Bias in healthcare is often hidden and expressed through unintentionally prejudiced communication between providers and patients. These “implicit biases'' often relate to a patient’s race, gender, or sexual orientation. Implicit biases are automatic attitudes and stereotypes that can operate outside personal awareness and lead to unequal treatment, health disparities, and a lack of patient support. Although much research focuses on implicit bias, the perspectives of those who experience it and the impact it has on these individuals is less explored. Of particular importance are voices of Black, Indigenous, and People of color (BIPOC) and those with marginalized gender identities or sexual orientations (LGBTQ+). These groups have historically suffered from health inequities. For example, research indicates that BIPOC people may be undertreated for pain and LGBTQ+ people may be refused care. The UnBIASED project at the University of Washington and the University of California, San Diego addresses implicit bias in patient-provider communication through computational sensing tools to provide communication feedback. Through 25 interviews with people who identified as BIPOC, LGBTQ+, or both, we explored patients' perspectives on experiencing implicit bias when communicating with healthcare providers. We analyzed interviews through an inductive qualitative approach to understand negative and positive experiences, and identify participants' ideal solutions for improving patient-provider communication. For example, participants suggested having a patient advocate, providing feedback to the provider, and improving providers’ cultural competence. We report on these findings with the goal of describing common pain points and specific sources of dissatisfaction among patients who experience implicit bias. These findings help raise awareness of clinical implicit bias from the perspectives of patients, encourage further research, and suggest patient-driven, patient-centered solutions for how implicit bias can be overcome at personal and institutional levels.

After radiologists perform a set of chest-x-rays (CXRs, or radiographs) they write a short report, which is a free-text description of their observations and interpretations. Because these reports are free-text documents, there is the risk of miscommunication, which can result in reduced patient outcomes. In this study, we develop a predictive model that takes a radiology report as input and returns the probability that the report describes a positive diagnosis for pneumonia, a common respiratory condition characterized by the accumulation of fluid in the lungs. The development of such a model is challenging due to the complexity of human language (natural language). Natural language processing seeks to translate human language to a machine-understandable form. We systematically generated five predictive models. Briefly, using the R programming language, we 1) randomly assigned reports from the MIMIC-CXR database to the training set consisting of 700 reports and testing set consisting of 300 reports, 2) created a count matrix giving the frequencies of different sets of 3 consecutive words (trigram), 3) performed feature selection to identify terms that differentiate between positive and negative cases, and 4) trained the models (k nearest neighbor, random forest, gradient boosting machine, xgboost, adaboost). Our results indicate the xgboost algorithm performs the best on the testing set with a Brier Score (bs) of 0.185, but is closely followed by gradient boosting (bs=0.188), random forest (bs=0.188), adaboost (bs=0.193), and lastly, KNN (bs=0.309). These results indicate that although the xgboost model is superior, several models have similar performance. The high performance suggests machine learning models have the potential to impact patient care in radiology. Interestingly, we identified a number of reports that were consistently predicted incorrectly across all models. In collaboration with a radiologist, we plan to investigate these reports more thoroughly to improve our prediction results.

The purpose of my research is to explore the protein-ligand binding interaction by using sequence encoding and signal analysis to process and understand amino-acid sequences. Applications of this technique would be useful in a variety of biomedical fields, but more specifically in creating a platform for a unique and streamlined vaccine candidacy process. If we can encode protein/DNA sequences using electron-ion interaction-potential, then by applying various signal processing functions we can more easily identify the meaning of these complex structures. The goal in doing this would be to relate simple amino-acids, the building blocks of our genetic sequences, to numerical values which we may manipulate. Combining these inferences with a convolutional neural network, the result would create a non-empirical and efficient method of understanding protein folding and bimolecular binding interaction, specifically through predicting pIC50 binding affinity. The methodology begins with accessing a large set of human amino-acid sequence data, transforming the data using signal processing, and learning from the data to understand similarities between sequences and predict binding affinity. The anticipated results will initially be the neural networks ability to predict binding affinity. Further results and experimentation would involve tuning the model to be more adaptive and testing new data from the SARS-Cov-2 virus. The more variety of human data the model may learn from, the more adaptive and accurate it will predict pIC50 values in an efficient, non-empirical manner.

Adolescents are vulnerable to high levels of stress in their lives that usually result from school, relationships, and family life. Approximately 27% of US teens report very high levels of daily stress, and 31% report feeling overwhelmed from negative stress. The data of fluctuating stress levels throughout the day can facilitate formulating effective stress measurement and reduction techniques for teens, which is imperative to support this vulnerable population. Using social robots to collect these data and offer mental-health counseling can be very cost-effective and scalable to intervene in critical mental health situations in adolescents worldwide. Today’s teens are the first generation to spend a lifetime living and increasingly experiencing human-computer interaction. According to far-seeing scholars, it is critical to innovate, design, and prototype technologies enhancing the connection between humans and robots targeting next generations. A wide array of research in human-robot interaction (HRI) focuses on specific age groups, where assistive technologies are mostly used to help the populations of elderly people and young children. However, very little research has been conducted to address teen-stress, or teen-robot interaction. My research in Project EMAR (Ecological Momentary Assessment Robot) aims to collect in-the-moment data from teens to map their stress and mood levels and offer counseling through a social robot EMAR focusing specifically on interventions for Dialectic Behavioral Therapy (DBT), and Acceptance and Commitment Therapy (ACT), two evidence-based therapies with efficacy treating teenager’s mental health. EMAR interacts with teens intimately through activities containing sounds, texts and images to collect data measuring moods and stress with EMA (Ecological Momentary Assessment) technique. EMA allows adolescents to report on sensations, feelings and behaviors close in time to actual experiences. Thus, EMA effectively minimizes recall bias, maximizes ecological validity, and allows study of micro processes that influence behavior in real-world contexts.

Blockchain is a distributed ledger technology that promises greater efficiency, security and transparency than traditional centralized ledger technologies through the use of consensus mechanisms, incentivized participation, and immutable smart contracts, among other features. For much of its history, Blockchain was predominantly divided into public, permissionless platforms and private, permissioned platforms, but in recent years these categories have expanded to include both consortium and hybrid blockchains. Hybrid blockchain in particular offers a unique solution for industries like supply chain management (SCM) and logistics which cannot operate on a strictly public or private basis, and struggle to establish trust between parties. Motivated by the current lack of research and example implementations of hybrid blockchain, especially in SCM and logistics contexts, the objective of this research is to contribute to the existing literature by designing and implementing a prototype hybrid blockchain-based dApp (decentralized app) focused on addressing issues within the supply chain management and logistics industry. Additionally, our secondary objective is to synthesize our review of the currently available literature on hybrid blockchain and its application in SCM and logistics into an easily digestible format, which will help outline the specific benefits hybrid blockchain provides in SCM use cases as compared to other forms of blockchain. Ultimately, our goal is to help fill the hybrid blockchain research gap by synthesizing the current literature, and providing an example hybrid blockchain implementation as reference for organizations considering implementing hybrid blockchain solutions, especially in SCM and logistics contexts. This presentation will include a brief introduction to hybrid blockchain and SCM use cases as well as an overview of our dApp design schema.

People who are blind or visually impaired (BVI) use computers with accessibility technology called screen readers. The linear nature of these screen reader interactions makes understanding or navigating hierarchical structures like nested menus or tabular content on the web difficult for BVI users. To improve the experience of non-visually navigating nonlinear data, previous work introduced Spatial Region Interaction Techniques (SPRITEs) for nonvisual access- a novel method for navigating two-dimensional structures using the keyboard. Though the SPRITEs techniques proved to be valuable for BVI users to complete spatial tasks, the evaluation that led to this result was limited to a lab setting. Our work expands on the previous exploration by implementing a subset of SPRITEs techniques related to table navigations in the form of an add-on for NVDA, the most used screen reader according to the WebAIM screen reader survey. The development of the add-on opens up the possibility of conducting a field study where we could collect data and feedback from BVI users and investigate the efficacy of SPRITEs in enhancing their day-to-day web browsing experience outside of the lab setting. We introduce SPRITEs table navigation and discuss a tutorial designed to teach this to BVI users, the result of a pilot study on the SPRITEs NVDA add-on with a blind participant, and the learnings that helped improve the web-based tutorial for the add-on. We close by outlining plans for a future field study. We anticipate the study to inform future iterations of SPRITEs as well as gather insights on the BVI community adaptation of the novel nonlinear navigation techniques distinct from traditional screen reader interactions, and offer exemplary evidence of translating research to reach the end-user.

Supply chain consists of the networking between companies and suppliers to ensure the proper manufacturing of products to the consumer. A successful supply chain requires effective end-to-end traceability to ensure the authenticity and safety of the materials being processed and distributed. Challenges associated with increasing complexity, insufficient networking, and third-party trust issues have led to the search for new frameworks to satisfy supply chain management needs. Blockchain, with its out-of-the-box trust management, immutability, transparency, and decentralized nature has become a promising next step for suppliers and businesses. Popular solutions such as Ethereum, Hyperledger Fabric, and Hyperledger Sawtooth solve these challenges by improving the communication, trust management, and scalability of supply chain applications. Through the use of smart contracts and cryptographic verification, users can add logic to the supply chain without requiring an understanding of the core system. We look past this with the aim to build upon the current methodologies, by conducting a feasibility analysis on the core mechanisms and internal design choices within these applications which are overlooked in current literature. Our presentation consists of defining the preliminary terms, a literature review, and an explanation of the implementation-level parameters to provide insights into the core bottlenecks and potential vulnerabilities within these supply chain systems.