OpenAI o1-Preview vs. ChatGPT in Healthcare: A New Frontier in Medical AI Reasoning

Cureus, Год журнала: 2024, Номер unknown

Опубликована: Окт. 1, 2024

This editorial explores the recent advancements in generative artificial intelligence with newly-released OpenAI o1-Preview, comparing its capabilities to traditional ChatGPT (GPT-4) model, particularly context of healthcare. While has shown many applications for general medical advice and patient interactions, o1-Preview introduces new features advanced reasoning skills using a

Язык: Английский

---

DeepSeek in Healthcare: Revealing Opportunities and Steering Challenges of a New Open-Source Artificial Intelligence Frontier

Cureus, Год журнала: 2025, Номер unknown

Опубликована: Фев. 18, 2025

Generative Artificial Intelligence (GAI) has driven several advancements in healthcare, with large language models (LLMs) such as OpenAI's ChatGPT, Google's Gemini, and Microsoft's Copilot demonstrating potential clinical decision support, medical education, research acceleration. However, their closed-source architecture, high computational costs, limited adaptability to specialized contexts remained key barriers universal adoption. Now, the rise of DeepSeek's DeepThink (R1), an open-source LLM, gaining prominence since mid-January 2025, new opportunities challenges emerge for healthcare integration AI-driven research. Unlike proprietary models, DeepSeek fosters continuous learning by leveraging publicly available datasets, possibly enhancing ever-evolving knowledge scientific reasoning. Its transparent, community-driven approach may enable greater customization, regional specialization, collaboration among data researchers clinicians. Additionally, supports offline deployment, addressing some privacy concerns. Despite these promising advantages, presents ethical regulatory challenges. Users' worries have emerged, concerns about user retention policies developer access user-generated content without opt-out options. when used applications, its compliance China's data-sharing regulations highlights urgent need clear international governance. Furthermore, like other LLMs, face limitations related inherent biases, hallucinations, output reliability, which warrants rigorous validation human oversight before application. This editorial explores role workflows, while also highlighting security, accuracy, responsible AI With careful implementation, considerations, collaboration, similar LLMs could enhance innovation, providing cost-effective, scalable solutions ensuring expertise remains at forefront patient care.

Язык: Английский

---

Perceptions and Earliest Experiences of Medical Students and Faculty With ChatGPT in Medical Education: Qualitative Study

JMIR Medical Education, Год журнала: 2025, Номер 11, С. e63400 - e63400

Опубликована: Фев. 20, 2025

Background With the rapid development of artificial intelligence technologies, there is a growing interest in potential use intelligence–based tools like ChatGPT medical education. However, limited research on initial perceptions and experiences faculty students with ChatGPT, particularly Saudi Arabia. Objective This study aimed to explore earliest knowledge, perceived benefits, concerns, limitations using education among at leading Arabian university. Methods A qualitative exploratory was conducted April 2023, involving focused meetings varying levels experience. thematic analysis used identify key themes subthemes emerging from discussions. Results Participants demonstrated good knowledge its functions. The main were use, concerns about benefits included collecting summarizing information saving time effort. centered around lack critical thinking provided, ambiguity references, access, trust output ethical concerns. Conclusions provides valuable insights into regarding newly introduced large language models While recognized, participants also expressed requiring further studies for effective integration education, exploring impact learning outcomes, student satisfaction, skills.

Язык: Английский

---

AI Chatbots and Cognitive Control: Enhancing Executive Functions Through Chatbot Interactions: A Systematic Review

Brain Sciences, Год журнала: 2025, Номер 15(1), С. 47 - 47

Опубликована: Янв. 6, 2025

Background/Objectives: The evolution of digital technology enhances the broadening a person's intellectual growth. Research points out that implementing innovative applications world improves human social, cognitive, and metacognitive behavior. Artificial intelligence chatbots are yet another human-made construct. These forms software simulate conversation, understand process user input, provide personalized responses. Executive function includes set higher mental processes necessary for formulating, planning, achieving goal. present study aims to investigate executive reinforcement through artificial chatbots, outlining potentials, limitations, future research suggestions. Specifically, examined three questions: use conversational in functioning training, their impact on executive-cognitive skills, duration any improvements. Methods: assessment existing literature was implemented using systematic review method, according PRISMA 2020 Principles. avalanche search method employed conduct source following databases: Scopus, Web Science, PubMed, complementary Google Scholar. This included studies from 2021 experimental, observational, or mixed methods. It AI-based conversationalists support functions, such as anxiety, stress, depression, memory, attention, cognitive load, behavioral changes. In addition, this general populations with specific neurological conditions, all peer-reviewed, written English, full-text access. However, excluded before 2021, reviews, non-AI-based conversationalists, not targeting range skills abilities, without open criteria aligned objectives, ensuring focus AI agents function. initial collection totaled n = 115 articles; however, eligibility requirements led final selection 10 studies. Results: findings suggested positive effects enhance improve skills. Although, several limitations were identified, making it still difficult generalize reproduce effects. Conclusions: an tool can assistant learning expanding contributing metacognitive, social development individual. its training is at primary stage. highlighted need unified framework reference studies, better designs, diverse populations, larger sample sizes participants, longitudinal observe long-term use.

Язык: Английский

---

OpenAI's Sora and Google's Veo 2 in Action: A Narrative Review of Artificial Intelligence-driven Video Generation Models Transforming Healthcare

Cureus, Год журнала: 2025, Номер unknown

Опубликована: Янв. 17, 2025

The rapid evolution of generative artificial intelligence (AI) has introduced transformative technologies across various domains, with text-to-video (T2V) generation models emerging as innovations in the field. This narrative review explores potential T2V AI used healthcare, focusing on their applications, challenges, and future directions. Advanced platforms, such Sora Turbo (OpenAI, Inc., San Francisco, California, United States) Veo 2 (Google LLC, Mountain View, States), both announced December 2024, offer capability to generate high-fidelity video contents. Such could revolutionize healthcare by providing tailored videos for patient education, enhancing medical training, possibly optimizing telemedicine. We conducted a comprehensive literature search databases including PubMed Google Scholar, identified 41 relevant studies published between 2020 2024. Our findings reveal significant possible benefits improving standardizing customized remote consultations. However, critical challenges persist, risks misinformation (or deepfake), privacy breaches, ethical concerns, limitations authenticity. Detection mechanisms deepfakes regulatory frameworks remain underdeveloped, necessitating further interdisciplinary research vigilant policy development. Future advancements enable real-time visualizations augmented reality training. achieving these will require addressing accessibility ensure equitable implementation prevent disparities. By fostering collaboration among stakeholders, systems technologists, transform global into more effective, universal, innovative system while safeguarding against its misuse.

Язык: Английский

---

Advancing Clinical Chatbot Validation Using AI-Powered Evaluation With a New 3-Bot Evaluation System: Instrument Validation Study

JMIR Nursing, Год журнала: 2025, Номер 8, С. e63058 - e63058

Опубликована: Фев. 27, 2025

Abstract Background The health care sector faces a projected shortfall of 10 million workers by 2030. Artificial intelligence (AI) automation in areas such as patient education and initial therapy screening presents strategic response to mitigate this shortage reallocate medical staff higher-priority tasks. However, current methods evaluating early-stage AI chatbots are highly limited due safety concerns the amount time effort that goes into them. Objective This study introduces novel 3-bot method for efficiently testing validating provider chatbots. To extensively test without involving real patients or researchers, various bots an evaluator bot were developed. Methods Provider interacted with embodying frustrated, anxious, depressed personas. An reviewed interaction transcripts based on specific criteria. Human experts then each transcript, bot’s results compared human evaluation ensure accuracy. Results patient-education evaluations nearly identical, minimal variance, limiting opportunity further analysis. also yielded similar between evaluator. Statistical analysis confirmed reliability accuracy evaluations. Conclusions innovative ensures safe, adaptable, effective means refine early versions risking investing excessive researcher effort. Our could have benefitted from larger criteria, we had extremely evaluators, which arisen because small number We prompting input practical consideration increases prompts. In future, using techniques retrieval augmented generation will allow system receive more information become accurate rapid validation automate basic tasks, freeing providers address complex

Язык: Английский

---

Building and beta-testing a secure, credible and trustworthy artificially intelligent chatbot that will not misinform, hallucinate or stigmatize substance use disorder: the Be Well Buddy chatbot (Preprint)

JMIR Human Factors, Год журнала: 2025, Номер 12, С. e69144 - e69144

Опубликована: Март 6, 2025

Abstract Background Artificially intelligent (AI) chatbots that deploy natural language processing and machine learning are becoming more common in health care to facilitate patient education outreach; however, generative such as ChatGPT face challenges, they can misinform hallucinate. Health systems increasingly interested using these tools for education, access care, self-management, but need reassurances AI be secure credible. Objective This study aimed build a system people use send SMS with questions about substance use, which used screen disorder (SUD). The will rely on data transfer via third party vendors thus require reliable trustworthy encryption of protected information . Methods We describe the process specifications building an chatbot users gain SUD from Be Well Texas, clinical provider affiliated University Texas Sciences Center at San Antonio. Results uses classify expert-curated content related SUD. It illustrates how we comply best practices HIPPA (Health Insurance Portability Accountability Act) compliance rest, while still offering state-of-the-art dynamic, user-driven conversation dialogue SUD, treatment services. Conclusions Recent calls attention user-friendly design concerning user rights honor digital regulations offerings suggest this is timely appropriate advancing field AI.

Язык: Английский

---

Evaluating AI Language Models for Reference Services: A Comparative Study of ChatGPT, Gemini, and Copilot

Internet Reference Services Quarterly, Год журнала: 2025, Номер unknown, С. 1 - 14

Опубликована: Март 17, 2025

Язык: Английский

---

Generative AI in Medicine and Healthcare: Moving Beyond the ‘Peak of Inflated Expectations’

Future Internet, Год журнала: 2024, Номер 16(12), С. 462 - 462

Опубликована: Дек. 9, 2024

The rapid development of specific-purpose Large Language Models (LLMs), such as Med-PaLM, MEDITRON-70B, and Med-Gemini, has significantly impacted healthcare, offering unprecedented capabilities in clinical decision support, diagnostics, personalized health monitoring. This paper reviews the advancements medicine-specific LLMs, integration Retrieval-Augmented Generation (RAG) prompt engineering, their applications improving diagnostic accuracy educational utility. Despite potential, these technologies present challenges, including bias, hallucinations, need for robust safety protocols. also discusses regulatory ethical considerations necessary integrating models into mainstream healthcare. By examining current studies developments, this aims to provide a comprehensive overview state LLMs medicine highlight future directions research application. study concludes that while hold immense safe effective practice requires rigorous testing, ongoing evaluation, continuous collaboration among stakeholders.

Язык: Английский

---

Transforming orthopaedics with AI: Insights from a custom ChatGPT on ESSKA osteotomy consensus

Knee Surgery Sports Traumatology Arthroscopy, Год журнала: 2025, Номер unknown

Опубликована: Март 13, 2025

Язык: Английский

---