Faculty Bibliography

UNav is a computer-vision-based localization and navigation aid that provides step-by-step route instructions to reach selected destinations without any infrastructure in both indoor and outdoor environments. Despite the initial literature highlighting UNav's potential, clinical efficacy has not yet been rigorously evaluated. Herein, we assess UNav against standard in-person travel directions (SIPTD) for persons with blindness or low vision (PBLV) in an ecologically valid environment using a non-inferiority design. Twenty BLV subjects (age = 38 ± 8.4; nine females) were recruited and asked to navigate to a variety of destinations, over short-range distances (<200 m), in unfamiliar spaces, using either UNav or SIPTD. Navigation performance was assessed with nine dependent variables to assess travel confidence, as well as spatial and temporal performances, including path efficiency, total time, and wrong turns. The results suggest that UNav is not only non-inferior to the standard-of-care in wayfinding (SIPTD) but also superior on 8 out of 9 metrics, as compared to SIPTD. This study highlights the range of benefits computer vision-based aids provide to PBLV in short-range navigation and provides key insights into how users benefit from this systematic form of computer-aided guidance, demonstrating transformative promise for educational attainment, gainful employment, and recreational participation.

People with blindness and low vision (pBLV) encounter substantial challenges when it comes to comprehensive scene recognition and precise object identification in unfamiliar environments. Additionally, due to the vision loss, pBLV have difficulty in accessing and identifying potential tripping hazards independently. Previous assistive technologies for the visually impaired often struggle in real-world scenarios due to the need for constant training and lack of robustness, which limits their effectiveness, especially in dynamic and unfamiliar environments, where accurate and efficient perception is crucial. Therefore, we frame our research question in this paper as: How can we assist pBLV in recognizing scenes, identifying objects, and detecting potential tripping hazards in unfamiliar environments, where existing assistive technologies often falter due to their lack of robustness? We hypothesize that by leveraging large pretrained foundation models and prompt engineering, we can create a system that effectively addresses the challenges faced by pBLV in unfamiliar environments. Motivated by the prevalence of large pretrained foundation models, particularly in assistive robotics applications, due to their accurate perception and robust contextual understanding in real-world scenarios induced by extensive pretraining, we present a pioneering approach that leverages foundation models to enhance visual perception for pBLV, offering detailed and comprehensive descriptions of the surrounding environment and providing warnings about potential risks. Specifically, our method begins by leveraging a large-image tagging model (i.e., Recognize Anything Model (RAM)) to identify all common objects present in the captured images. The recognition results and user query are then integrated into a prompt, tailored specifically for pBLV, using prompt engineering. By combining the prompt and input image, a vision-language foundation model (i.e., InstructBLIP) generates detailed and comprehensive descriptions of the environment and identifies potential risks in the environment by analyzing environmental objects and scenic landmarks, relevant to the prompt. We evaluate our approach through experiments conducted on both indoor and outdoor datasets. Our results demonstrate that our method can recognize objects accurately and provide insightful descriptions and analysis of the environment for pBLV.

Background: The Visual Symptoms and Signs Screen (V-SASS) is a tool to identify vision deficits and facilitate referrals to vision specialists. The study objectives were to determine feasibility and clinician perspectives of the V-SASS. Methods: Prospective, multisite study with 141 new-onset stroke participants. After V-SASS administration, feasibility and predictive success were assessed. Results: The V-SASS identified vision symptoms and signs with high feasibility (>75%). Of those who screened positive, 93.1% had deficits in visual function or functional vision. Conclusions: The V-SASS was found to be feasible in multiple settings and accurately identify vision deficits and appropriately trigger vision referrals.

PURPOSE/OBJECTIVE:Remote patient monitoring (RPM) is a tool for patients to share data collected outside of office visits. RPM uses technology and the digital transmission of data to inform clinician decision-making in patient care. Using RPM to track routine physical activity is feasible to operationalize, given contemporary consumer-grade devices that can sync to the electronic health record. Objective monitoring through RPM can be more reliable than patient self-reporting for physical activity. DESIGN AND METHODS/METHODS:This article reports on four pilot studies that highlight the utility and practicality of RPM for physical activity monitoring in outpatient clinical care. Settings include endocrinology, cardiology, neurology, and pulmonology settings. RESULTS:The four pilot use cases discussed demonstrate how RPM is utilized to monitor physical activity, a shift that has broad implications for prediction, prevention, diagnosis, and management of chronic disease and rehabilitation progress. CLINICAL RELEVANCE/CONCLUSIONS:If RPM for physical activity is to be expanded, it will be important to consider that certain populations may face challenges when accessing digital health services. CONCLUSION/CONCLUSIONS:RPM technology provides an opportunity for clinicians to obtain objective feedback for monitoring progress of patients in rehabilitation settings. Nurses working in rehabilitation settings may need to provide additional patient education and support to improve uptake.

Significant disparities exist in detecting and treating breast cancer in women with disabilities, leading to cancer detection at advanced stages. This paper provides an overview of disparities for women with disabilities related to breast cancer screening and care, primarily focusing on significant mobility disabilities. Current care gaps include screening barriers related to accessibility and inequitable treatment options, with race/ethnicity, socioeconomic status, geographic location, and disability severity factors, mediating the disparities for this population. The reasons for these disparities are myriad and stem from both system-level deficiencies and individual-level provider bias. Although structural changes are warranted, individual healthcare providers must also be incorporated in the requisite change. Intersectionality is critical to disparities and inequities and should be central to any discussion of strategies for improving care for people with disabilities, many of whom have intersectional identities. Efforts to reduce screening rate disparities for breast cancer in women with significant mobility disabilities should start with improving accessibility through removing structural barriers, establishing comprehensive accessibility standards, and addressing healthcare provider bias. Future interventional studies are needed to implement and assess the value of programs to improve breast cancer screening rates in women with disabilities. Increasing the representation of women with disabilities in clinical trials may provide another avenue for reducing treatment disparities, as these trials often provide breakthrough treatment to women with cancer diagnosed at later stages. Ultimately, attention to the specific needs of patients with disabilities should be improved across the US to promote inclusive and effective cancer screening and treatment.