Data Science Commons^™

Comparative Analysis Of Feature Selection And Machine Learning Models For Breast Cancer Risk Prediction, Tonmoy Roy

Student Research Symposium

The comparative analysis of feature selection and machine learning models for breast cancer risk prediction aims to develop accurate and efficient models for diagnosing breast cancer. In this analysis, we explore different feature selection techniques and machine learning models to identify the most effective feature combination for breast cancer risk prediction. Our study provides valuable insights into the importance of feature selection and model selection in developing accurate breast cancer risk prediction models. Using the three features provide high accuracy to detect breast cancer. Overall, this study highlights the importance of combining feature selection techniques with machine learning algorithms to …

Physio-Psycho-Social Interaction Mechanism In Dyadic Health Of Young And Middle-Aged Stroke Survivors And Their Spousal Caregivers: A Longitudinal Observational Study Protocol, Dandan Xiang, Zhen-Xiang Zhang, Song Ge, Wen Na Wang, Bei-Lei Lin, Su-Yan Chen, Er-Feng Guo, Peng-Bo Zhang, Zhi-Wei Liu, Hui Li, Yong-Xia Mei

Faculty, Staff and Student Publications

Introduction: In recent years, stroke has become more common among young people. Stroke not only has a profound impact on patients' health but also incurs stress and health threats to their caregivers, especially spousal caregivers. Moreover, the health of stroke survivors and their caregivers is interdependent. To our knowledge, no study has explored dyadic health of young and middle-aged stroke survivors and their spousal caregivers from physiological, psychological and social perspectives. Therefore, this proposed study aims to explore the mechanism of how physiological, psychological and social factors affect dyadic health of young and middle-aged stroke survivors and their spousal caregivers. …

Quantitative Proteomic Screening Uncovers Candidate Diagnostic And Monitoring Serum Biomarkers Of Ankylosing Spondylitis, Mark Hwang, Shervin Assassi, Jim Zheng, Jessica Castillo, Reyna Chavez, Kamala Vanarsa, Chandra Mohan, John Reveille

Faculty, Staff and Student Publications

BACKGROUND: We sought to discover serum biomarkers of ankylosing spondylitis (AS) for diagnosis and monitoring disease activity.

METHODS: We studied biologic-treatment-naïve AS and healthy control (HC) patients' sera. Eighty samples matched by age, gender, and race (1:1:1 ratio) for AS patients with active disease, inactive disease, and HC were analyzed with SOMAscan™, an aptamer-based discovery platform. T-tests tests were performed for high/low-disease activity AS patients versus HCs (diagnosis) and high versus low disease activity (Monitoring) in a 2:1 and 1:1 ratio, respectively, to identify differentially expressed proteins (DEPs). We used the Cytoscape Molecular Complex Detection (MCODE) plugin to find clusters …

Distribution Of Serum Uric Acid Concentration And Its Association With Lipid Profiles: A Single-Center Retrospective Study In Children Aged 3 To 12 Years With Adenoid And Tonsillar Hypertrophy, Jiating Yu, Xin Liu, Honglei Ji, Yawei Zhang, Hanqiang Zhan, Ziyin Zhang, Jianguo Wen, Zhimin Wang

Faculty, Staff and Student Publications

BACKGROUND: Presently, there is no consensus regarding the optimal serum uric acid (SUA) concentration for pediatric patients. Adenoid and tonsillar hypertrophy is considered to be closely associated with pediatric metabolic syndrome and cardiovascular risk and is a common condition in children admitted to the hospital. Therefore, we aimed to evaluate the relationship between SUA and dyslipidemia and propose a reference range for SUA concentration that is associated with a healthy lipid profile in hospitalized children with adenoid and tonsillar hypertrophy.

METHODS: Preoperative data from 4922 children admitted for elective adenoidectomy and/or tonsillectomy surgery due to adenoid and tonsillar hypertrophy were …

Domain Specific Analysis Of Privacy Practices And Concerns In The Mobile Application Market, Fahimeh Ebrahimi Meymand

LSU Doctoral Dissertations

Mobile applications (apps) constantly demand access to sensitive user information in exchange for more personalized services. These-mostly unjustified-data collection tactics have raised major privacy concerns among mobile app users. Existing research on mobile app privacy aims to identify these concerns, expose apps with malicious data collection practices, assess the quality of apps' privacy policies, and propose automated solutions for privacy leak detection and prevention. However, existing solutions are generic, frequently missing the contextual characteristics of different application domains. To address these limitations, in this dissertation, we study privacy in the app store at a domain level. Our objective is to …

Twitter Database Health Visualization, Tor Qureshi

2023 IDIR Data Visualization Challenges-Archive

By utilizing the Twitter IDs and their corresponding posts in the database, we were able to create a UI that generates a graph that demonstrates a word or phrases' usage over time based on the number of times mentioned within the time span of the database (2011-2023). In the future, this could be improved by combining it with the Twitter API to monitor live trends and associations.

Analysis Of Hawk Mountain Wind Speed To Raptor Count Trends From 1976 Through 2021, Dale E. Parson

Computer Science and Information Technology Faculty

This analysis of summer 2023 is a sequel to the summer 2022 Analysis of Hawk Mountain Sanctuary Observation Data from 1976 through 2021, also available as a web page through end of 2024 here. A presentation of that and subsequent analysis presented at Kutztown University in November 2022 and to Hawk Mountain researchers in January 2023 is available as PDF slides here and also on the web through 2024 here. This work was funded by a Kutztown University Research Grant for spring 2022 through summer 2023. Analytical use of these data proceeded through a subset of projects in three courses …

Investigating The Use Of Recurrent Neural Networks In Modeling Guitar Distortion Effects, Caleb Koch, Scott Hawley, Andrew Fyfe

[Archive] Belmont University Research Symposium (BURS)

Guitar players have been modifying their guitar tone with audio effects ever since the mid-20th century. Traditionally, these effects have been achieved by passing a guitar signal through a series of electronic circuits which modify the signal to produce the desired audio effect. With advances in computer technology, audio “plugins” have been created to produce audio effects digitally through programming algorithms. More recently, machine learning researchers have been exploring the use of neural networks to replicate and produce audio effects initially created by analog and digital effects units. Recurrent Neural Networks have proven to be exceptional at modeling audio effects …

Sports Data Science Job Requirements, Cam E. Morse

Student Publications

Data science is an extremely fast growing field in which job opportunities are opening in every industry related to data science. Within the data science field is the sports data science industry which has it's own requirements and specificities that may not be present in other industries. In this paper, research is done using multiple job posting websites such as LinkedIn, Indeed, Sportstek jobs, and TeamworkOnline to explore the job descriptions of many different sports data science jobs. These job descriptions are then examined using Python coding to find the frequencies of specific data science skills in the various job …

Beyond News Values On Twitter: Predicting Factors That Drive User Engagement In News, Zhiyan Zhong

Dartmouth College Master’s Theses

When deciding on what news stories to cover, traditional journalism determines news values by following several elements of newsworthiness, such as impact, timeliness, and prominence. However, these guidelines do not always seem to correspond with the success of content on social media. As people are increasingly turning to social media for news, our research aims to understand and predict factors that drive user engagement for news on social media. In this study, we analyze news content published on Twitter, and examine a diverse set of characteristics like metrics retrieved from the Twitter API and semantics by natural language processing, including …

Discerning Conversational Context In Online Health Communities For Personalized Digital Behavior Change Solutions Using Pragmatics To Reveal Intent In Social Media (Prism) Framework, Tavleen Singh, Kirk Roberts, Trevor Cohen, Nathan Cobb, Amy Franklin, Sahiti Myneni

Faculty, Staff and Student Publications

BACKGROUND: Online health communities (OHCs) have emerged as prominent platforms for behavior modification, and the digitization of online peer interactions has afforded researchers with unique opportunities to model multilevel mechanisms that drive behavior change. Existing studies, however, have been limited by a lack of methods that allow the capture of conversational context and socio-behavioral dynamics at scale, as manifested in these digital platforms.

OBJECTIVE: We develop, evaluate, and apply a novel methodological framework, Pragmatics to Reveal Intent in Social Media (PRISM), to facilitate granular characterization of peer interactions by combining multidimensional facets of human communication.

METHODS: We developed and applied …

Prediction Of Brain Metastases Development In Patients With Lung Cancer By Explainable Artificial Intelligence From Electronic Health Records, Zhao Li, Rongbin Li, Yujia Zhou, Laila Rasmy, Degui Zhi, Ping Zhu, Antonio Dono, Xiaoqian Jiang, Hua Xu, Yoshua Esquenazi, W Jim Zheng

Faculty, Staff and Student Publications

PURPOSE: Early detection of brain metastases (BMs) is critical for prompt treatment and optimal control of the disease. In this study, we seek to predict the risk of developing BM among patients diagnosed with lung cancer on the basis of electronic health record (EHR) data and to understand what factors are important for the model to predict BM development through explainable artificial intelligence approaches accurately.

MATERIALS AND METHODS: We trained a recurrent neural network model, REverse Time AttentIoN (RETAIN), to predict the risk of developing BM using structured EHR data. To interpret the model's decision process, we analyzed the attention …

Why Is Biomedical Informatics Hard? A Fundamental Framework, Todd R Johnson, Elmer V Bernstam

Faculty, Staff and Student Publications

Building on previous work to define the scientific discipline of biomedical informatics, we present a framework that categorizes fundamental challenges into groups based on data, information, and knowledge, along with the transitions between these levels. We define each level and argue that the framework provides a basis for separating informatics problems from non-informatics problems, identifying fundamental challenges in biomedical informatics, and provides guidance regarding the search for general, reusable solutions to informatics problems. We distinguish between processing data (symbols) and processing meaning. Computational systems, that are the basis for modern information technology (IT), process data. In contrast, many important challenges …

Convolutional Neural Network For Biomarker Discovery For Triple Negative Breast Cancer With Rna Sequencing Data, Xiangning Chen, Justin M Balko, Fei Ling, Yabin Jin, Anneliese Gonzalez, Zhongming Zhao, Jingchun Chen

Faculty, Staff and Student Publications

Triple negative breast cancers (TNBCs) are tumors with a poor treatment response and prognosis. In this study, we propose a new approach, candidate extraction from convolutional neural network (CNN) elements (CECE), for discovery of biomarkers for TNBCs. We used the GSE96058 and GSE81538 datasets to build a CNN model to classify TNBCs and non-TNBCs and used the model to make TNBC predictions for two additional datasets, the cancer genome atlas (TCGA) breast cancer RNA sequencing data and the data from Fudan University Shanghai Cancer Center (FUSCC). Using correctly predicted TNBCs from the GSE96058 and TCGA datasets, we calculated saliency maps …

Application Of An Ontology For Model Cards To Generate Computable Artifacts For Linking Machine Learning Information From Biomedical Research, Muhammad Tuan Amith, Licong Cui, Kirk Roberts, Cui Tao

Faculty, Staff and Student Publications

Model card reports provide a transparent description of machine learning models which includes information about their evaluation, limitations, intended use, etc. Federal health agencies have expressed an interest in model cards report for research studies using machine-learning based AI. Previously, we have developed an ontology model for model card reports to structure and formalize these reports. In this paper, we demonstrate a Java-based library (OWL API, FaCT++) that leverages our ontology to publish computable model card reports. We discuss future directions and other use cases that highlight applicability and feasibility of ontology-driven systems to support FAIR challenges.

De Novo Mutations Disturb Early Brain Development More Frequently Than Common Variants In Schizophrenia, Toshiyuki Itai, Peilin Jia, Yulin Dai, Jingchun Chen, Xiangning Chen, Zhongming Zhao

Faculty, Staff and Student Publications

Investigating functional, temporal, and cell-type expression features of mutations is important for understanding a complex disease. Here, we collected and analyzed common variants and de novo mutations (DNMs) in schizophrenia (SCZ). We collected 2,636 missense and loss-of-function (LoF) DNMs in 2,263 genes across 3,477 SCZ patients (SCZ-DNMs). We curated three gene lists: (a) SCZ-neuroGenes (159 genes), which are intolerant to LoF and missense DNMs and are neurologically important, (b) SCZ-moduleGenes (52 genes), which were derived from network analyses of SCZ-DNMs, and (c) SCZ-commonGenes (120 genes) from a recent GWAS as reference. To compare temporal gene expression, we used the BrainSpan …

A Diffusion Network Event History Estimator, Jeffrey J. Harden, Bruce A. Desmarais, Mark Brockway, Frederick J. Boehmke, Scott J. Lacombe, Fridolin Linder, Hanna Wallach

Government: Faculty Publications

Research on the diffusion of political decisions across jurisdictions typically accounts for units’ influence over each other with (1) observable measures or (2) by inferring latent network ties from past decisions. The former approach assumes that interdependence is static and perfectly captured by the data. The latter mitigates these issues but requires analytical tools that are separate from the main empirical methods for studying diffusion. As a solution, we introduce network event history analysis (NEHA), which incorporates latent network inference into conventional discrete-time event history models. We demonstrate NEHA’s unique methodological and substantive benefits in applications to policy adoption in …

High-Dimensional Variable Selection Via Knockoffs Using Gradient Boosting, Amr Essam Mohamed

Dissertations

As data continue to grow rapidly in size and complexity, efficient and effective statistical methods are needed to detect the important variables/features. Variable selection is one of the most crucial problems in statistical applications. This problem arises when one wants to model the relationship between the response and the predictors. The goal is to reduce the number of variables to a minimal set of explanatory variables that are truly associated with the response of interest to improve the model accuracy. Effectively choosing the true influential variables and controlling the False Discovery Rate (FDR) without sacrificing power has been a challenge …

Moral Injury To Inform Analysis Of Post-Traumatic Stress Disorder, Amanda Julia Manea

Senior Theses

Post-traumatic stress disorder (PTSD) is a mental health condition that almost one out of ten veterans struggle with. Although the National Center for PTSD has made extensive progress in characterizing and developing new treatments for PTSD, most veterans still experience symptoms of PTSD following treatment. Novel avenues of investigation, such as developing algorithms to review electronic health record (EHR) data and better understanding moral injury, are being pursued to address the gap that still exists when it comes to treating veterans. Moral injury is the individual evaluation of exposure to a potentially morally injurious event (PMIE) and can lead to …

Genetic Correlations Between Alzheimer’S Disease And Gut Microbiome Genera, Davis Cammann, Yimei Lu, Melika J Cummings, Mark L Zhang, Joan Manuel Cue, Jenifer Do, Jeffrey Ebersole, Xiangning Chen, Edwin C Oh, Jeffrey L Cummings, Jingchun Chen

Faculty, Staff and Student Publications

A growing body of evidence suggests that dysbiosis of the human gut microbiota is associated with neurodegenerative diseases like Alzheimer's disease (AD) via neuroinflammatory processes across the microbiota-gut-brain axis. The gut microbiota affects brain health through the secretion of toxins and short-chain fatty acids, which modulates gut permeability and numerous immune functions. Observational studies indicate that AD patients have reduced microbiome diversity, which could contribute to the pathogenesis of the disease. Uncovering the genetic basis of microbial abundance and its effect on AD could suggest lifestyle changes that may reduce an individual's risk for the disease. Using the largest genome-wide …