Sensing | HXI - Human-centered eXtended Intelligence

UNDERSTAND: Uplifting the New generation through DBT Education and Resilience for Social Triggers, Anxiety, Negativity, and Depression

Fri, 11 Jul 2025 00:00:00 +0000

Overview

Many college students experience comorbid depression and anxiety, exacerbating symptom severity and functional impairment. While evidence-based treatments like CBT and DBT demonstrate efficacy, they lack real-time, context-aware delivery at moments of heightened distress.

We are developing a mobile health (mHealth) system that leverages ubiquitous computing, wearable sensing, and machine learning to detect physiological and socio-behavioral indicators of distress in situ. Upon detection, the system delivers Just-In-Time Adaptive Interventions (JITAI) informed by DBT principles to provide personalized, contextually relevant support.

By targeting transdiagnostic mechanisms such as emotional dysregulation, interpersonal challenges, and cognitive distortions, our approach aims to improve scalability and relevance across diverse populations with comorbid mood and anxiety disorders.

Funding and External Collaborations

UNDERSTAND is funded by the National Institute of Mental Health (NIMH) at NIH, with the funded project starting 1 August 2026. It is a collaboration between the HXI Lab and the UC San Diego Department of Psychiatry and the Herbert Wertheim School of Public Health, bringing together expertise in DBT, clinical psychology, digital mental health, and ubiquitous sensing.

Student Mental Health and Well-Being: Research with WILLO

Mon, 14 Sep 2026 00:00:00 +0000

Overview

WILLO is UC San Diego’s well-being platform for students, run by the university. The HXI Lab does not operate WILLO. We collaborate with the teams behind it, and this page collects the research that has come out of that collaboration.

University mental health services are under strain, and the usual framing is that the problem is capacity. Our work argues the harder problem is reach: students who would benefit often do not connect with services that already exist. Working alongside a deployed campus platform lets us study that gap at the scale it actually occurs.

A sensing system can only use data students are willing to share. We therefore study where students draw that line and, more importantly, why: which modalities feel acceptable, how institutional trust governs those choices, and what that means for anyone designing a well-being sensing system a student population would actually use.

This research also connects to the lab’s work on just-in-time adaptive interventions in UNDERSTAND, and to EHR-embedded approaches for activating holistic care.

Collaborations

This research is conducted in partnership with the Joan & Irwin Jacobs Center for Health Innovation (JCHI) at UC San Diego Health, our principal collaborator on this work.

It also involves UC San Diego Student Health and Well-Being, Counseling and Psychological Services (CAPS), and the Center for Wireless and Population Health Systems, together with the WILLO team.

UbiStroke and HoloStroke: Multimodal and Immersive Assessment of Stroke

Thu, 23 Sep 2021 00:00:00 +0000

Overview

Stroke is a major leading cause of death and disability in the United States and stroke-related care poses a significant burden on the population. Recombinant Tissue Plasminogen Activator is the only therapy for stroke but it is utilized in less than 5% of acute strokes due to the narrow therapeutic time window for intervention, within 3 hours of the onset of symptoms. Stroke assessment is currently hindered by human analysis. Accurately diagnosing a stroke as soon as possible after the onset of symptoms requires a stroke specialist and adjunctive imaging techniques. Additionally, stroke outcome prediction is currently crude, and stroke deficit scales are generally unable to predict if a patient will do well or very poorly.

Two lines of work address that gap from opposite ends: making the deficits themselves measurable, and moving the expertise to wherever the patient is.

UbiStroke

UbiStroke develops techniques to reliably identify and quantify the degree of different stroke-related deficits, through an accurate per-patient stroke signature that will help to more precisely assess patients' deficits. The system exploits multiple sensors and generates a stroke assessment based on body posture, facial droop, pupil tracking, speech patterns, and other symptoms of stroke. We are evaluating UbiStroke’s introduction into the clinical setting to assist the clinician-performed NIHSS exam.

HoloStroke

HoloStroke grew out of UbiStroke and asks how mixed reality can extend stroke care beyond the bedside. Using the HoloLens, holograms of a patient, or of their imaging, are placed in three-dimensional space and can be transmitted to a distant site, letting a remote stroke neurologist assess and interact as if present in the same room.

The work has since branched into several directions. Holo-Stroke established that patients found remote holographic visits with a stroke provider satisfying and immersive. Holo-Stroke-CTA asked whether providers reading computed tomographic angiography for large vessel occlusion would do better in holographic space than with a conventional DICOM viewer, and found higher reliability and markedly higher satisfaction. Holo-Stroke-ii extended the approach to inpatient immersion, and Holo-PACS broadened it from stroke to radiographic scans more generally.

Funding and External Collaborations

UbiStroke and HoloStroke are a collaboration with the UCSD Stroke Center, and the UCSD Bioengineering Department, the Institute of Neural Computation, and HomniHealth. Research leading to UbiStroke has been funded by the National Science Foundation, the NSF I-Corps, the National Library of Medicine at NIH, IBM Research, and UCSD’s Office of Research Affairs.

Publications

(Holo-PACS): use of holograms to improve provider acumen when reading clinical radiographic scans

Brett C. Meyer, Ben Shifflett, Weichen Liu, Kunal AGrawal, Dawn M. Meyer, Reza Bavarsad Shahripour, Royya Modir, Thomas M. Hemmen, Sanad Batarseh, Marissa D’Souza, Tiffany Hu, Cattien Phan, Amy Radonich, Nadir Weibel

Holo-Stroke-ii: Stroke care through stroke hologram teleportation- inpatient immersion

Weichen Liu, Ben Shifflett, Teri McQuaid, Marissa D’Souza, Reza Bavarsad Shahripour, Kunal AGrawal, Dawn M. Meyer, Derek Dutt, Dale Keehan, Nadir Weibel, Brett C. Meyer

Holo-Stroke: Assessing for Immersive Stroke Care Through Stroke Hologram Teleportation

Nadir Weibel, Ben Alwood, Vish Ramesh, Weichen Liu, Dawn M Meyer, Teri McQuaid, Emily St Germain, Brett C Meyer

Developing aids to assist acute stroke diagnosis

Vish Ramesh, Stephanie Kim, Hong-An Nguyen, Kunal AGrawal, Brett C Meyer, Nadir Weibel

Assessing Clinicians' Reliance on Computational Aids for Acute Stroke Diagnosis

Vish Ramesh, Andrew Nguyen, Kunal AGrawal, Brett C Meyer, Gert Cauwenberghs, Nadir Weibel

Stroke-associated hemiparesis detection using body joints and support vector machines

Vish Ramesh, Kunal AGrawal, Brett Meyer, Gert Cauwenberghs, Nadir Weibel

Exploring stroke-associated hemiparesis assessment with support vector machines

Vish Ramesh, Kunal AGrawal, Brett Meyer, Gert Cauwenberghs, Nadir Weibel

UnBIASED: Understanding Biased patient-provider Interactions And Supporting Enhanced Discourse

Thu, 23 Sep 2021 00:00:00 +0000

Overview

Healthcare bias – based on patients’ race, gender, sexual orientation – and other factors lead to health disparities, such as lack of appropriate treatment and inadequate pain support. Such biases are often unintentional and “hidden” in communication between patients and doctors.

Existing approaches to address hidden bias are limited because they are removed from actual patient-doctor interactions in which bias hides. Technology offers an opportunity to design new approaches that can make den bias more visible and thus addressable.

We are investigating a new approach to address hidden healthcare bias by improving patient-doctor communication in primary care. This approach monitors body language for signs of bias and provides feedback to raise awareness of patients and doctors for opportunities to adjust their communication style.

We are partnering closely with patients and doctors to ensure this approach is guided by their experiences and needs. Through this collaborative effort, we expect to gain a deep understanding of how hidden bias is experienced and how we can address it better in the future.

More Info here: http://unbiased.health

Funding and External Collaborations

UnBIASED ia a 5-year project, funded by the National Library of Medicine (NLMR01LM013301), and it is a collaboration between the University of Washington and the HXI Lab at UC San Diego. Our ultimate goal is to create tools to support patients and the next generation of doctors to have bias-free interactions that promote healthcare access, quality, and equity.

SocialLM

Assessing communication at scale is the bottleneck. SocialLM asks whether large language models can track social behaviors directly from clinical transcripts without fine-tuning, and finds that they can, but unevenly: performance varies by patient race and by segment of the visit. Because that variability is itself an equity problem, the work introduces an agreement-weighted ensemble that improves both accuracy and stability, giving a practical route to social signal tracking at scale.

ChronoSense and Lab-in-a-Box

Mon, 27 Sep 2021 00:00:00 +0000

Screenshot of the ChronoSense UI. This tool enables a user to simultaneously capture multiple streams of multimodal data for use at a later point in time. It also allows for real-time and near-time analysis through it’s extensible plugin interface.

Overview

ChronoSense was born to serve researchers of all kinds helping them more easily conduct observational research. Temporally aware and aligned data capture can be incredibly difficult when multiple software has to be used to collect disparate data from cameras, microphones, screen capture software, eye trackers, and more. Post-hoc alignment can be time-consuming as well as technically challenging, requiring special hardware, environment artifacts, or even special computational tooling. By providing a unified environment for the capture of multiple data streams, ChronoSense massively simplifies the issue, giving observational researchers a tool to easily and quickly record data

Moving beyond observational research we enter into interventional studies, where the goal is to not just study humans but to also generate some sort of artifact that may provide some sort of feedback, support behavior modification, or otherwise prompt reflection that facilitates changes. On this front ChronoSense seeks to empower researchers with a data capture tool that can be extended to also perform inference as well as inform intervention design.