Core Viewpoint - The article emphasizes the significant advancement of Foundation Models (FM) in the potential applications of artificial intelligence (AI) in clinical care, highlighting the need for rigorous prospective validation and randomized controlled trials to bridge the gap between AI capabilities and real-world clinical environments [2][3][6]. Group 1: Foundation Model Development - A multi-modal visual-language ophthalmic foundation model named EyeFM was developed, which was validated through a prospective deployment across various global regions, including Asia, North America, Europe, and Africa [3][6]. - EyeFM was pre-trained using a diverse dataset of 14.5 million eye images, enabling it to perform various core clinical tasks effectively [6][11]. Group 2: Clinical Evaluation and Effectiveness - The effectiveness of EyeFM as a clinical assistance tool was evaluated through a randomized controlled trial involving 668 participants, showing a higher correct diagnosis rate of 92.2% compared to 75.4% in the control group [11][13]. - The study also indicated improved referral rates (92.2% vs 80.5%) and better self-management adherence (70.1% vs 49.1%) among the intervention group using EyeFM [11][13]. Group 3: Application and Future Implications - EyeFM serves as a comprehensive assistance system for ophthalmology, with potential applications across various clinical scenarios, enhancing the diagnostic capabilities of ophthalmologists and improving patient outcomes [12][13].

Core Insights - Google DeepMind has launched a new health-focused large language model (PH-LLM) that outperforms human doctors in sleep and fitness assessments, marking a significant advancement in AI-driven health management [1][3][35] Group 1: Model Performance - PH-LLM scored 79% in sleep medicine exams, surpassing human doctors who scored 76%, and achieved an impressive 88% in fitness assessments compared to human experts at 71% [3][15][17] - The model's performance is competitive with mainstream external models, showing slight advantages in sleep-related questions and equal performance in fitness-related questions [17][22] - PH-LLM demonstrated consistent performance across various difficulty levels, outperforming Gemini Ultra 1.0 and human experts in challenging questions [24][25] Group 2: Data Utilization - PH-LLM transforms data from wearable devices into actionable health insights, addressing the challenge of interpreting raw data that lacks context [5][8] - The model utilizes a two-phase training approach, incorporating demographic data, daily metrics, and individual exercise logs to enhance its ability to provide personalized health recommendations [12][30] - It can predict sleep quality based solely on sensor data, showcasing its capability to generate tailored advice for users [10][30] Group 3: Implications for Health Management - The research indicates that AI can convert passive health monitoring into proactive health management, emphasizing the potential of LLMs in preventive medicine [35][36] - PH-LLM's ability to understand user health data and provide timely recommendations signifies a shift towards more personalized healthcare solutions [36][37]

Core Insights - The Oxford University study challenges the reliability of AI models in real-world medical scenarios, despite their high performance in controlled environments [1][3][11] - The research indicates that while AI models like GPT-4o and Llama 3 perform well in isolated tasks, their effectiveness diminishes when interacting with real users [5][10][12] Group 1: Study Design and Methodology - The study involved 1,298 participants who were presented with ten real medical scenarios to assess their decision-making regarding symptoms and treatment options [3][5] - Participants were divided into groups, with one group using AI assistance and the other relying on personal knowledge or search engines [5][10] - The AI models demonstrated high accuracy in identifying diseases and suggesting treatment options when evaluated independently [3][5] Group 2: Interaction Challenges - When real users interacted with AI, the accuracy of disease identification dropped to 34.5%, indicating a significant gap in practical application [5][7] - The study found that users often failed to provide complete information, leading to misdiagnoses by the AI [7][11] - The communication between users and AI was identified as a critical failure point, with users misunderstanding or not following AI recommendations [7][9] Group 3: Implications for AI in Healthcare - The findings suggest that high scores in controlled tests do not translate to effective real-world applications, highlighting the complexities of human-AI interaction [11][12] - The study emphasizes the need for improved communication strategies between AI systems and users to enhance the practical utility of AI in medical settings [12] - The research serves as a reminder that the integration of AI into healthcare requires addressing the challenges of human behavior and communication, rather than solely focusing on technological advancements [12]