Edward Jay Wang

Yinan Xuan, Varun Viswanath, Sunny Chu et al.

Facial motion tracking in head-mounted displays (HMD) has the potential to enable immersive "face-to-face" interaction in a virtual environment. However, current works on facial tracking are not suitable for unobtrusive augmented reality (AR) glasses or do not have the ability to track arbitrary facial movements. In this work, we demonstrate a novel system called SpecTracle that tracks a user's facial motions using two wide-angle cameras mounted right next to the visor of a Hololens. Avoiding the usage of cameras extended in front of the face, our system greatly improves the feasibility to integrate full-face tracking into a low-profile form factor. We also demonstrate that a neural network-based model processing the wide-angle cameras can run in real-time at 24 frames per second (fps) on a mobile GPU and track independent facial movement for different parts of the face with a user-independent model. Using a short personalized calibration, the system improves its tracking performance by 42.3% compared to the user-independent model.

Jason S. Hoffman, Varun Viswanath, Xinyi Ding et al.

Hypoxemia, a medical condition that occurs when the blood is not carrying enough oxygen to adequately supply the tissues, is a leading indicator for dangerous complications of respiratory diseases like asthma, COPD, and COVID-19. While purpose-built pulse oximeters can provide accurate blood-oxygen saturation (SpO$_2$) readings that allow for diagnosis of hypoxemia, enabling this capability in unmodified smartphone cameras via a software update could give more people access to important information about their health, as well as improve physicians' ability to remotely diagnose and treat respiratory conditions. In this work, we take a step towards this goal by performing the first clinical development validation on a smartphone-based SpO$_2$ sensing system using a varied fraction of inspired oxygen (FiO$_2$) protocol, creating a clinically relevant validation dataset for solely smartphone-based methods on a wide range of SpO$_2$ values (70%-100%) for the first time. This contrasts with previous studies, which evaluated performance on a far smaller range (85%-100%). We build a deep learning model using this data to demonstrate accurate reporting of SpO$_2$ level with an overall MAE=5.00% SpO$_2$ and identifying positive cases of low SpO$_2$<90% with 81% sensitivity and 79% specificity. We ground our analysis with a summary of recent literature in smartphone-based SpO2 monitoring, and we provide the data from the FiO$_2$ study in open-source format, so that others may build on this work.

Yuzhe Yang, Yujia Liu, Xin Liu et al.

Advances in artificial intelligence (AI) have achieved expert-level performance in medical imaging applications. Notably, self-supervised vision-language foundation models can detect a broad spectrum of pathologies without relying on explicit training annotations. However, it is crucial to ensure that these AI models do not mirror or amplify human biases, thereby disadvantaging historically marginalized groups such as females or Black patients. The manifestation of such biases could systematically delay essential medical care for certain patient subgroups. In this study, we investigate the algorithmic fairness of state-of-the-art vision-language foundation models in chest X-ray diagnosis across five globally-sourced datasets. Our findings reveal that compared to board-certified radiologists, these foundation models consistently underdiagnose marginalized groups, with even higher rates seen in intersectional subgroups, such as Black female patients. Such demographic biases present over a wide range of pathologies and demographic attributes. Further analysis of the model embedding uncovers its significant encoding of demographic information. Deploying AI systems with these biases in medical imaging can intensify pre-existing care disparities, posing potential challenges to equitable healthcare access and raising ethical questions about their clinical application.

Chris Brogly, Saif Rjaibi, Charlotte Liang et al.

Small Language Models (SLMs) have potential to be used for automatically labelling and identifying aspects of text data for medicine/health-related purposes from documents and the web. As their resource requirements are significantly lower than Large Language Models (LLMs), these can be deployed potentially on more types of devices. SLMs often are benchmarked on health/medicine-related tasks, such as MedQA, although performance on these can vary especially depending on the size of the model in terms of number of parameters. Furthermore, these test results may not necessarily reflect real-world performance regarding the automatic labelling or identification of texts in documents and the web. As a result, we compared topic-relatedness scores from Microsofts phi-3-mini-4k-instruct SLM to the topic-relatedness scores from 7 human evaluators on 1144 samples of medical/health-related texts and 1117 samples of sports injury-related texts. These texts were from a larger dataset of about 9 million news headlines, each of which were processed and assigned scores by phi-3-mini-4k-instruct. Our sample was selected (filtered) based on 1 (low filtering) or more (high filtering) Boolean conditions on the phi-3 SLM scores. We found low-moderate significant correlations between the scores from the SLM and human evaluators for sports injury texts with low filtering (\r{ho} = 0.3413, p < 0.001) and medicine/health texts with high filtering (\r{ho} = 0.3854, p < 0.001), and low significant correlation for medicine/health texts with low filtering (\r{ho} = 0.2255, p < 0.001). There was negligible, insignificant correlation for sports injury-related texts with high filtering (\r{ho} = 0.0318, p = 0.4466).

Yujia Liu, Sophia Yu, Hongyue Jin et al.

Online health resources and large language models (LLMs) are increasingly used as a first point of contact for medical decision-making, yet their reliability in healthcare remains limited by low accuracy, lack of transparency, and susceptibility to unverified information. We introduce a proof-of-concept conversational self-triage system that guides LLMs with 100 clinically validated flowcharts from the American Medical Association, providing a structured and auditable framework for patient decision support. The system leverages a multi-agent framework consisting of a retrieval agent, a decision agent, and a chat agent to identify the most relevant flowchart, interpret patient responses, and deliver personalized, patient-friendly recommendations, respectively. Performance was evaluated at scale using synthetic datasets of simulated conversations. The system achieved 95.29% top-3 accuracy in flowchart retrieval (N=2,000) and 99.10% accuracy in flowchart navigation across varied conversational styles and conditions (N=37,200). By combining the flexibility of free-text interaction with the rigor of standardized clinical protocols, this approach demonstrates the feasibility of transparent, accurate, and generalizable AI-assisted self-triage, with potential to support informed patient decision-making while improving healthcare resource utilization.

Jessica Maria Echterhoff, Edward J. Wang

Contextual sensing using wearable cameras has seen a variety of different camera angles proposed to capture a wide gamut of different visual scenes. In this paper, we propose a new camera view that aims to capture the same visual information as many of the camera positions and orientations combined from a single camera view point. The camera, mounted on the corner of a glasses frame is pointing downwards towards the floor, a field-of-view we named Personal Activity Radius (PAR). The PAR field-of-view captures the visual information around a wearer's personal bubble, including items they interact with, their body motion, their surrounding environment, etc. In our evaluation, we tested the PAR view's interpretability by human labelers in two different activity tracking scenarios: food related behaviors and exercise tracking. Human labelers achieved an overall high level of precision in identifying body motions in exercise tracking of 91% precision and eating/drinking motions at 96% precision. Item interaction identification reached a precision of 86% precision for labeling grocery categories. We show a high level on the device setup and contextual views we were able to capture with the device. We see that the camera wide angle captures different activities such as driving, shopping, gym exercises, walking and eating and can observe the specific interaction item of the user as well as the immediate contextual surrounding.