Medicine and Health Sciences Commons^™

Use Gpt-J Prompt Generation With Roberta For Ner Models On Diagnosis Extraction Of Periodontal Diagnosis From Electronic Dental Records, Yao-Shun Chuang, Xiaoqian Jiang, Chun-Teh Lee, Ryan Brandon, Duong Tran, Oluwabunmi Tokede, Muhammad F Walji

Faculty, Staff and Student Publications

This study explored the usability of prompt generation on named entity recognition (NER) tasks and the performance in different settings of the prompt. The prompt generation by GPT-J models was utilized to directly test the gold standard as well as to generate the seed and further fed to the RoBERTa model with the spaCy package. In the direct test, a lower ratio of negative examples with higher numbers of examples in prompt achieved the best results with a F1 score of 0.72. The performance revealed consistency, 0.92-0.97 in the F1 score, in all settings after training with the RoBERTa model. …

Towards Fair Patient-Trial Matching Via Patient-Criterion Level Fairness Constraint, Chia-Yuan Chang, Jiayi Yuan, Sirui Ding, Qiaoyu Tan, Kai Zhang, Xiaoqian Jiang, Xia Hu, Na Zou

Faculty, Staff and Student Publications

Clinical trials are indispensable in developing new treatments, but they face obstacles in patient recruitment and retention, hindering the enrollment of necessary participants. To tackle these challenges, deep learning frameworks have been created to match patients to trials. These frameworks calculate the similarity between patients and clinical trial eligibility criteria, considering the discrepancy between inclusion and exclusion criteria. Recent studies have shown that these frameworks outperform earlier approaches. However, deep learning models may raise fairness issues in patient-trial matching when certain sensitive groups of individuals are underrepresented in clinical trials, leading to incomplete or inaccurate data and potential harm. To …

The Kynurenine Pathway In Alzheimer’S Disease: A Meta-Analysis Of Central And Peripheral Levels, Brisa S Fernandes, Mehmet Enes Inam, Nitesh Enduru, Joao Quevedo, Zhongming Zhao

Faculty, Staff and Student Publications

OBJECTIVE: Changes in the kynurenine pathway are recognized in psychiatric disorders, but their role in Alzheimer's disease (AD) is less clear. We aimed to conduct a systematic review and meta-analysis to determine whether tryptophan and kynurenine pathway metabolites are altered in AD.

METHODS: We performed a systematic review and random-effects meta-analyses. Inclusion criteria were studies that compared AD and cognitively normal (CN) groups and assessed tryptophan or kynurenine pathway metabolites in cerebrospinal fluid or peripheral blood.

RESULTS: Twenty-two studies with a total of 1,356 participants (664 with AD and 692 CN individuals) were included. Tryptophan was decreased only in peripheral …

Automated Detection Of Hippocampal Sclerosis Using Real-World Clinical Mri Images, Jingwen Jiang, Jiajun Qiu, Jin Yin, Junren Wang, Xinyue Jiang, Zuo Yi, Yang Chen, Xiaobo Zhou, Xiutian Sima

Faculty, Staff and Student Publications

BACKGROUND: Hippocampal sclerosis (HS) is the most common pathological type of temporal lobe epilepsy (TLE) and one of the important surgical markers. Currently, HS is mainly diagnosed manually by radiologists based on visual inspection of MRI, which greatly relies on MRI quality and physician experience. In clinical practice, non-thin MRI scans are often used due to the time and efficiency needed for the acquisition. However, these scans can be difficult for junior physicians to interpret accurately. Thus, the rapid and accurate diagnosis of HS using real-world MRI images in clinical settings is a challenging task.

OBJECTIVE: Our aim was to …

Machine Learning Framework For Real-World Electronic Health Records Regarding Missingness, Interpretability, And Fairness, Jing Lucas Liu

Theses and Dissertations--Computer Science

Machine learning (ML) and deep learning (DL) techniques have shown promising results in healthcare applications using Electronic Health Records (EHRs) data. However, their adoption in real-world healthcare settings is hindered by three major challenges. Firstly, real-world EHR data typically contains numerous missing values. Secondly, traditional ML/DL models are typically considered black-boxes, whereas interpretability is required for real-world healthcare applications. Finally, differences in data distributions may lead to unfairness and performance disparities, particularly in subpopulations.

This dissertation proposes methods to address missing data, interpretability, and fairness issues. The first work proposes an ensemble prediction framework for EHR data with large missing …

Architectural Design Of A Blockchain-Enabled, Federated Learning Platform For Algorithmic Fairness In Predictive Health Care: Design Science Study, Xueping Liang, Juan Zhao, Yan Chen, Eranga Bandara, Sachin Shetty

VMASC Publications

Background: Developing effective and generalizable predictive models is critical for disease prediction and clinical decision-making, often requiring diverse samples to mitigate population bias and address algorithmic fairness. However, a major challenge is to retrieve learning models across multiple institutions without bringing in local biases and inequity, while preserving individual patients' privacy at each site.

Objective: This study aims to understand the issues of bias and fairness in the machine learning process used in the predictive health care domain. We proposed a software architecture that integrates federated learning and blockchain to improve fairness, while maintaining acceptable prediction accuracy and minimizing overhead …

A Query Engine For Self-Controlled Case Series, With An Application To Covid-19 Ehr Data, Xiaojin Li, Yan Huang, Licong Cui, Guo-Qiang Zhang

Faculty, Staff and Student Publications

Self-controlled case series (SCCS) is a statistical method in epidemiological study design that uses individuals as their own controls, with comparisons made within the same individuals at different time points of observation. SCCS has been applied in settings where it is difficult to identify comparison or control groups. To provide computational support for SCCS, we introduce a query engine called Self-Controlled Case Query (SCCQ) and use it to extract cohorts of self-controlled case series from a large-scale COVID-19 Electronic Health Records (EHR) dataset. Visual summary of the queried population through the R-Shiny visualization framework offers SCCQ's query result dashboard to …

Federated Learning Based Futuristic Biomedical Big-Data Analysis And Standardization, Afifa Salsabil Fathima, Syed Muzamil Basha, Syed Thouheed Ahmed, Sandeep Kumar Mathivanan, Sukumar Rajendran, Saurav Mallik, Zhongming Zhao

Faculty, Staff and Student Publications

Medical data processing and analytics exert significant influence in furnishing dependable decision support for prospective biomedical applications. Given the sensitive nature of medical data, specialized techniques and frameworks tailored for application-centric processing are imperative. This article presents a conceptualization for the analysis and uniformitarian of datasets through the implementation of Federated Learning (FL). The realm of medical big data stems from diverse origins, necessitating the delineation of data provenance and attribute paradigms to facilitate feature extraction and dependency assessment. The architecture governing the data collection framework is intricately linked to remote data transmission, thereby engendering efficient customization oversight. The operational …

Machine Learning-Driven Exploration Of Drug Therapies For Triple-Negative Breast Cancer Treatment, Aman Chandra Kaushik, Zhongming Zhao

Faculty, Staff and Student Publications

Breast cancer is the second leading cause of cancer death in women among all cancer types. It is highly heterogeneous in nature, which means that the tumors have different morphologies and there is heterogeneity even among people who have the same type of tumor. Several staging and classifying systems have been developed due to the variability of different types of breast cancer. Due to high heterogeneity, personalized treatment has become a new strategy. Out of all breast cancer subtypes, triple-negative breast cancer (TNBC) comprises ∼10%-15%. TNBC refers to the subtype of breast cancer where cells do not express estrogen receptors, …

Predictive Digital Twin For Optimizing Patient-Specific Radiotherapy Regimens Under Uncertainty In High-Grade Gliomas, Anirban Chaudhuri, Graham Pash, David A Hormuth, Guillermo Lorenzo, Michael Kapteyn, Chengyue Wu, Ernesto A B F Lima, Thomas E Yankeelov, Karen Willcox

Faculty, Staff and Student Publications

We develop a methodology to create data-driven predictive digital twins for optimal risk-aware clinical decision-making. We illustrate the methodology as an enabler for an anticipatory personalized treatment that accounts for uncertainties in the underlying tumor biology in high-grade gliomas, where heterogeneity in the response to standard-of-care (SOC) radiotherapy contributes to sub-optimal patient outcomes. The digital twin is initialized through prior distributions derived from population-level clinical data in the literature for a mechanistic model's parameters. Then the digital twin is personalized using Bayesian model calibration for assimilating patient-specific magnetic resonance imaging data. The calibrated digital twin is used to propose optimal …

The Short- And Long-Term Readmission Of Four Major Categories Of Digestive System Cancers: Does Obesity Or Metabolic Disorder Matter?, Yan Li, Xiaoqin Wu, Yongfeng Song, Peipei Wang, Bofei Zhang, Bingzhou Guo, Ziwei Liu, Yafei Wu, Shanshan Shao, Yiping Cheng, Honglin Guo, Xiude Fan, Jiajun Zhao

Faculty, Staff and Student Publications

Purpose: Patients with digestive system cancers (DSCs) are at a high risk for hospitalizations; however, the risk factors for readmission remain unknown. Here, we established a retrospective cohort study to assess the association between metabolic obesity phenotypes and readmission risks of DSC.

Experimental design: A total of 142,753 and 74,566 patients at index hospitalization were ultimately selected from the Nationwide Readmissions Database (NRD) 2018 to establish the 30-day and 180-day readmission cohorts, respectively. The study population was classified into four groups: metabolically healthy non-obese (MHNO), metabolically healthy obese (MHO), metabolically unhealthy non-obese (MUNO), and metabolically unhealthy obese (MUO). Multivariate Cox …

Receptor-Interacting Protein 1 And 3 Kinase Activity Are Required For High-Fat Diet Induced Liver Injury In Mice, Xiaoqin Wu, Rakesh K Arya, Emily Huang, Megan R Mcmullen, Laura E Nagy

Faculty, Staff and Student Publications

BACKGROUND: The RIP1-RIP3-MLKL-mediated cell death pathway is associated with progression of non-alcohol-associated fatty liver/steatohepatitis (NAFL/NASH). Previous work identified a critical role for MLKL, the key effector regulating necroptosis, but not RIP3, in mediating high fat diet-induced liver injury in mice. RIP1 and RIP3 have active N-terminus kinase domains essential for activation of MLKL and subsequent necroptosis. However, little is known regarding domain-specific roles of RIP1/RIP3 kinase in liver diseases. Here, we hypothesized that RIP1/RIP3 kinase activity are required for the development of high fat diet-induced liver injury.

METHODS:Rip1K45A/K45A and Rip3K51A/K51A kinase-dead mice on a C57BL/6J background and their littermate …

Acute Myeloid Leukemia With Concurrent Npm1 And Runx1 Mutations, Zhuang Zuo, L Jeffrey Medeiros, C Cameron Yin

Faculty, Staff and Student Publications

NPM1 mutation, as a founding genetic event, cooperates with other gene mutations, such as DNMT3A and FLT3, to promote the development of acute myeloid leukemia. NPM1 mutation, however, has been reported to be mutually exclusive with RUNX1 mutation in acute myeloid leukemia cases. In this study, we analyzed mutation panel testing data from a relatively large cohort of rare AML cases with both NPM1 and RUNX1 mutations. We describe the dynamic process of the emergence of these mutations, as well as molecular genetic features and clinical outcome of these patients. We show that concurrence of both mutations in acute …

Integrated Clinical Genotype-Phenotype Characteristics Of Early T-Cell Precursor Acute Lymphoblastic Leukemia, Matthew T Ye, Yi Wang, Zhuang Zuo, Steliana Calin, Hua He, Zhenya Tang, Elias J Jabbour, Gautam Borthakur, Yizhuo Zhang, Yaling Yang, M James You

Faculty, Staff and Student Publications

Background: Early T-cell precursor acute lymphoblastic leukemia (ETP-ALL) is a distinct subtype of T-ALL with a unique immunophenotype and high treatment failure rate. The molecular genetic abnormalities and their prognostic impact in ETP-ALL patients are poorly understood.

Methods: The authors performed systematic analyses of the clinicopathologic features with an emphasis on molecular genetic aspects of 32 patients with ETP-ALL.

Results: The median age was 43 years (range, 16-71). The blasts were positive for cytoplasmic CD3 and CD7 and negative for CD1a and CD8. Other markers expressed included CD34 (88%), CD33 (72%), CD117 (68%), CD13 (58%), CD5 (partial, 56%), CD2 (38%), …

Revolutionizing Bone Regeneration: Advanced Biomaterials For Healing Compromised Bone Defects, Kamal Awad, Neelam Ahuja, Ahmed S Yacoub, Leticia Brotto, Simon Young, Antonios Mikos, Pranesh Aswath, Venu Varanasi

Faculty, Staff and Student Publications

In this review, we explore the application of novel biomaterial-based therapies specifically targeted towards craniofacial bone defects. The repair and regeneration of critical sized bone defects in the craniofacial region requires the use of bioactive materials to stabilize and expedite the healing process. However, the existing clinical approaches face challenges in effectively treating complex craniofacial bone defects, including issues such as oxidative stress, inflammation, and soft tissue loss. Given that a significant portion of individuals affected by traumatic bone defects in the craniofacial area belong to the aging population, there is an urgent need for innovative biomaterials to address the …

Ribonuclease 1 Enhances Antitumor Immunity Against Breast Cancer By Boosting T Cell Activation, Ying-Nai Wang, Heng-Huan Lee, Zhou Jiang, Li-Chuan Chan, Gabriel N Hortobagyi, Dihua Yu, Mien-Chie Hung

Faculty, Staff and Student Publications

The secretory enzyme human ribonuclease 1 (RNase1) is involved in innate immunity and anti-inflammation, achieving host defense and anti-cancer effects; however, whether RNase1 contributes to adaptive immune response in the tumor microenvironment (TME) remains unclear. Here, we established a syngeneic immunocompetent mouse model in breast cancer and demonstrated that ectopic RNase1 expression significantly inhibited tumor progression. Overall changes in immunological profiles in the mouse tumors were analyzed by mass cytometry and showed that the RNase1-expressing tumor cells significantly induced CD4+ Th1 and Th17 cells and natural killer cells and reduced granulocytic myeloid-derived suppressor cells, supporting that RNase1 favors an antitumor …

Sound Speed Estimation For Distributed Aberration Correction In Laterally Varying Media, Rehman Ali, Trevor M Mitcham, Melanie Singh, Marvin M Doyley, Richard R Bouchard, Jeremy J Dahl, Nebojsa Duric

Faculty, Staff and Student Publications

Spatial variation in sound speed causes aberration in medical ultrasound imaging. Although our previous work has examined aberration correction in the presence of a spatially varying sound speed, practical implementations were limited to layered media due to the sound speed estimation process involved. Unfortunately, most models of layered media do not capture the lateral variations in sound speed that have the greatest aberrative effect on the image. Building upon a Fourier split-step migration technique from geophysics, this work introduces an iterative sound speed estimation and distributed aberration correction technique that can model and correct for aberrations resulting from laterally varying …

Naproxen Chemoprevention Induces Proliferation Of Cytotoxic Lymphocytes In Lynch Syndrome Colorectal Mucosa, Charles M Bowen, Nan Deng, Laura Reyes-Uribe, Edwin Roger Parra, Pedro Rocha, Luisa M Solis, Ignacio I Wistuba, Valerie O Sepeda, Lana Vornik, Marjorie Perloff, Eva Szabo, Asad Umar, Krishna M Sinha, Powel H Brown, Eduardo Vilar

Faculty, Staff and Student Publications

BACKGROUND: Recent clinical trial data from Lynch Syndrome (LS) carriers demonstrated that naproxen administered for 6-months is a safe primary chemoprevention that promotes activation of different resident immune cell types without increasing lymphoid cellularity. While intriguing, the precise immune cell types enriched by naproxen remained unanswered. Here, we have utilized cutting-edge technology to elucidate the immune cell types activated by naproxen in mucosal tissue of LS patients.

METHODS: Normal colorectal mucosa samples (pre- and post-treatment) from a subset of patients enrolled in the randomized and placebo-controlled 'Naproxen Study' were obtained and subjected to a tissue microarray for image mass cytometry …

Membranous Nephropathy In Chronic Lymphocytic Leukemia Responsive To Ibrutinib: A Case Report, Anna-Eve Turcotte, William F Glass, Jamie S Lin, Jan A Burger

Faculty, Staff and Student Publications

Membranous nephropathy (MN) is an uncommon renal presentation in patients with chronic lymphocytic leukemia (CLL), and as such, there is no standard therapy for these patients. A few cases of MN in CLL have been described with varying success in MN treatment involving alkylating agents and fludarabine. Here we report the first case of MN in a patient with CLL treated with ibrutinib with complete renal response. This presentation underlines the importance of recognizing rare glomerular diseases that may occur with CLL and offers a new therapeutic avenue to the treatment of CLL-associated MN.

Machine Learning-Based Prediction Of Acute Mortality In Emergency Department Patients Using Twelve-Lead Electrocardiogram, Po-Cheng Chang, Zhi-Yong Liu, Yu-Chang Huang, Yu-Chun Hsu, Jung-Sheng Chen, Ching-Heng Lin, Richard Tsai, Chung-Chuan Chou, Ming-Shien Wen, Hung-Ta Wo, Wen-Chen Lee, Hao-Tien Liu, Chun-Chieh Wang, Chang-Fu Kuo

Faculty, Staff and Student Publications

BACKGROUND: The risk of mortality is relatively high among patients who visit the emergency department (ED), and stratifying patients at high risk can help improve medical care. This study aimed to create a machine-learning model that utilizes the standard 12-lead ECG to forecast acute mortality risk in ED patients.

METHODS: The database included patients who visited the EDs and underwent standard 12-lead ECG between October 2007 and December 2017. A convolutional neural network (CNN) ECG model was developed to classify survival and mortality using 12-lead ECG tracings acquired from 345,593 ED patients. For machine learning model development, the patients were …

Artificial Intelligence-Enabled Electrocardiographic Screening For Left Ventricular Systolic Dysfunction And Mortality Risk Prediction, Yu-Chang Huang, Yu-Chun Hsu, Zhi-Yong Liu, Ching-Heng Lin, Richard Tsai, Jung-Sheng Chen, Po-Cheng Chang, Hao-Tien Liu, Wen-Chen Lee, Hung-Ta Wo, Chung-Chuan Chou, Chun-Chieh Wang, Ming-Shien Wen, Chang-Fu Kuo

Faculty, Staff and Student Publications

BACKGROUND: Left ventricular systolic dysfunction (LVSD) characterized by a reduced left ventricular ejection fraction (LVEF) is associated with adverse patient outcomes. We aimed to build a deep neural network (DNN)-based model using standard 12-lead electrocardiogram (ECG) to screen for LVSD and stratify patient prognosis.

METHODS: This retrospective chart review study was conducted using data from consecutive adults who underwent ECG examinations at Chang Gung Memorial Hospital in Taiwan between October 2007 and December 2019. DNN models were developed to recognize LVSD, defined as LVEF

RESULTS: The mean age of patients in the testing dataset was 63.7 ± 16.3 years (46.3% …

Distinct Patterns Of Auto-Reactive Antibodies Associated With Organ-Specific Immune-Related Adverse Events, Mehmet Altan, Quan-Zhen Li, Qi Wang, Natalie I Vokes, Ajay Sheshadri, Jianjun Gao, Chengsong Zhu, Hai T Tran, Saumil Gandhi, Mara B Antonoff, Stephen Swisher, Jing Wang, Lauren A Byers, Noha Abdel-Wahab, Maria C Franco-Vega, Yinghong Wang, J Jack Lee, Jianjun Zhang, John V Heymach

Faculty, Staff and Student Publications

UNLABELLED: The roles of preexisting auto-reactive antibodies in immune-related adverse events (irAEs) associated with immune checkpoint inhibitor therapy are not well defined. Here, we analyzed plasma samples longitudinally collected at predefined time points and at the time of irAEs from 58 patients with immunotherapy naïve metastatic non-small cell lung cancer treated on clinical protocol with ipilimumab and nivolumab. We used a proteomic microarray system capable of assaying antibody reactivity for IgG and IgM fractions against 120 antigens for systemically evaluating the correlations between auto-reactive antibodies and certain organ-specific irAEs. We found that distinct patterns of auto-reactive antibodies at baseline were …

Efficient Federated Kinship Relationship Identification, Xinyue Wang, Leonard Dervishi, Wentao Li, Xiaoqian Jiang, Erman Ayday, Jaideep Vaidya

Faculty, Staff and Student Publications

Kinship relationship estimation plays a significant role in today's genome studies. Since genetic data are mostly stored and protected in different silos, retrieving the desirable kinship relationships across federated data warehouses is a non-trivial problem. The ability to identify and connect related individuals is important for both research and clinical applications. In this work, we propose a new privacy-preserving kinship relationship estimation framework: Incremental Update Kinship Identification (INK). The proposed framework includes three key components that allow us to control the balance between privacy and accuracy (of kinship estimation): an incremental process coupled with the use of auxiliary information and …

Sensitive Data Detection With High-Throughput Machine Learning Models In Electrical Health Records, Kai Zhang, Xiaoqian Jiang

Faculty, Staff and Student Publications

In the era of big data, there is an increasing need for healthcare providers, communities, and researchers to share data and collaborate to improve health outcomes, generate valuable insights, and advance research. The Health Insurance Portability and Accountability Act of 1996 (HIPAA) is a federal law designed to protect sensitive health information by defining regulations for protected health information (PHI). However, it does not provide efficient tools for detecting or removing PHI before data sharing. One of the challenges in this area of research is the heterogeneous nature of PHI fields in data across different parties. This variability makes rule-based …

Large Language Models For Healthcare Data Augmentation: An Example On Patient-Trial Matching, Jiayi Yuan, Ruixiang Tang, Xiaoqian Jiang, Xia Hu

Faculty, Staff and Student Publications

The process of matching patients with suitable clinical trials is essential for advancing medical research and providing optimal care. However, current approaches face challenges such as data standardization, ethical considerations, and a lack of interoperability between Electronic Health Records (EHRs) and clinical trial criteria. In this paper, we explore the potential of large language models (LLMs) to address these challenges by leveraging their advanced natural language generation capabilities to improve compatibility between EHRs and clinical trial descriptions. We propose an innovative privacy-aware data augmentation approach for LLM-based patient-trial matching (LLM-PTM), which balances the benefits of LLMs while ensuring the security …

Split Learning For Distributed Collaborative Training Of Deep Learning Models In Health Informatics, Zhuohang Li, Chao Yan, Xinmeng Zhang, Gharib Gharibi, Zhijun Yin, Xiaoqian Jiang, Bradley A Malin

Faculty, Staff and Student Publications

Deep learning continues to rapidly evolve and is now demonstrating remarkable potential for numerous medical prediction tasks. However, realizing deep learning models that generalize across healthcare organizations is challenging. This is due, in part, to the inherent siloed nature of these organizations and patient privacy requirements. To address this problem, we illustrate how split learning can enable collaborative training of deep learning models across disparate and privately maintained health datasets, while keeping the original records and model parameters private. We introduce a new privacy-preserving distributed learning framework that offers a higher level of privacy compared to conventional federated learning. We …

A Scientific Communication Mentoring Intervention Benefits Diverse Mentees With Language Variety Related Discomfort, Carrie A Cameron, Hwa Young Lee, Cheryl B Anderson, Erin K Dahlstrom, Shine Chang

Faculty, Staff and Student Publications

We studied social-psychological effects over time of a faculty-mentor workshop intervention that addressed attitudes associated with language variety and their impact on scientific communication (SC) skill development of PhD and postdoctoral STEM research trainees (N = 274). Six months after their mentors attended the workshop, all mentees had significant gains in productivity in speaking tasks. In particular, mentees with high language discomfort rated their quality of communication with their mentor and their enthusiasm about communicating more highly (p < .05 for both measures), compared to mentees with low language discomfort. In addition, mentees raised speaking nonstandardized varieties of English reported significant reductions in discomfort related to language use (p = .003), compared to mentees raised speaking standardized English. We conclude that training mentors to understand and respond to …

Integrating Comorbidity Knowledge For Alzheimer's Disease Drug Repurposing Using Multi-Task Graph Neural Network, Ko-Hong Lin, Kang-Lin Hsieh, Xiaoqian Jiang, Yejin Kim

Faculty, Staff and Student Publications

Alzheimer's Disease (AD) is a multifactorial disease that shares common etiologies with its multiple comorbidities, especially vascular diseases. To predict repurposable drugs for AD utilizing the relatively well-investigated comorbidities' knowledge, we proposed a multi-task graph neural network (GNN)-based pipeline that incorporates the corresponding biomedical interactome of these diseases with their genetic markers and effective therapeutics. Our pipeline can accurately capture the interactions and disease classification in the network. Next, we predicted drugs that might interact with the AD module by the node embedding similarity. Our candidates are mostly BBB permeable, and literature evidence showed their potential for treating AD pathologies, …

Local Contrastive Learning For Medical Image Recognition, Syed A Rizvi, Ruixiang Tang, Xiaoqian Jiang, Xiaotian Ma, Xia Hu

Faculty, Staff and Student Publications

The proliferation of Deep Learning (DL)-based methods for radiographic image analysis has created a great demand for expert-labeled radiology data. Recent self-supervised frameworks have alleviated the need for expert labeling by obtaining supervision from associated radiology reports. These frameworks, however, struggle to distinguish the subtle differences between different pathologies in medical images. Additionally, many of them do not provide interpretation between image regions and text, making it difficult for radiologists to assess model predictions. In this work, we propose Local Region Contrastive Learning (LRCLR), a flexible fine-tuning framework that adds layers for significant image region selection as well as cross-modality …

School-Based Intervention Impacts Availability Of Vegetables And Beverages In Participants’ Homes, Erin A Hudson, Marissa Burgermaster, Sophia M Isis, Matthew R Jeans, Sarvenaz Vandyousefi, Matthew J Landry, Rebecca Seguin-Fowler, Joya Chandra, Jaimie Davis

Faculty, Staff and Student Publications

As rates of metabolic syndrome rise, children consume too few vegetables and too much added sugar. Because children tend to eat what is available at home, the home environment plays a key role in shaping dietary habits. This secondary analysis evaluated the effects of a school-based gardening, cooking, and nutrition education intervention (TX Sprouts) compared to control on the availability of vegetables, fruit juice, and sugar-sweetened beverages (SSBs) at home. In the TX Sprouts cluster-randomized trial, 16 schools were randomized to TX Sprouts (