the two intervention groups? Researchers will compare students assigned to the Interactive AI Video Avatar Group (interacting with visual and auditory embodied avatars for face-to-face communication simulations) with students assigned to the Personalized GPT Group (interacting via a text/voice-based dialogue interface) to see if the interface modality affects learning performance, student satisfaction, and AI attitudes. Participants will: * Complete baseline questionnaires before the intervention, including a descriptive information form, a Professional English Knowledge Test, the Generative Artificial Intelligence Attitude Scale (GenAIAS), and a Generative AI Usage and Competence Scale. * Use their randomly assigned AI teaching tool (interactive video avatar or personalized GPT) as a supplementary learning partner throughout the semester. * Complete post-intervention evaluations at the end of the semester, including the Professional English Knowledge Test, GenAIAS, and an evaluation form to rate tool satisfaction.

AI-Generated Video Distraction Via Virtual Reality for Fear and Pain During Pediatric Circumcision

This randomized controlled trial evaluated the effect of artificial intelligence-generated video distraction delivered via virtual reality on procedural fear and pain in children undergoing circumcision. A total of 80 children aged 4-12 years were assigned to an intervention group (n=40) or a control group (n=40). Children in the intervention group received AI-generated video distraction via virtual reality, whereas children in the control group received routine care. Pain and emotional responses were assessed from the perspectives of the child, parent, and nurse. Physiological parameters were also measured before and after the procedure. The study aimed to determine whether AI-generated video distraction delivered via virtual reality reduces procedural fear and pain during pediatric circumcision.

Teaching Medical Students to Verify AI-Generated Citation Hallucinations

Generative artificial intelligence (GenAI) tools are increasingly used by medical students for literature searching, scientific writing, and research. However, AI-generated citations may contain errors. Some references may not exist or may contain incorrect bibliographic details, while other references may be genuine but may not actually support the claim for which they are cited. This randomized educational study will evaluate whether a structured citation-verification framework called SARA can improve medical students' ability to identify and correct these problems. SARA teaches students to assess four elements of a citation: Source authenticity, Accuracy, Relevance, and Alignment between the cited evidence and the claim being made. Year 3-5 medical students will be randomly assigned to either a 75-minute SARA training session or an attention-matched session on responsible use of GenAI in academic work. Participants will complete citation-verification assessments before training, immediately after training, and 12 weeks later. The main outcome will assess whether students can independently apply the verification approach to an unstructured literature-review task 12 weeks after training, without being prompted to use SARA. The study will also examine which types of citation errors remain difficult, whether students initiate appropriate verification, the quality of their verification, handling of valid citations, and confidence in their judgments. A subgroup of participants will take part in think-aloud and follow-up interviews to explore how they approach citation verification and transfer the strategy to new tasks.

OpenEvidence Safety and Comparative Efficacy of Four LLM's in Clinical Practice

OpenEvidence is an online tool that aggregates and synthesizes data from peer-reviewed medical studies, then producing a response to a user's questions using generative AI. While it is in use by a number of clinicians (including residents) today, there is little to no published data on whether the tool's outputs are accurate and whether this information appropriately informs clinical decision making. Similarly, a number of clinicians are turning to other large language models (LLM's) to assist in decision making when providing clinical care. While there have been a number of studies published on the accuracy of these LLM's responses to medical boards questions or clinical vignettes, there have been few studies to date examining their performance in a real world clinical setting, and even fewer comparing this performance. In this study, investigators have two goals: 1. To determine whether the use of the AI tool "OpenEvidence" leads to clinically appropriate decisions when utilized by family medicine, internal medicine, and psychiatry residents in the course of clinical practice. 2. To determine how the output of the OpenEvidence tool compares with three other commonly-used, publicly-available large language models (OpenAI's ChatGPT, Anthropic's Claude, and Google's Gemini) in answering common questions that residents have in the course of clinical practice. To accomplish study goal #1, investigators have enlisted residents in the above specialties to use the OpenEvidence tool in the course of clinical practice. In order to mitigate any safety risks, the residents will also use a typical reference tool for their question, which is referred to as the "Gold Standard" tool. These tools include PubMed and UpToDate. The residents will: 1. State their clinical question. 2. Query OpenEvidence, capturing their prompt and the OpenEvidence output for data analysis. All residents will undergo training in prompt engineering at the start of the study. 3. State their clinical conclusion based on the OpenEvidence data. 4. Query the Gold Standard Resource. 5. State their final clinical conclusion. 6. Answer a question on whether their clinical conclusion was modified by the Gold Standard reference. 7. Answer a question on whether they had any clinical safety concerns on the output from OpenEvidence. Attending physician Subject Matter Experts (SMEs) matched by specialty with at least 5 years of post-training clinical experience will then evaluate the residents' responses. 5 years was chosen based the book "Outliers" by Malcolm Gladwell, in which he asserts that 10,000 hours of focused practice is needed to achieve expertise in a field. SMEs will be asked to evaluate the residents' initial clinical questions and their conclusions based only on OpenEvidence. They will be asked to rate the clinical appropriateness of those conclusions on a scale of 1-10. For questions where the SME's rate the clinical appropriateness of the residents' conclusions poorly (\< 5/10), they will be asked to review the OpenEvidence output and answer an additional question as to whether the output was incorrect or the resident misinterpreted the output from the tool. To accomplish goal #2, the initial prompt entered by the residents into OpenEvidence will be copied by the research team into ChatGPT, Gemini, and Claude. The outputs from each tool (including OpenEvidence) will be surfaced to SMEs, who will be asked to rate each output based on accuracy, completeness, and bias. Likert scales will be used for these ratings. SMEs will also be asked an open-ended question to identify any patient safety issues from any of the outputs.

Patient Aid for Theory-Driven Health Communication (PATH): Translating Goal-Power Theory Into an Instrument and Generative AI Support for Palliative Care Communication

The goal of this clinical trial is to learn whether an artificial intelligence (AI)-supported communication tool can help improve communication between people receiving palliative care and their healthcare providers. The study will also evaluate a new questionnaire designed to measure the quality of healthcare communication. The main questions this study aims to answer are: 1. Can the new questionnaire accurately measure the quality of communication between participants and healthcare providers? 2. Does using the AI-supported communication tool, called NurseChat+, help participants feel more confident and prepared before meeting with their healthcare team? 3. Does NurseChat+ improve the quality of communication during palliative care visits? Researchers will compare participants who use NurseChat+ together with their usual care to participants who receive usual care alone to see whether the tool improves communication outcomes. The study will be conducted in three stages. First, researchers will develop and test a questionnaire that measures healthcare communication. Next, they will develop and refine the NurseChat+ tool. Finally, they will test the tool in adults receiving palliative care at National Taiwan University Hospital. Participants in the final stage of the study will be randomly assigned to one of two groups. One group will use NurseChat+ before their scheduled medical visits in addition to receiving usual care, while the other group will receive usual care only. Participants will complete questionnaires about their communication experiences during the study.

Implementation of a Blended Online and Offline Teaching Model

This study aims to design, implement, and evaluate a blended online and offline teaching model for Internal Medicine Nursing, integrating generative artificial intelligence (GAI), a virtual simulation platform, card-based exercises, and scenario simulation. The objective is to address key limitations of traditional teaching, including low student engagement, insufficient cultivation of clinical thinking, limited personalized learning, and a disconnect between theory and practice. A mixed-methods approach will be used. All undergraduate nursing students from the 2024 cohort at Changsha Medical University will be enrolled via convenience sampling as the experimental group to receive the new blended model. The 2023 cohort will serve as the control group, receiving traditional teaching. Quantitative data (course grades, satisfaction questionnaires) and qualitative data (semi-structured interviews) will be collected to comprehensively evaluate the model's effectiveness. Expected outcomes include improved student mastery of theoretical knowledge, enhanced practical skills and clinical thinking, increased learning interest, and higher teaching satisfaction. The study intends to provide a replicable, scalable innovative solution for nursing education reform, ultimately contributing to the training of high-quality applied nursing talents. Key problems addressed: Overcoming single-method teaching and poor interaction through GAI and gamification. Enhancing clinical thinking and decision-making via dynamic GAI cases and card-based exercises. Providing personalized learning paths and instant feedback using GAI technology. Bridging the theory-practice gap with high-fidelity virtual and scenario simulations. Implementing a multi-dimensional evaluation system beyond final exams to assess comprehensive student abilities.