Clinical Research Directory

The Effect of Artificial Intelligence-Supported Intramuscular and Subcutaneous Injection Training on Nursing Students

The complexity of healthcare services and technological advances today have necessitated the adoption of innovative approaches in nursing education. Among these innovative approaches, artificial intelligence (AI) has established itself as a technology that is increasingly present in nursing education processes, offering a supportive, personalized, and interactive learning experience. AI's contributions to nursing students' acquisition of fundamental competencies such as clinical decision-making, skill development, and critical thinking are rapidly increasing. Especially in high-risk, invasive, and clinically skill-intensive applications, AI-supported educational models both enhance learning quality and support patient safety. Intramuscular and subcutaneous injections are among the basic invasive skills that nursing students must learn. These applications require a high level of cognitive and psychomotor competence from students. Incorrect injection practices can lead to complications such as drug absorption problems, nerve damage, hematoma, or infection, making it critically important to teach these skills correctly and safely. In this context, AI-supported education systems stand out as an effective tool for teaching injection skills. Artificial intelligence-based chatbots provide students with both theoretical knowledge and practical guidance. For example, before injecting a muscle group, a student can learn about the anatomy of the muscle, determine the correct angle, and remember precautions against potential complications through the chatbot. Artificial intelligence also reinforces the learning process by instantly answering students' questions, preventing the acquisition of incorrect information. Recent studies emphasize that AI-supported learning tools positively influence students' attitudes toward learning, increasing their motivation and academic satisfaction levels. Accordingly, the integration of AI-based technologies in the process of training future nurses is no longer an option but a necessity. Particularly in complex and delicate skills such as intramuscular and subcutaneous injections, AI-supported chatbots can facilitate student learning, increase skill accuracy, and support clinical safety. Therefore, it is crucial for nursing education programs to combine artificial intelligence technologies with pedagogical foundations to provide student-centered, safe, and effective learning environments.

How Pediatric Nurses' Reasoning Skills Affect Quality Nursing Care

This descriptive study aims to examine the impact of pediatric nurses' hypothetical and creative reasoning skills on the quality of nursing care. The research seeks to answer the following questions: Do the sociodemographic characteristics of pediatric nurses influence the quality of nursing care they provide? Do pediatric nurses' hypothetical and creative reasoning skills affect the quality of the nursing care they deliver? Participants will be asked to select the response that best reflects their own perspective for each item. This process will take approximately 10 minutes.

RTSS Adoption Into Physiotherapists Documentation

The Rehabilitation Treatment Specification System (RTSS) is a framework that aims to support clinicians in reasoning and documenting how to deliver rehabilitation. This was explored in a pilot study in 2023 that tested the feasibility of a 6-week teaching programme aiming to support the adoption of the RTSS into practise of physiotherapists and subsequently measure its effect on clinicians reasoning of treatment. Whilst clinical reasoning scores improved, adoption of the framework remained low. Interviews within this study revealed the difficulty clinicians experienced in transitioning to documenting the RTSS. Further local work within Guy's \& St Thomas NHS foundation trust (GSTT) resulted in modified integrations of the RTSS into electronic health record systems as well as training, yet adoption still remained limited. With documentation being cited as an influence of RTSS adoption and thus contributing to its clinical benefit, this qualitative study will attempt to make clear what factors facilitate and/or limit RTSS documentation adoption, and how they exert their influence. The findings from this study will inform the design of interventions that will aid future study of benefit of the RTSS on physiotherapy practice. To achieve these aims, interviews will be conducted virtually via MS Teams, by the lead researcher, with approximately 12-16 volunteering physiotherapists who have attempted to document the RTSS, within the site of GSTT. The interviews will last approximately 1 hour, and will be partially structured in nature to invite in-depth discussion of topic. Analyses of the data will be performed by a team of 3 clinical academics working between GSTT and King's College London with study findings to be disseminated in a peer-reviewed journal and at professional conferences

AMIE's Clinical Conversational Abilities in an Urgent Care Setting

The purpose of this study is to determine the feasibility of a conversational artificial intelligence (AI) system to have a meaningful clinical conversation with a patient prior to an urgent care visit with their primary care physician. In this study, patients who are seeking an urgent care visit (that is, any type of medical visit with their primary care provider for a new complaint) will first have a conversation with an AI system. This interaction with the AI system will happen less than a week before their visit with their physician, and will be supervised by an independent physician who will interrupt in case there are any concerns about patient safety. After the interaction, a summary of the conversation will be sent to the patient's PCP, who will review prior to the in-person visit. The researchers will investigate: * Patient views on the AI system * PCP views on the AI system * Overall safety, as measured by the physician safety supervisor * Quality of clinical conversations, measured by standardized rubrics * Quality of diagnostic and management plans generated by the AI; these will not be shared with the patient or physician, but will be generated after the fact and compared with the actual diagnosis and management plan.