Clinical Research Directory

Isolating and Mitigating Sequentially Dependent Perceptual Errors in Clinical Visual Search

Remote-store-and-forward teledermatology has recently grown exponentially in popularity and use as an efficient, accurate, and cost-effective way to improve the health and well-being of countless patients. Despite advances in machine learning and computer vision, the screening and reading of dermatological images still depends on the visual system of human observers (e.g., clinicians), who receive extensive training to best recognize lesions and anomalies. In remote store-and-forward teledermatology settings, clinicians may examine hundreds of images on a daily basis, seeing several images one after the other. A main underlying assumption of their work is that clinician percepts and decisions about a current image are completely independent from prior viewings. However, we and other groups demonstrated that the visual system has visual serial dependencies (VSDs) at many levels, from perception to decision making, including in clinical tasks. These sequential dependencies, replicated hundreds of times in the literature, mean that what was seen in the past influences (and captures) what is seen and reported at this moment. Theoretically, VSDs are helpful in an autocorrelated natural world, but they are suboptimal in visual tasks conducted in artificial situations where images are not always related. Importantly, serial dependencies in perceptual processing could thus produce significant errors during diagnostic judgments of dermatological images. Our central hypothesis is that VSD can have a disruptive effect in asynchronous remote-store-and-forward teledermatology judgments that impairs accurate detection and recognition of lesions. This hypothesis is supported by our robust pilot data, which show that VSD strongly biases lesion classification in both untrained observers and expert clinicians. The rationale for the proposed research projects is that once it is known how serial dependence arises and how it impacts judgments, we can understand how to control for it. Hence, accuracy of lesion detection and diagnosis can significantly improve. The specific objectives of this proposal are to establish (Aim 1), identify (Aim 2) and mitigate (Aim 3) the impact of VSD on remote-store-and-forward dermatological judgments.

Visual Function Screening System With Special Needs Children and Typical Preschoolers

The early visual screening of children plays a critical role in promoting visual development, especially for those with visual impairments. Among various approaches, eye-tracking based visual assessment has emerged as a promising tool, particularly for infants, toddlers, and children with developmental disabilities who are unable to complete traditional vision tests. The object of this study is to design and investigate the effectiveness of using a deep learning based, individualized eye-tracking system to assess visual function, specifically visual acuity and visual field, in typical preschool children and infants under the age of three. This study aims to establish a reliable, noninvasive visual screening method that accommodates the diverse needs and abilities of young children.

Leveraging Artificial Intelligence to Prevent Vision Loss From Diabetes Among Socioeconomically Disadvantaged Communities

This study aims to investigate whether a novel artificial intelligence based screening strategy (AI-Based point of caRe, Incorporating Diagnosis, SchedulinG, and Education or AI-BRIDGE), which allows primary care providers to screen patients for vision-threatening diabetic eye disease in the primary care clinic, improves screening and follow-up care rates across race/ethnicity groups and reduces racial/ethnic disparities in screening.

Experiment 2: One Target in Many Situations

The goal is to look for qualitative differences in visual search behavior when one search is performed many times in a row compared to when multiple search tasks are intermixed. Four search tasks are tested. The target is the same in every task but the types of distractors change from task to task. In the Mixed condition, the four tasks are randomly changed from trial to trial. In the Blocked condition, each task is run as a block of 100 trials.

Mixed Vs Blocked Search: Four Unique Tasks

The goal is to look for qualitative differences in visual search behavior when one search is performed many times in a row compared to when multiple search tasks are intermixed. Four search tasks are tested. In the Mixed condition, the four tasks are randomly changed from trial to trial. In the Blocked condition, each task is run as a block of 100 trials.

Experiment 3: Mixed vs Blocked; Dashboard Paradigm

The goal is to look for qualitative differences in visual search behavior when one search is performed many times in a row compared to when multiple search tasks are intermixed. Four search tasks are tested. The target is the same in every task but the types of distractors change from task to task. In this version, observers get some degree of choice in what they are searching.

Eye and Carotenoid Augmentation Research and Evaluation (EyeCARE)

The primary study outcomes are to investigate the effects of 4-month daily carotenoid complex supplementation on carotenoid status in the macula and skin and visual fatigue among adults 20-45 years of age. Secondary outcomes will examine the supplementation effects on cognitive function.

Intermediate Visual Space Perception

The ability to judge the locations of various objects from oneself during self-motion in the intermediate distance range (\~2-25m) is crucial for successful performance of activities of daily living, such as walking and driving. However, little is known about the mechanisms of visual space perception involved in judging distance, the focus of this project, in the planning and/or execution of self-motion in the natural 3D environment. The theoretical knowledge to be gained from this project will contribute to the scientific literature and provide insights into how eye and neurological defects could impair visual space perception, wayfinding, and mobility.