Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 10501 publications
A Scalable Framework for Evaluating Health Language Models
Neil Mallinar
Tony Faranesh
Brent Winslow
Nova Hammerquist
Ben Graef
Cathy Speed
Mark Malhotra
Shwetak Patel
Xavi Prieto
Daniel McDuff
Ahmed Metwally
(2025)
Preview abstract
Large language models (LLMs) have emerged as powerful tools for analyzing complex datasets. Recent studies demonstrate their potential to generate useful, personalized responses when provided with patient-specific health information that encompasses lifestyle, biomarkers, and context. As LLM-driven health applications are increasingly adopted, rigorous and efficient one-sided evaluation methodologies are crucial to ensure response quality across multiple dimensions, including accuracy, personalization and safety. Current evaluation practices for open-ended text responses heavily rely on human experts. This approach introduces human factors and is often cost-prohibitive, labor-intensive, and hinders scalability, especially in complex domains like healthcare where response assessment necessitates domain expertise and considers multifaceted patient data. In this work, we introduce Adaptive Precise Boolean rubrics: an evaluation framework that streamlines human and automated evaluation of open-ended questions by identifying gaps in model responses using a minimal set of targeted rubrics questions. Our approach is based on recent work in more general evaluation settings that contrasts a smaller set of complex evaluation targets with a larger set of more precise, granular targets answerable with simple boolean responses. We validate this approach in metabolic health, a domain encompassing diabetes, cardiovascular disease, and obesity. Our results demonstrate that Adaptive Precise Boolean rubrics yield higher inter-rater agreement among expert and non-expert human evaluators, and in automated assessments, compared to traditional Likert scales, while requiring approximately half the evaluation time of Likert-based methods. This enhanced efficiency, particularly in automated evaluation and non-expert contributions, paves the way for more extensive and cost-effective evaluation of LLMs in health.
View details
Validation of a Deep Learning Model for Diabetic Retinopathy on Patients with Young-Onset Diabetes
Tony Tan-Torres
Pradeep Praveen
Divleen Jeji
Arthur Brant
Xiang Yin
Lu Yang
Tayyeba Ali
Ilana Traynis
Dushyantsinh Jadeja
Rajroshan Sawhney
Sunny Virmani
Pradeep Venkatesh
Nikhil Tandon
Ophthalmology and Therapy (2025)
Preview abstract
Introduction
While many deep learning systems (DLSs) for diabetic retinopathy (DR) have been developed and validated on cohorts with an average age of 50s or older, fewer studies have examined younger individuals. This study aimed to understand DLS performance for younger individuals, who tend to display anatomic differences, such as prominent retinal sheen. This sheen can be mistaken for exudates or cotton wool spots, and potentially confound DLSs.
Methods
This was a prospective cross-sectional cohort study in a “Diabetes of young” clinic in India, enrolling 321 individuals between ages 18 and 45 (98.8% with type 1 diabetes). Participants had fundus photographs taken and the photos were adjudicated by experienced graders to obtain reference DR grades. We defined a younger cohort (age 18–25) and an older cohort (age 26–45) and examined differences in DLS performance between the two cohorts. The main outcome measures were sensitivity and specificity for DR.
Results
Eye-level sensitivity for moderate-or-worse DR was 97.6% [95% confidence interval (CI) 91.2, 98.2] for the younger cohort and 94.0% [88.8, 98.1] for the older cohort (p = 0.418 for difference). The specificity for moderate-or-worse DR significantly differed between the younger and older cohorts, 97.9% [95.9, 99.3] and 92.1% [87.6, 96.0], respectively (p = 0.008). Similar trends were observed for diabetic macular edema (DME); sensitivity was 79.0% [57.9, 93.6] for the younger cohort and 77.5% [60.8, 90.6] for the older cohort (p = 0.893), whereas specificity was 97.0% [94.5, 99.0] and 92.0% [88.2, 95.5] (p = 0.018). Retinal sheen presence (94% of images) was associated with DME presence (p < 0.0001). Image review suggested that sheen presence confounded reference DME status, increasing noise in the labels and depressing measured sensitivity. The gradability rate for both DR and DME was near-perfect (99% for both).
Conclusion
DLS-based DR screening performed well in younger individuals aged 18–25, with comparable sensitivity and higher specificity compared to individuals aged 26–45. Sheen presence in this cohort made identification of DME difficult for graders and depressed measured DLS sensitivity; additional studies incorporating optical coherence tomography may improve accuracy of measuring DLS DME sensitivity.
View details
ESAM++: Efficient Online 3D Perception on the Edge
Qin Liu
Lavisha Aggarwal
Vikas Bahirwani
Lin Li
Aleksander Holynski
Saptarashmi Bandyopadhyay
Zhengyang Shen
Marc Niethammer
Ehsan Adeli
Andrea Colaco
2025
Preview abstract
Online 3D scene perception in real time is critical for robotics, AR/VR, and autonomous systems, particularly in edge computing scenarios where computational resources are limited. Recent state-of-the-art methods like EmbodiedSAM (ESAM) demonstrate the promise of online 3D perception by leveraging the 2D visual foundation model (VFM) with efficient 3D query lifting and merging. However, ESAM depends on a computationally expensive sparse 3D U-Net for point cloud feature extraction, which we identify as the primary efficiency bottleneck. In this paper, we propose a lightweight and scalable alternative for online 3D scene perception tailored to edge devices. Our method introduces a 3D Sparse FeaturePyramid Network (SFPN) that efficiently captures multi-scale geometric features from streaming 3D point clouds while significantly reducing computational over-head and model size. We evaluate our approach on four challenging segmentation benchmarks—ScanNet, ScanNet200, SceneNN, and 3RScan—demonstrating that our model achieves competitive accuracy with up to 3×faster inference and 3×small model size compared to ESAM, enabling practical deployment in real-world edge scenarios. Code and models will be released.
View details
Preview abstract
Browser fingerprinting is an online tracking technique that is being increasingly adopted for profiling and ad targeting purposes. While prior work has analyzed the prevalence and impact of browser fingerprinting on the Web, they have traditionally relied on large-scale automated crawls. Naturally, these cannot replicate real-human interactions, e.g., solve CAPTCHAs, evade bot detectors, or operate behind login pages and paywalls. This prompts the question as to whether or not the fingerprinting ecosystem is appreciably different in real-world browsing sessions. In this paper, we begin to address this question by designing and conducting a user study aimed at collecting actual telemetry data from real browsing sessions of 30 users.
We find that almost half of the fingerprinting websites identified from real user browsing sessions are missed by equivalent automated crawls. This is mainly due to the inability of automated crawls to identify and visit authentication pages, being blocked by bot detectors, and/or failing to perform user interactions that specifically trigger browser fingerprinting scripts. We also find new fingerprinting vectors that are consistently present in fingerprinting scripts captured by real user browsing sessions yet missing from automated crawls. Finally, we assess the feasibility of collecting fingerprinting training data in a privacy-preserving way. We conclude that private models built on real user browsing sessions can detect browser fingerprinting more effectively than models trained on automated crawls alone, while simultaneously providing strong privacy guarantees to users.
View details
Preview abstract
We consider the Coalition Structure Learning (CSL) problem in multi-agent systems, motivated by the existence of coalitions in many real-world systems, e.g., trading platforms and auction systems. In this problem, there is a hidden coalition structure within a set of $n$ agents, which affects the behavior of the agents in games. Our goal is to actively design a sequence of games
for the agents to play, such that observations in these games can be used to learn the hidden coalition structure. In particular, we consider the setting where in each round, we design and present a game together with a strategy profile to the agents, and receive a multiple-bit observation -- for each agent, we observe whether or not they would like to deviate from the specified strategy in this given game. Our contributions are three-fold: First, we show that we can learn the coalition structure in $O(\log n)$ rounds if we are allowed to choose any normal-form game in each round, matching the information-theoretical lower bound, and the result can be extended to congestion games. Second, in a more restricted setting where we can only choose a graphical game with degree limit $d$, we develop an algorithm to learn the coalition structure in $O(n/d+\log d)$ rounds. Third, when we can only learn the coalition structure through running second-price auctions with personalized reserve prices, we show that the coalition structure can be learned in $O(c\log n)$ rounds, where $c$ is the size of the largest coalition.
View details
Passive Heart Rate Monitoring During Smartphone Use in Everyday Life
Shun Liao
Paolo Di Achille
Jiang Wu
Silviu Borac
Jonathan Wang
Eric Teasley
Lawrence Cai
Daniel McDuff
Hao-Wei Su
Brent Winslow
Anupam Pathak
Shwetak Patel
Jim Taylor
Jamie Rogers
(2025)
Preview abstract
Resting heart rate (RHR) is an important biomarker of cardiovascular health and mortality, but tracking it longitudinally generally requires a wearable device, limiting its availability. We present PHRM, a deep learning system for passive heart rate (HR) and RHR measurements during ordinary smartphone use, using facial video-based photoplethysmography. Our system was developed using 225,773 videos from 495 participants and validated on 185,970 videos from 205 participants in laboratory and free-living conditions – the largest validation study of its kind. Compared to reference electrocardiogram, PHRM achieved a mean absolute percentage error (MAPE) <10% for HR measurements across three skin tone groups of light, medium and dark pigmentation; MAPE for each skin tone group was non-inferior versus the others. Daily RHR measured by PHRM had a mean absolute error <5 bpm compared to a wearable HR tracker, and was associated with known risk factors. These results highlight the potential of smartphones to enable passive and equitable heart health monitoring.
View details
Triaging mammography with artificial intelligence: an implementation study
Sarah M. Friedewald
Sunny Jansen
Fereshteh Mahvar
Timo Kohlberger
David V. Schacht
Sonya Bhole
Dipti Gupta
Scott Mayer McKinney
Stacey Caron
David Melnick
Mozziyar Etemadi
Samantha Winter
Alejandra Maciel
Luca Speroni
Martha Sevenich
Arnav Agharwal
Rubin Zhang
Gavin Duggan
Shiro Kadowaki
Atilla Kiraly
Jie Yang
Basil Mustafa
Krish Eswaran
Shravya Shetty
Breast Cancer Research and Treatment (2025)
Preview abstract
Purpose
Many breast centers are unable to provide immediate results at the time of screening mammography which results in delayed patient care. Implementing artificial intelligence (AI) could identify patients who may have breast cancer and accelerate the time to diagnostic imaging and biopsy diagnosis.
Methods
In this prospective randomized, unblinded, controlled implementation study we enrolled 1000 screening participants between March 2021 and May 2022. The experimental group used an AI system to prioritize a subset of cases for same-visit radiologist evaluation, and same-visit diagnostic workup if necessary. The control group followed the standard of care. The primary operational endpoints were time to additional imaging (TA) and time to biopsy diagnosis (TB).
Results
The final cohort included 463 experimental and 392 control participants. The one-sided Mann-Whitney U test was employed for analysis of TA and TB. In the control group, the TA was 25.6 days [95% CI 22.0–29.9] and TB was 55.9 days [95% CI 45.5–69.6]. In comparison, the experimental group's mean TA was reduced by 25% (6.4 fewer days [one-sided 95% CI > 0.3], p<0.001) and mean TB was reduced by 30% (16.8 fewer days; 95% CI > 5.1], p=0.003). The time reduction was more pronounced for AI-prioritized participants in the experimental group. All participants eventually diagnosed with breast cancer were prioritized by the AI.
Conclusions
Implementing AI prioritization can accelerate care timelines for patients requiring additional workup, while maintaining the efficiency of delayed interpretation for most participants. Reducing diagnostic delays could contribute to improved patient adherence, decreased anxiety and addressing disparities in access to timely care.
View details
Preview abstract
AI coding assistants are rapidly becoming integral to modern software development. A key challenge in this space is the continual need to migrate and modernize codebases in response to evolving software ecosystems. Traditionally, such migrations have relied on rule-based systems and human intervention. With the advent of powerful large language models (LLMs), AI-driven agentic frameworks offer a promising alternative-but their effectiveness has not been systematically evaluated. In this paper, we introduce FreshBrew, a novel benchmark for evaluating AI agents on project-level Java migrations, with a specific focus on measuring an agent's ability to preserve program semantics and avoid reward hacking, which we argue requires projects with high test coverage for a rigorous and reliable evaluation. We benchmark several state-of-the-art LLMs, and compare their performance against established rule-based tools. Our evaluation of AI agents on this benchmark of 228 repositories shows that the top-performing model, Gemini 2.5 Flash, can successfully migrate 52.3 percent of projects to JDK 17. Our empirical analysis reveals novel insights into the critical strengths and limitations of current agentic approaches, offering actionable insights into their real-world applicability. Our empirical study reveals failure modes of current AI agents in realistic Java modernization tasks, providing a foundation for evaluating trustworthy code-migration systems. By releasing FreshBrew, we aim to facilitate rigorous, reproducible evaluation and catalyze progress in AI-driven codebase modernization.
View details
Data-Driven Mechanism Design: Jointly Eliciting Preferences and Information
Dirk Bergemann
Marek Bojko
Paul Duetting
Haifeng Xu
EC '25: Proceedings of the 26th ACM Conference on Economics and Computation (2025), pp. 507
Preview abstract
We study mechanism design when agents have private preferences and private information about a common payoff-relevant state. We show that standard message-driven mechanisms cannot implement socially efficient allocations when agents have multidimensional types, even under favorable conditions.
To overcome this limitation, we propose data-driven mechanisms that leverage additional post-allocation information, modeled as an estimator of the payoff-relevant state. Our data-driven mechanisms extend the classic Vickrey-Clarke-Groves class. We show that they achieve exact implementation in posterior equilibrium when the state is either fully revealed or the utility is affine in an unbiased estimator. We also show that they achieve approximate implementation with a consistent estimator, converging to exact implementation as the estimator converges, and present bounds on the convergence rate.
We demonstrate applications to digital advertising auctions and large language model (LLM)-based mechanisms, where user engagement naturally reveals relevant information.
View details
The Cost of Consistency: Submodular Maximization with Constant Recourse
Paul Duetting
Federico Fusco
Ashkan Norouzi Fard
Ola Svensson
Proceedings of the 57th Annual ACM Symposium on Theory of Computing (2025), 1406–1417
Preview abstract
In this work, we study online submodular maximization and how the requirement of maintaining a stable solution impacts the approximation. In particular, we seek bounds on the best-possible
approximation ratio that is attainable when the algorithm is allowed to make, at most, a constant number of updates per step. We show a tight information-theoretic bound of $2/3$ for general monotone submodular functions and an improved (also tight) bound of $3/4$ for coverage functions. Since both these bounds are attained by non poly-time algorithms, we also give a poly-time randomized algorithm that achieves a $0.51$-approximation. Combined with an
information-theoretic hardness of $1/2$ for deterministic algorithms from prior work, our work thus shows a separation between deterministic and randomized algorithms, both information theoretically and for poly-time algorithms.
View details
Preview abstract
We investigate Learning from Label Proportions (LLP), a partial information setting where examples in a training set are grouped into bags, and only aggregate label values in each bag are available. Despite the partial observability, the goal is still to achieve small regret at the level of individual examples. We give results on the sample complexity of LLP under square loss, showing that our sample complexity is essentially optimal. From an algorithmic viewpoint, we rely on carefully designed variants of Empirical Risk Minimization, and Stochastic Gradient Descent algorithms, combined with ad hoc variance reduction techniques. On one hand, our theoretical results improve in important ways on the existing literature on LLP, specifically in the way the sample complexity depends on the bag size. On the other hand, we validate our algorithmic solutions on several datasets, demonstrating improved empirical performance (better accuracy for less samples) against recent baselines.
View details
InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMs
Jing Jin
Xiuxiu Yuan
Jun Jiang
Jingtao Zhou
Yiyi Huang
Zheng Xu
Kristen Wright
Jason Mayes
Mark Sherwood
Johnny Lee
Alex Olwal
Ram Iyengar
Na Li
Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI), ACM, pp. 23
Preview abstract
Visual programming has the potential of providing novice programmers with a low-code experience to build customized processing pipelines. Existing systems typically require users to build pipelines from scratch, implying that novice users are expected to set up and link appropriate nodes from a blank workspace. In this paper, we introduce InstructPipe, an AI assistant for prototyping machine learning (ML) pipelines with text instructions. We contribute two large language model (LLM) modules and a code interpreter as part of our framework. The LLM modules generate pseudocode for a target pipeline, and the interpreter renders the pipeline in the node-graph editor for further human-AI collaboration. Both technical and user evaluation (N=16) shows that InstructPipe empowers users to streamline their ML pipeline workflow, reduce their learning curve, and leverage open-ended commands to spark innovative ideas.
View details
Automated loss of pulse detection on a commercial smartwatch
Kamal Shah
Yiwen Chen
Anthony Stange
Lawrence Cai
Matt Wimmer
Pramod Rudrapatna
Shelten Yuen
Anupam Pathak
Shwetak Patel
Mark Malhotra
Marc Stogaitis
Jeanie Phan
Ali Connell
Jim Taylor
Jacqueline Shreibati
Daniel McDuff
Tajinder Gadh
Jake Sunshine
Nature, 642 (2025), pp. 174-181
Preview abstract
Out-of-hospital cardiac arrest is a time-sensitive emergency that requires prompt identification and intervention: sudden, unwitnessed cardiac arrest is nearly unsurvivable. A cardinal sign of cardiac arrest is sudden loss of pulse. Automated biosensor detection of unwitnessed cardiac arrest, and dispatch of medical assistance, may improve survivability given the substantial prognostic role of time, but only if the false-positive burden on public emergency medical systems is minimized. 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 detections.
View details
Preview abstract
Storage on Android has evolved significantly over the years, with each new Android version introducing changes aimed at enhancing usability, security, and privacy. While these updates typically help with restricting app access to storage through various mechanisms, they may occasionally introduce new complexities and vulnerabilities. A prime example is the introduction of scoped storage in Android 10, which fundamentally changed how apps interact with files. While intended to enhance user privacy by limiting broad access to shared storage, scoped storage has also presented developers with new challenges and potential vulnerabilities to address. However, despite its significance for user privacy and app functionality, no systematic studies have been performed to study Android’s scoped storage at depth from a security perspective. In this paper, we present the first systematic security analysis of the scoped storage mechanism. To this end, we design and implement a testing tool, named ScopeVerif, that relies on differential analysis to uncover security issues and implementation inconsistencies in Android’s storage. Specifically, ScopeVerif takes a list of security properties and checks if there are any file operations that violate any security properties defined in the official Android documentation. Additionally, we conduct a comprehensive analysis across different Android versions as well as a cross-OEM analysis to identify discrepancies in different implementations and their security implications. Our study identifies both known and unknown issues of scoped storage. Our cross-version analysis highlights undocumented changes as well as partially fixed security loopholes across versions. Additionally, we discovered several vulnerabilities in scoped storage implementations by different OEMs. These vulnerabilities stem from deviations from the documented and correct behavior, which potentially poses security risks. The affected OEMs and Google have acknowledged our findings and offered us bug bounties in response.
View details
Mind the GAP: Geometry Aware Passthrough Mitigates Cybersickness
Trishia Chemaly
Mohit Goyal
Sakar Khattar
Bjorn Vlaskamp
Aveek Purohit
Konstantine Tsotsos
2025
Preview abstract
Virtual Reality headsets isolate users from the real-world by restricting their perception to the virtual-world. Video See-Through (VST) headsets address this by utilizing world-facing cameras to create Augmented Reality experiences. However, directly displaying camera feeds can cause visual discomfort and cybersickness due to the inaccurate perception of scale and exaggerated motion parallax. This paper presents initial findings on the potential of geometry aware passthrough systems to mitigate cybersickness through enhanced depth perception. We introduce a promising protocol for quantitatively measuring cybersickness experienced by users in VST headsets. Using this protocol, we conduct a user study to compare direct passthrough and geometry aware passthrough systems. To the best of our knowledge, our study is the first one to reveal reduced nausea, disorientation, and total scores of cybersickness with geometry aware passthrough. It also uncovers several potential avenues to further mitigate visually-induced discomfort.
View details
