Large language models (LLMs) are revolutionizing healthcare by improving diagnosis, patient care, and decision support through interactive communication. More recently, they have been applied to analyzing physiological time-series like wearable data for health insight extraction. Existing methods embed raw numerical sequences directly into prompts, which exceeds token limits and increases computational costs. Additionally, some studies integrated features extracted from time-series in textual prompts or applied multimodal approaches. However, these methods often produce generic and unreliable outputs due to LLMs' limited analytical rigor and inefficiency in interpreting continuous waveforms. In this paper, we develop an LLM-powered agent for physiological time-series analysis aimed to bridge the gap in integrating LLMs with well-established analytical tools. Built on the OpenCHA, an open-source LLM-powered framework, our agent features an orchestrator that integrates user interaction, data sources, and analytical tools to generate accurate health insights. To evaluate its effectiveness, we implement a case study on heart rate (HR) estimation from Photoplethysmogram (PPG) signals using a dataset of PPG and Electrocardiogram (ECG) recordings in a remote health monitoring study. The agent's performance is benchmarked against OpenAI GPT-4o-mini and GPT-4o, with ECG serving as the gold standard for HR estimation. Results demonstrate that our agent significantly outperforms benchmark models by achieving lower error rates and more reliable HR estimations. The agent implementation is publicly available on GitHub.

In just a few years, Samsung has built up a substantial collection of artificial intelligence tricks, features and apps. While some of them have been impressive, like live translation and annotation, others (often involving generative AI) aren't actually helpful -- or notable -- enough to warrant regular use. The latest trio of Galaxy S flagship phones means another barrage of AI. Samsung has saved the best hardware for its S25 Ultra, of course, but the company also has smaller (and cheaper) flagships, with the Galaxy S25 ( 800) and larger S25 ( 1,000) both launching at the same time. And those AI features could be more crucial for the base S25 and larger S25 .

Health monitoring systems have revolutionized modern healthcare by enabling the continuous capture of physiological and behavioral data, essential for preventive measures and early health intervention. While integrating this data with Large Language Models (LLMs) has shown promise in delivering interactive health advice, traditional methods like Retrieval-Augmented Generation (RAG) and fine-tuning often fail to fully utilize the complex, multi-dimensional, and temporally relevant data from wearable devices. These conventional approaches typically provide limited actionable and personalized health insights due to their inadequate capacity to dynamically integrate and interpret diverse health data streams. In response, this paper introduces a graph-augmented LLM framework designed to significantly enhance the personalization and clarity of health insights. Utilizing a hierarchical graph structure, the framework captures inter and intra-patient relationships, enriching LLM prompts with dynamic feature importance scores derived from a Random Forest Model. The effectiveness of this approach is demonstrated through a sleep analysis case study involving 20 college students during the COVID-19 lockdown, highlighting the potential of our model to generate actionable and personalized health insights efficiently. We leverage another LLM to evaluate the insights for relevance, comprehensiveness, actionability, and personalization, addressing the critical need for models that process and interpret complex health data effectively. Our findings show that augmenting prompts with our framework yields significant improvements in all 4 criteria. Through our framework, we can elicit well-crafted, more thoughtful responses tailored to a specific patient.

But what is next in the pipeline? We are thrilled to share exciting updates on our Longevity App Beta and our plans for the future. We are proud to have onboarded close to 1500 users from 60 countries around the world, who have provided valuable feedback to help us provide the best user experience. The App received stellar reception, with users from all walks of life sharing their valuable feedback, including many in medical professions. In our recent comprehensive development update, we shared our plans for completion and release on public app stores.

It's true: A good night's sleep really does help us do our best the next day, and a couple of bad nights of sleep could hurt us for days to come. That's according to a new study from Microsoft's research organization, which analyzed anonymized data on people's online activities and sleep behavior to show how sleep quality impacts our ability to type queries on a search engine and click on the results. The research reinforces the importance of catching ZZZs and highlights the negative influence of sleep deprivation on our ability to think and act. "When you don't sleep well, it affects your cognitive performance, which means your work performance and lots of other things," said Tim Althoff, who led the research during a summer 2016 internship with Microsoft's research organization in Redmond, Washington. For example, the study shows that people who sleep less than six hours for two consecutive nights are sluggish for the next six days.