Language models excel at diagnostic assessments on curated medical case-studies and vignettes, performing on par with, or better than, clinical professionals. However, existing studies focus on complex scenarios with rich context making it difficult to draw conclusions about how these systems perform for patients reporting symptoms in everyday life. We deployed SymptomAI, a set of conversational AI agents for end-to-end patient interviewing and differential diagnosis (DDx), via the Fitbit app in a study that randomized participants (N=13,917) to interact with five AI agents. This corpus captures diverse communication and a realistic distribution of illnesses from a real world population. A subset of 1,228 participants reported a clinician-provided diagnosis, and 517 of these were further evaluated by a panel of clinicians during over 250 hours of annotation. SymptomAI DDx were significantly more accurate (OR = 2.56, p < 0.001) than those from independent clinicians given the same dialogue in a blinded randomized comparison. Moreover, agentic strategies which conduct a dedicated symptom interview that elicit additional symptom information before providing a diagnosis, perform substantially better than baseline, user-guided conversations (p < 0.001). An auxiliary analysis on 1,509 conversations from a general US population panel validated that these results generalize beyond wearable device users. We used SymptomAI diagnoses as labels for all 13,917 participants to analyze over 500,000 days of wearable metrics across nearly 400 unique conditions. We identified strong associations between acute infections and physiological shifts (e.g., OR > 7 for influenza). While limited by self-reported ground truth, these results demonstrate the benefits of a dedicated and complete symptom interview compared to a user-guided symptom discussion, which is the default of most consumer LLMs.

Wearable sensors enable the continuous acquisition of high-resolution physiological waveforms, such as photoplethysmography and accelerometry, under free-living conditions. However, inferring health-related phenotypes from these signals presents significant challenges due to high sampling frequencies, multimodal dependencies, and extreme sequence lengths (e.g., weeks of recordings), compounded by a scarcity of ground-truth labels. To address these challenges, existing self-supervised learning (SSL) methodologies typically follow two paradigms: (1) learning rich morphological representations from short waveform segments while collapsing longitudinal dynamics through simple aggregation, or (2) modeling behavioral patterns from coarse, hand-crafted features (e.g. heart rate, step counts) spanning longer horizons but foregoing subtle, predictive signatures in raw waveforms. To bridge this gap, we propose WavesFM, a foundation model utilizing a two-stage SSL framework for longitudinal physiological data. Specifically, we decompose the learning problem into two stages: first, a segment-level encoder is pretrained to extract local embeddings from short waveforms; subsequently, a temporal encoder is trained to model the sequence of these embeddings across a multi-day horizon. This hierarchical approach overcomes the computational complexity of high-resolution, long-sequence data, allowing the overall model to capture both local signal semantics and the complex circadian and inter-day variations governing physiological dynamics. Pretrained on over 6.8M hours (N=324k individuals) of recordings for the first stage and 5.3M hours (N=10k) for the second stage, WavesFM demonstrates superior performance across 58 diverse tasks spanning demographics, lifestyle, health conditions, and medications.

While ubiquitous wearable sensors capture a wealth of behavioral and physiological information, effectively transforming these signals into personalized health insights is challenging. Specifically, converting low-level sensor data into representations capable of characterizing higher-level states is difficult due to high phenotypic diversity and variation in individual baseline health, physiology, and lifestyle factors. Moreover, collecting wearable data paired with health outcome annotations is laborious and expensive, and retrospective annotation remains practically unfeasible, contributing to a scarcity of data with high-quality labels. To overcome these limitations, we propose a foundation model for wearable health that is pretrained on more than one trillion minutes of unlabeled sensor signals drawn from a large cohort of five million participants. We demonstrate that the joint scaling of model capacity and pretraining data volume leads to systematic improvements in performance, as evaluated on a diverse set of 35 health prediction tasks, spanning cardiovascular, metabolic, sleep, and mental health, as well as lifestyle choices and demographic factors. We find that this population scale representation unlocks label-efficient few-shot learning and generative capabilities for robust daily metric estimation. To further leverage this learned representation, we deploy a classroom of LLM agents to autonomously search the space of downstream predictive heads built on the model embeddings, showing broad performance improvements that increase with LLM model capacity. Finally, we show how integrating these downstream predictors into a Personal Health Agent can support model responses that are more relevant, contextually aware, and safe, and we validate this via 1,860 ratings from a cohort of clinicians.

Resting heart rate (RHR) is a key biomarker of cardiovascular health and mortality1–3, but passively tracking it longitudinally generally requires a wearable device, limiting its availability. Here we present passive heart-rate monitoring (PHRM), a deep-learning system that uses facial video-based photoplethysmography for passive measurements of heart rate (HR) and RHR during everyday smartphone interactions. Our system was developed using 192,353 videos from 485 participants and validated on 162,546 videos from 211 participants in laboratory and free-living conditions, representing, to our knowledge, the largest validation study of its kind. PHRM outperformed state-of-the-art methods on our benchmarks. Compared with reference electrocardiograms, PHRM achieved a mean absolute percentage error (MAPE) lower than 10% for HR measurements across three skin-tone groups of light, medium and dark pigmentation, meeting industry accuracy standards; MAPE for each skin-tone group was non-inferior versus the others. Daily RHR measured by PHRM had a mean absolute error of less than five beats per minute, compared with a wearable HR tracker, and was associated with known risk factors for cardiovascular disease. These results highlight the potential of smartphones for enabling passive and equitable monitoring of heart health. To facilitate further research, we publicly release a large, annotated smartphone video dataset along with a pre-trained HR model. A machine-learning model that uses smartphone cameras to measure heart rate in the background during normal daily phone use and subsequently estimate resting heart rate could make it easier for people to monitor heart health.

A comprehensive differential diagnosis is a cornerstone of medical care that is often reached through an iterative process of interpretation that combines clinical history, physical examination, investigations and procedures. Interactive interfaces powered by large language models present new opportunities to assist and automate aspects of this process1. Here we introduce the Articulate Medical Intelligence Explorer (AMIE), a large language model that is optimized for diagnostic reasoning, and evaluate its ability to generate a differential diagnosis alone or as an aid to clinicians. Twenty clinicians evaluated 302 challenging, real-world medical cases sourced from published case reports. Each case report was read by two clinicians, who were randomized to one of two assistive conditions: assistance from search engines and standard medical resources; or assistance from AMIE in addition to these tools. All clinicians provided a baseline, unassisted differential diagnosis prior to using the respective assistive tools. AMIE exhibited standalone performance that exceeded that of unassisted clinicians (top-10 accuracy 59.1% versus 33.6%, P = 0.04). Comparing the two assisted study arms, the differential diagnosis quality score was higher for clinicians assisted by AMIE (top-10 accuracy 51.7%) compared with clinicians without its assistance (36.1%; McNemar's test: 45.7, P < 0.01) and clinicians with search (44.4%; McNemar's test: 4.75, P = 0.03). Further, clinicians assisted by AMIE arrived at more comprehensive differential lists than those without assistance from AMIE. Our study suggests that AMIE has potential to improve clinicians' diagnostic reasoning and accuracy in challenging cases, meriting further real-world evaluation for its ability to empower physicians and widen patients' access to specialist-level expertise.

Gait metrics are key biomarkers for health and fall risk; however, their accurate measurement is challenging, demanding costly laboratory equipment. Smartphones may offer accurate estimates but require precise placement; smartwatches offer a more practical and consistent platform for continuous tracking. This work introduces a multi-head deep learning model that estimates spatio-temporal walking metrics (gait speed, double support time, and unilateral step length, swing time, and stance time) from consumer smartwatch inertial measurement unit (IMU) signals and user height. Across 246 participants, smartwatch estimates exhibited strong validity (Pearson r>0.80) and excellent reliability (ICC >0.80) across most metrics, mirroring smartphone performance. These findings establish smartwatches as a viable and highly comparable platform for accurate, reliable gait analysis, enabling more ubiquitous gait-based health tracking.

Subjective well-being is a cornerstone of individual and societal health, yet its scientific measurement has traditionally relied on self-report methods prone to recall bias and high participant burden. This has left a gap in our understanding of well-being as it is expressed in everyday life. We hypothesized that candid smiles captured during natural smartphone interactions could serve as a scalable, objective behavioral correlate of positive affect. To test this, we analyzed 405,448 video clips passively recorded from 233 consented participants over one week. Using a deep learning model to quantify smile intensity, we identified distinct diurnal and daily patterns. Daily patterns of smile intensity across the week showed strong correlation with national survey data on happiness (r=0.92), and diurnal rhythms documented close correspondence with established results from the day reconstruction method (r=0.80). Higher daily mean smile intensity was significantly associated with more physical activity (Beta coefficient = 0.043, 95

Smartphone-based heart rate (HR) monitoring apps using finger-over-camera photoplethysmography (PPG) face significant challenges in performance evaluation and device compatibility due to device variability and fragmentation. Manual testing is impractical, and standardized methods are lacking. This paper presents a novel, high-throughput bench-testing platform to address this critical need. We designed a system comprising a test rig capable of holding 12 smartphones for parallel testing, a method for generating synthetic PPG test videos with controllable HR and signal quality, and a host machine for coordinating video playback and data logging. The system achieved a mean absolute percentage error (MAPE) of 0.11% +/- 0.001% between input and measured HR, and a correlation coefficient of 0.92 +/- 0.008 between input and measured PPG signals using a clinically-validated smartphone-based HR app. Bench-testing results of 20 different smartphone models correctly classified all the devices as meeting the ANSI/CTA accuracy standards for HR monitors (MAPE <10%) when compared to a prospective clinical study with 80 participants, demonstrating high positive predictive value. This platform offers a scalable solution for pre-deployment testing of smartphone HR apps to improve app performance, ensure device compatibility, and advance the field of mobile health.

Hypertension is a silent killer, with over half of affected adults unaware of their condition 1,2 . This lack of awareness is a major concern, as early intervention is critical for preventing major adverse cardiovascular events 3,4 . While cuffless wearable blood pressure (BP) monitors offer comfort and convenience, their reliance on periodic calibration and inconsistent accuracy have limited their clinical adoption 5,6 . Here we show that applying artificial intelligence (AI) pre-trained on almost 500,000 hours of data to multimodal waveforms (photoplethysmography and accelerometry) recorded using a widely available consumer smartwatch (AI-PPG-ACC-HTN), without any cuff calibration, can detect hypertension with accuracy levels comparable to traditional cuffed BP devices in the existing clinical framework, including both initial and confirmatory screening. We validated AI-PPG-ACC-HTN in a prospective, multicenter study of 196 diverse participants free from known cardiovascular disease and antihypertensive medication against gold-standard 24-hour ambulatory BP monitoring. Over seven days of real-world monitoring, AI-PPG-ACC-HTN detected hypertension with a sensitivity of 65.8% (95% CI, 54.0%-76.3%), specificity of 90.0% (83.2-94.7), and positive predictive value (PPV) of 80.6% (68.6-89.6). In comparison, initial office BP screening achieved a sensitivity of 55.3% (43.4-66.7), specificity of 90.0% (83.2-94.7) and PPV of 77.8% (64.4-88.0). For confirmatory testing of participants with elevated BP identified by initial office BP screening (N=48), AI-PPG-ACC-HTN detected hypertension with a sensitivity of 78.4% (61.8-90.2), specificity of 90.9% (58.7-99.8) and PPV of 96.7% (82.8-99.9). Comparatively, repeat office BP achieved a sensitivity of 67.6% (50.2-82.0), specificity of 63.6% (30.8-89.1) and PPV of 86.2% (68.3-96.1); multiday home BP monitoring achieved a sensitivity of 89.2% (74.6-97.0), specificity of 81.8% (48.2-97.7) and PPV of 94.3% (80.8-99.3). These results highlight an opportunity for consumer smartwatches to facilitate population-level opportunistic hypertension screening, offering an accessible tool to address this major public health challenge.

Out-of-hospital cardiac arrest is a time-sensitive emergency that requires prompt identification and intervention: sudden, unwitnessed cardiac arrest is nearly unsurvivable1-3. A cardinal sign of cardiac arrest is sudden loss of pulse4. Automated biosensor detection of unwitnessed cardiac arrest, and dispatch of medical assistance, may improve survivability given the substantial prognostic role of time3,5, but only if the false-positive burden on public emergency medical systems is minimized5-7. Here we show that a multimodal, machine learning-based algorithm on a smartwatch can reach performance thresholds making it deployable at a societal scale. First, using photoplethysmography, we show that wearable photoplethysmography measurements of peripheral pulselessness (induced through an arterial occlusion model) manifest similarly to pulselessness caused by a common cardiac arrest arrhythmia, ventricular fibrillation. On the basis of the similarity of the photoplethysmography signal (from ventricular fibrillation or arterial occlusion), we developed and validated a loss of pulse detection algorithm using data from peripheral pulselessness and free-living conditions. Following its development, we evaluated the end-to-end algorithm prospectively: there was 1 unintentional emergency call per 21.67 user-years across two prospective studies; the sensitivity was 67.23% (95% confidence interval of 64.32% to 70.05%) in a prospective arterial occlusion cardiac arrest simulation model. These results indicate an opportunity, deployable at scale, for wearable-based detection of sudden loss of pulse while minimizing societal costs of excess false detections7.

Quantification of motor symptom progression in Parkinson’s disease (PD) patients is crucial for assessing disease progression and for optimizing therapeutic interventions, such as dopaminergic medications and deep brain stimulation. Cumulative and heuristic clinical experience has identified various clinical signs associated with PD severity, but these are neither objectively quantifiable nor robustly validated. Video-based objective symptom quantification enabled by machine learning (ML) introduces a potential solution. However, video-based diagnostic tools often have implementation challenges due to expensive and inaccessible technology, and typical “black-box” ML implementations are not tailored to be clinically interpretable. Here, we address these needs by releasing a comprehensive kinematic dataset and developing an interpretable video-based framework that predicts high versus low PD motor symptom severity according to MDS-UPDRS Part III metrics. This data driven approach validated and robustly quantified canonical movement features and identified new clinical insights, not previously appreciated as related to clinical severity, including pinkie finger movements and lower limb and axial features of gait. Our framework is enabled by retrospective, single-view, seconds-long videos recorded on consumer-grade devices such as smartphones, tablets, and digital cameras, thereby eliminating the requirement for specialized equipment. Following interpretable ML principles, our framework enforces robustness and interpretability by integrating (1) automatic, data-driven kinematic metric evaluation guided by pre-defined digital features of movement, (2) combination of bi-domain (body and hand) kinematic features, and (3) sparsity-inducing and stability-driven ML analysis with simple-to-interpret models. These elements ensure that the proposed framework quantifies clinically meaningful motor features useful for both ML predictions and clinical analysis.

Heart rate (HR) is a crucial physiological signal that can be used to monitor health and fitness. Traditional methods for measuring HR require wearable devices, which can be inconvenient or uncomfortable, especially during sleep and meditation. Noncontact HR detection methods employing microwave radar can be a promising alternative. However, the existing approaches in the literature usually use high-gain antennas and require the sensor to face the user's chest or back, making them difficult to integrate into a portable device and unsuitable for sleep and meditation tracking applications. This study presents a novel approach for noncontact HR detection using a miniaturized Soli radar chip embedded in a portable device (Google Nest Hub). The chip has a $6.5 \mbox{ mm} \times 5 \mbox{ mm} \times 0.9 \mbox{ mm}$ dimension and can be easily integrated into various devices. The proposed approach utilizes advanced signal processing and machine learning techniques to extract HRs from radar signals. The approach is validated on a sleep dataset (62 users, 498 hours) and a meditation dataset (114 users, 1131 minutes). The approach achieves a mean absolute error (MAE) of $1.69$ bpm and a mean absolute percentage error (MAPE) of $2.67\%$ on the sleep dataset. On the meditation dataset, the approach achieves an MAE of $1.05$ bpm and a MAPE of $1.56\%$. The recall rates for the two datasets are $88.53\%$ and $98.16\%$, respectively. This study represents the first application of the noncontact HR detection technology to sleep and meditation tracking, offering a promising alternative to wearable devices for HR monitoring during sleep and meditation.

We present LuckyChirp, a contactless, passive, opportunistic respiratory tracking solution for commodity device using cascaded sonar modeling. Compared to conventional sonar methods that only solve the respiratory estimation problem (“what is the respiratory rate”), LuckyChirp also solves the additional respiratory detection problem (“is the human present and static enough for respiration sensing”). LuckyChirp uses a custom neural network on pulsed sonar’s wavelet transformed features to detect respiration. The classifier is then cascaded with a respiratory rate estimator. Such holistic design eliminates user friction of manually activating the system and enables passive respiration monitoring for all-day natural use. With Google Nest Hub and Pixel 4 as experimental devices, LuckyChirp achieves a mean absolute error of 0.48±0.98 and 1.07±1.67 breaths/min, respectively, for 20 users participating in a whole-night study. Compared to direct respiratory estimation without respiration classification, this is a ×6 (Nest Hub) and ×4 (Pixel) reduction in error.

BackgroundWe explored whether a noninvasive handheld device using Active Cancellation of Tremor (ACT) technology could stabilize tremor-induced motion of a spoon in individuals with essential tremor (ET).MethodsFifteen ET subjects (9 men, 6 women) performed 3 tasks with the ACT device turned on and off. Tremor severity was rated with the Fahn-Tolosa-Marin Tremor Rating Scale (TRS). Subjective improvement was rated by subjects with the Clinical Global Impression Scale (CGI-S). Tremor amplitude was measured using device-embedded accelerometers in 11 subjects.ResultsTRS scores improved with ACT on (versus off) in all 3 tasks: holding (1.000.76 vs. 0.27 +/- 0.70; P=0.016), eating (1.47 +/- 1.06 vs. 0.13 +/- 0.64; P=0.001), and transferring (1.33 +/- 0.82 vs. 0.27 +/- 0.59; P=0.001). CGI-S improved with eating and transferring, but not the holding task. Accelerometer measurements demonstrated 71% to 76% reduction in tremor with the ACT device on.ConclusionsThis noninvasive handheld ACT device can reduce tremor amplitude and severity for eating and transferring tasks in individuals with ET. (c) 2013 International Parkinson and Movement Disorder Society

OBJECTIVE: To demonstrate the effectiveness of a handheld device on reducing tremor, using Active Cancellation of Tremor (ACT) technology.