Try a new search

Format these results:

Searched for:

person:rizzoj01 or hudsot01

active:yes

exclude-minors:true

Total Results:

100


A Multi-Modal Foundation Model to Assist People with Blindness and Low Vision in Environmental Interaction

Hao, Yu; Yang, Fan; Huang, Hao; Yuan, Shuaihang; Rangan, Sundeep; Rizzo, John Ross; Wang, Yao; Fang, Yi
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.
SCOPUS:85194155730
ISSN: 2313-433x
CID: 5659742

A Multi-Modal Foundation Model to Assist People with Blindness and Low Vision in Environmental Interaction

Hao, Yu; Yang, Fan; Huang, Hao; Yuan, Shuaihang; Rangan, Sundeep; Rizzo, John-Ross; Wang, Yao; Fang, Yi
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.
PMCID:11122237
PMID: 38786557
ISSN: 2313-433x
CID: 5655102

Feasibility and Clinician Perspectives of the Visual Symptoms and Signs Screen: A Multisite Pilot Study

Roberts, Pamela S.; Wertheimer, Jeffrey; Ouellette, Debra; Hreha, Kimberly; Watters, Kelsey; Fielder, Jaimee; Graf, Min Jeong P.; Weden, Kathleen M.; Rizzo, John Ross
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.
SCOPUS:85182920425
ISSN: 0882-7524
CID: 5629402

Accuracy and Usability of Smartphone-Based Distance Estimation Approaches for Visual Assistive Technology Development

Hamilton-Fletcher, Giles; Liu, Mingxin; Sheng, Diwei; Feng, Chen; Hudson, Todd E.; Rizzo, John Ross; Chan, Kevin C.
Goal: Distance information is highly requested in assistive smartphone Apps by people who are blind or low vision (PBLV). However, current techniques have not been evaluated systematically for accuracy and usability. Methods: We tested five smartphone-based distance-estimation approaches in the image center and periphery at 1-3 meters, including machine learning (CoreML), infrared grid distortion (IR_self), light detection and ranging (LiDAR_back), and augmented reality room-tracking on the front (ARKit_self) and back-facing cameras (ARKit_back). Results: For accuracy in the image center, all approaches had <±2.5 cm average error, except CoreML which had ±5.2-6.2 cm average error at 2-3 meters. In the periphery, all approaches were more inaccurate, with CoreML and IR_self having the highest average errors at ±41 cm and ±32 cm respectively. For usability, CoreML fared favorably with the lowest central processing unit usage, second lowest battery usage, highest field-of-view, and no specialized sensor requirements. Conclusions: We provide key information that helps design reliable smartphone-based visual assistive technologies to enhance the functionality of PBLV.
SCOPUS:85183662391
ISSN: 2644-1276
CID: 5700992

Implementing Remote Patient Monitoring of Physical Activity in Clinical Practice

McCarthy, Margaret; Jevotovsky, David; Mann, Devin; Veerubhotla, Akhila; Muise, Eleanor; Whiteson, Jonathan; Rizzo, John Ross
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.
PMID: 37723623
ISSN: 2048-7940
CID: 5591172

Disparities in Breast Cancer Patients with Disabilities: Care Gaps, Accessibility, and Best Practices

Keegan, Grace; Rizzo, John-Ross; Joseph, Kathie-Ann
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.
PMID: 37421404
ISSN: 1460-2105
CID: 5539552

Methodological Issues Relevant to Blinding in Physical Medicine and Rehabilitation Research

Annaswamy, Thiru; Cunniff, Kegan; Rizzo, J R; Naeimi, Tahereh; Kumbhare, Dinesh; Batavia, Mitchell
Blinding in research is important and the field of PM&R poses special consideration due to the patient populations and treatment methodologies used. Historically, blinding has been increasingly relevant to conducting good quality research. The main reason to blind is to reduce bias. There are several strategies to blinding. At times, when blinding is not possible, alternatives to blinding include sham control and description of study and control groups. Illustrative examples of blinding used in PM&R research are described in this article along with how to assess success and fidelity of blinding.
PMID: 36897811
ISSN: 1537-7385
CID: 5432942

Virtual reality as a means to explore assistive technologies for the visually impaired

Ricci, Fabiana Sofia; Boldini, Alain; Ma, Xinda; Beheshti, Mahya; Geruschat, Duane R; Seiple, William H; Rizzo, John-Ross; Porfiri, Maurizio
Visual impairment represents a significant health and economic burden affecting 596 million globally. The incidence of visual impairment is expected to double by 2050 as our population ages. Independent navigation is challenging for persons with visual impairment, as they often rely on non-visual sensory signals to find the optimal route. In this context, electronic travel aids are promising solutions that can be used for obstacle detection and/or route guidance. However, electronic travel aids have limitations such as low uptake and limited training that restrict their widespread use. Here, we present a virtual reality platform for testing, refining, and training with electronic travel aids. We demonstrate the viability on an electronic travel aid developed in-house, consist of a wearable haptic feedback device. We designed an experiment in which participants donned the electronic travel aid and performed a virtual task while experiencing a simulation of three different visual impairments: age-related macular degeneration, diabetic retinopathy, and glaucoma. Our experiments indicate that our electronic travel aid significantly improves the completion time for all the three visual impairments and reduces the number of collisions for diabetic retinopathy and glaucoma. Overall, the combination of virtual reality and electronic travel aid may have a beneficial role on mobility rehabilitation of persons with visual impairment, by allowing early-phase testing of electronic travel aid prototypes in safe, realistic, and controllable settings.
PMCID:10281573
PMID: 37339135
ISSN: 2767-3170
CID: 5542612

Wearables for Persons with Blindness and Low Vision: Form Factor Matters

Han, Yangha Hank; Beheshti, Mahya; Jones, Blake; Hudson, Todd E; Seiple, William H; Rizzo, John-Ross Jr
Based on statistics from the WHO and the International Agency for the Prevention of Blindness, an estimated 43.3 million people have blindness and 295 million have moderate and severe vision impairment globally as of 2020, statistics expected to increase to 61 million and 474 million respectively by 2050, staggering numbers. Blindness and low vision (BLV) stultify many activities of daily living, as sight is beneficial to most functional tasks. Assistive technologies for persons with blindness and low vision (pBLV) consist of a wide range of aids that work in some way to enhance one's functioning and support independence. Although handheld and head-mounted approaches have been primary foci when building new platforms or devices to support function and mobility, this perspective reviews potential shortcomings of these form factors or embodiments and posits that a body-centered approach may overcome many of these limitations.
PMID: 37115821
ISSN: 1949-3614
CID: 5465582

The BLV App Arcade: a new curated repository and evaluation rubric for mobile applications supporting blindness and low vision

Liu, Bennett M; Beheshti, Mahya; Naeimi, Tahareh; Zhu, Zhigang; Vedanthan, Rajesh; Seiple, William; Rizzo, John-Ross
PURPOSE/UNASSIGNED:Visual impairment-related disabilities have become increasingly pervasive. Current reports estimate a total of 36 million persons with blindness and 217 million persons with moderate to severe visual impairment worldwide. Assistive technologies (AT), including text-to-speech software, navigational/spatial guides, and object recognition tools have the capacity to improve the lives of people with blindness and low vision. However, access to such AT is constrained by high costs and implementation barriers. More recently, expansive growth in mobile computing has enabled many technologies to be translated into mobile applications. As a result, a marketplace of accessibility apps has become available, yet no framework exists to facilitate navigation of this voluminous space. MATERIALS AND METHODS/UNASSIGNED:We developed the BLV (Blind and Low Vision) App Arcade: a fun, engaging, and searchable curated repository of app AT broken down into 11 categories spanning a wide variety of themes from entertainment to navigation. Additionally, a standardized evaluation metric was formalized to assess each app in five key dimensions: reputability, privacy, data sharing, effectiveness, and ease of use/accessibility. In this paper, we describe the methodological approaches, considerations, and metrics used to find, store and score mobile applications. CONCLUSION/UNASSIGNED:The development of a comprehensive and standardized database of apps with a scoring rubric has the potential to increase access to reputable tools for the visually impaired community, especially for those in low- and middle-income demographics, who may have access to mobile devices but otherwise have limited access to more expensive technologies or services.
PMID: 36927193
ISSN: 1748-3115
CID: 5495902