Richard Wang

Pandey and Milli's latest #research sheds light on the consequences of engagement-driven algorithms on #socialmedia. Discover how X’s system could be contributing to increased divisiveness and what alternatives might foster better discourse. Read more: https://hubs.ly/Q02qrfgL0 #onlineresearch #userengagement #phdchat #onlinesurveys #participantrecruitment

👉🏼 Accuracy, readability, and understandability of large language models for prostate cancer information to the public 🤓 Jacob S Hershenhouse 👇🏻 https://lnkd.in/ek8wbVfg 🔍 Focus on data insights: - GPT-generated output was deemed correct by 71.7% to 94.3% of raters across 9 scenarios. - GPT-generated simplified layperson summaries were rated as accurate in 8 of 9 scenarios. - Mean readability of layperson summaries was significantly higher than original GPT outputs. 💡 Main outcomes and implications: - GPT shows promise for correct patient education for prostate cancer-related content. - Enhancing accuracy, completeness, clarity, and readability of GPT responses can improve its utility in medical chatbots. 📚 Field significance: - Improving the quality of information provided by large language models can enhance patient education and decision-making in healthcare. - Optimizing language model outputs for patient consumption can bridge the gap between complex medical information and public understanding. 🗄️: [#prostatecancer #GPT #patienteducation #healthcare #medicalchatbots]

👉🏼 Prompt engineering on leveraging large language models in generating response to InBasket messages 🤓 Sherry Yan 👇🏻 https://lnkd.in/eZpReUeH 🔍 Focus on data insights: - 📈 The study demonstrated a significant increase in physician acceptance of LLM-generated draft responses, rising from 62% to 84% after three iterations of prompt engineering. - 🗣️ Patients reported a notable improvement in the tone (78%) and overall quality (80%) of messages generated by the optimized prompts compared to the original ones. - 🤖 A majority of patients (76%) could not distinguish between human and LLM-generated responses, indicating high-quality output from the model. 💡 Main outcomes and implications: - 🔄 Iterative prompt engineering proved effective in enhancing the quality of responses to Patient Medical Advice Requests (PMARs), suggesting a viable method for improving clinician-patient communication. - 🧠 Clinicians expressed that the use of LLMs could significantly reduce cognitive load when managing InBasket messages, potentially leading to improved efficiency in clinical settings. - 💬 The findings highlight the potential for LLMs to bridge gaps in patient care by providing timely and relevant information, thus improving patient satisfaction. 📚 Field significance: - 🌐 This research underscores the transformative role of AI and LLMs in healthcare, particularly in managing communication and administrative tasks. - 🏥 The study contributes to the growing body of evidence supporting the integration of AI tools in clinical workflows, paving the way for future innovations in patient care. - 📊 It emphasizes the importance of user feedback in refining AI applications, ensuring that they meet the needs of both clinicians and patients effectively. 🗄️: [#AI #LargeLanguageModels #Healthcare #PatientCare #PromptEngineering #ClinicalCommunication #CognitiveLoad #PatientSatisfaction #InBasketMessages]