Evaluation of validity and reliability of AI Chatbots as public sources of information on dental trauma

Dental Traumatology, Год журнала: 2024, Номер unknown

Опубликована: Окт. 17, 2024

This study aimed to assess the validity and reliability of AI chatbots, including Bing, ChatGPT 3.5, Google Gemini, Claude AI, in addressing frequently asked questions (FAQs) related dental trauma.

Язык: Английский

---

The Role of ChatGPT and AI Chatbots in Optimizing Antibiotic Therapy: A Comprehensive Narrative Review

Antibiotics, Год журнала: 2025, Номер 14(1), С. 60 - 60

Опубликована: Янв. 9, 2025

Background/Objectives: Antimicrobial resistance represents a growing global health crisis, demanding innovative approaches to improve antibiotic stewardship. Artificial intelligence (AI) chatbots based on large language models have shown potential as tools support clinicians, especially non-specialists, in optimizing therapy. This review aims synthesize current evidence the capabilities, limitations, and future directions for AI enhancing selection patient outcomes. Methods: A narrative was conducted by analyzing studies published last five years across databases such PubMed, SCOPUS, Web of Science, Google Scholar. The focused research discussing AI-based chatbots, stewardship, clinical decision systems. Studies were evaluated methodological soundness significance, findings synthesized narratively. Results: Current highlights ability assist guideline-based recommendations, medical education, enhance decision-making. Promising results include satisfactory accuracy preliminary diagnostic prescriptive tasks. However, challenges inconsistent handling nuances, susceptibility unsafe advice, algorithmic biases, data privacy concerns, limited validation underscore importance human oversight refinement. Conclusions: complement stewardship efforts promoting appropriate use improving Realizing this will require rigorous trials, interdisciplinary collaboration, regulatory clarity, tailored improvements ensure their safe effective integration into practice.

Язык: Английский

---

Building Trust in AI Solutions: The Role of AI in Patient Support (Preprint)

Опубликована: Фев. 20, 2025

Building on the successful engagement and testing with heart failure patients, authors are exploring feasibility of using a voice-activated conversational agent to improve outcomes for patients following gastrointestinal (GI) surgery.

Язык: Английский

---

What Dialogue Content Leads to a Trust Relationship and Behavior Change? Dialogue and Questionnaire Analysis

Опубликована: Апрель 23, 2025

Язык: Английский

---

An In-House Approach to AI: Developing a Custom Chatbot for Library Services

Internet Reference Services Quarterly, Год журнала: 2025, Номер unknown, С. 1 - 13

Опубликована: Апрель 25, 2025

Язык: Английский

---

AI with a Heart: How perceived authenticity and warmth shape trust in healthcare chatbots

Journal of Marketing Communications, Год журнала: 2025, Номер unknown, С. 1 - 21

Опубликована: Май 21, 2025

Язык: Английский

---

Designing an AI Chatbot for Team-Based Diabetes Care: An Iterative Human-in-the-Loop Approach

Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 261 - 276

Опубликована: Янв. 1, 2025

Язык: Английский

---

Evaluating the Reliability and Quality of Sarcoidosis-Related Information Provided by AI Chatbots

Healthcare, Год журнала: 2025, Номер 13(11), С. 1344 - 1344

Опубликована: Июнь 5, 2025

Background and Objectives: Artificial intelligence (AI) chatbots are increasingly employed for the dissemination of health information; however, apprehensions regarding their accuracy reliability remain. The intricacy sarcoidosis may lead to misinformation omissions that affect patient comprehension. This study assessed usability AI-generated information on by evaluating quality, reliability, readability, understandability, actionability chatbot responses patient-centered queries. Methods: cross-sectional evaluation included 11 AI comprising both general-purpose retrieval-augmented tools. Four sarcoidosis-related queries derived from Google Trends were submitted each under standardized conditions. Responses independently evaluated four blinded pulmonology experts using DISCERN, Patient Education Materials Assessment Tool—Printable (PEMAT-P), Flesch–Kincaid readability metrics. A Web Resource Rating (WRR) score was also calculated. Inter-rater intraclass correlation coefficients (ICCs). Results: Retrieval-augmented models such as ChatGPT-4o Deep Research, Perplexity Grok3 Search outperformed across PEMAT-P, WRR However, these high-performing produced text at significantly higher reading levels (Flesch–Kincaid Grade Level > 16), reducing accessibility. Actionability scores consistently lower than understandability all models. ICCs exceeded 0.80 domains, indicating excellent inter-rater reliability. Conclusions: Although some can generate accurate well-structured questions, limited low present barriers effective education. Optimization strategies, prompt refinement, literacy adaptation, domain-specific model development, required improve utility in complex disease communication.

Язык: Английский

---

Retail consumers' conundrum: An in-depth qualitative study navigating the motivations and aversion of chatbots

Journal of Retailing and Consumer Services, Год журнала: 2024, Номер 82, С. 104147 - 104147

Опубликована: Ноя. 13, 2024

Язык: Английский

---

Evaluation and Prototype of Health Counseling LLM Using the Turing Test

Опубликована: Авг. 22, 2024

In 2021, Japan's medical expenses will exceed 45 trillion yen, and the shortage of doctors, especially in remote mountainous areas, is becoming serious, making it difficult to maintain system. We have conducted a study 800 health consultation text data. developed an on-premise counseling LLM system by constructing dialogue flow based on Turing test this using 200 data verified its effectiveness with three professionals. The was comparison experiment between conventional infrastructure focuses exercise guidance analyzes gender, height, weight, body fat percentage, muscle mass. While accuracy 87.5%, showed higher 93.1%. Although telemedicine has been slow spread Japan, introduction Personal Health Record Large Language Models potential reduce burden physicians. future, we aim improve Japanese language medical-specific evaluation scales.

Язык: Английский

---