Analytical, Diagnostic and Therapeutic Techniques and Equipment Commons^™

Multi-Modal Mri Based Segmentation Of Brain Metastases Using Adaptive Self-Attention, Evan Savaria

Computer Science Faculty Publications

Brain metastases (BMs) are the most common adult central nervous system malignancy, affecting 20–40% of cancer patients. Accurate segmentation of metastatic lesions in multi-modal MRI is essential for treatment planning and prognosis however, manual delineation is time consuming and prone to variability. Traditional deep learning models such as U-Net, have improved segmentation accuracy but capture limited long-range dependencies and struggle with variations in metastasis size, shape, and distribution. This study introduces the Adaptive Integrated Multi-modal Segmentation (AIMS) model, an adaptive self-attention framework within a hybrid U-Net and Transformer architecture to enhance BM segmentation by leveraging multi-modal MRI integration. The proposed …

Optiselect And Enshap: Integrating Machine Learning And Game Theory For Ischemic Stroke Prediction, Pritam Chakraborty, Anjan Bandyopadhyay, Sricheta Parul, Sujata Swain, Partha Sarathy Banerjee, Tapas Si, Hong Qin, Saurav Mallik

Computer Science Faculty Publications

Stroke analysis using game theory and machine learning techniques. The study investigates the use of the Shapley value in predictive ischemic brain stroke analysis. Initially, preference algorithms identify the most important features in various machine learning models, including logistic regression, K-nearest neighbor, decision tree, support vector machine (linear kernel), support vector machine ( RBF kernel), neural networks, etc. For each sample, the top 3, 4, and 5 features are evaluated and selected to evaluate their performance. The Shapley value method was used to rank the models using their best four features based on their predictive capabilities. As a result, better-performing …

Patient Perceptions Of Audio-Only Versus Video Telehealth Visits: A Qualitative Study Among Patients In An Academic Medical Center Setting, Ryan Kruis, Elizabeth A. Brown, Jada Johnson, Kit N. Simpson, James Mcelligott, Jillian Harvey

Community & Environmental Health Faculty Publications

Introduction: Telehealth utilization surged during the COVID-19 pandemic, offering expanded health care access. Audio-only visits emerged as a crucial tool for patients facing technology or connectivity barriers to still use telehealth. This qualitative study aims to better understand patient perceptions of audio-only versus video telehealth visits during the COVID-19 pandemic, and how patients perceive the role of each in their overall health care. Methods: Semi-structured interviews were conducted with 14 adult patients seeking care at an academic medical center located in the Southeast region of the United States. Patients had experienced both an audio-only and video telehealth visit within the …

Development Of A Positive Urinalysis Criteria Using A Machine Learning Approach, Kari Flicker, Jessica Parrott, Tammy Speerhas, Turaj Vazifedan, Theresa Guins, Jeffrey Bobrowtiz, Anne Mcevoy, Jade Eves, Debra Conrad, Benjamin Klick

Ellmer School of Nursing Faculty Publications

Background: Urinary tract infections (UTIs) are a commonly encountered diagnosis at pediatric urgent care (UC) centers. The urinalysis (UA) is usually the initial study in UC settings used to guide decisions regarding initiating empiric antibiotics and/or pursuing urine culture. However, studies in pediatric UC settings examining the ideal threshold for a positive result are lacking.

Methods: UA result data were extracted from the records of 6,327 pediatric patients, which were collected as part of a previous QI project. Logistic regression was used to determine the predictors of positive urine cultures. Decision trees for a positive UA result for both clean …

Predicting The Need For Cardiovascular Surgery: A Comparative Study Of Machine Learning Models, Arman Ghavidel, Pilar Pazos, Rolando Del Aguila Suarez, Alireza Atashi

Engineering Management & Systems Engineering Faculty Publications

This research examines the efficacy of ensemble Machine Learning (ML) models, mainly focusing on Deep Neural Networks (DNNs), in predicting the need for cardiovascular surgery, a critical aspect of clinical decision-making. It addresses key challenges such as class imbalance, which is pivotal in healthcare settings. The research involved a comprehensive comparison and evaluation of the performance of previously published ML methods against a new Deep Learning (DL) model. This comparison utilized a dataset encompassing 50,000 patient records from a large hospital between 2015-2022. The study proposes enhancing the efficacy of these models through feature selection and hyperparameter optimization, employing techniques …

Effects Of Ultrasonic Use On Hearing Loss In Dental Hygienists: A Matched Pairs Design Study, Jessica Suedbeck, Emily A. Ludwig, James Blando, Nathan Michalak

Dental Hygiene Faculty Publications

Purpose: Dental professionals are exposed to hazardous noise levels on a daily basis in clinical practice. The purpose of this study was to compare the hearing status of dental hygienists who utilize ultrasonic scalers in the workplace compared to age-matched control participants (non-dental hygienists) who were not exposed to ultrasonic noise.

Methods: A convenience sample of nineteen dental hygienists (experimental) and nineteen non-dental hygienists (control) was recruited for this study. A matched pairs design was utilized; participants in each group were matched based on age and gender to eliminate confounding variables. The testing procedure consisted of an audiologist performing a …

Selecting And Evaluating Key Mds-Updrs Activities Using Wearable Devices For Parkinson's Disease Self-Assessment, Yuting Zhao, Xulong Wang, Xiyang Peng, Ziheng Li, Fengtao Nan, Menghui Zhuo, Jun Qi, Yun Yang, Zhong Zhao, Lida Xu, Po Yang

Information Technology & Decision Sciences Faculty Publications

Parkinson's disease (PD) is a complex neurodegenerative disease in the elderly. This disease has no cure, but assessing these motor symptoms will help slow down that progression. Inertial sensing-based wearable devices (ISWDs) such as mobile phones and smartwatches have been widely employed to analyse the condition of PD patients. However, most studies purely focused on a single activity or symptom, which may ignore the correlation between activities and complementary characteristics. In this paper, a novel technical pipeline is proposed for fine-grained classification of PD severity grades, which identify the most representative activities. We also propose a multi-activities combination scheme based …

Studying The Role Of Novel Carbon Nano Tubes As A Therapeutic Agent To Treat Triple Negative Breast Cancer (Tnbc) - An In Vitro And In Vivo Study, Kamal Asadipour, Narendra Banerjee, Jazmine Cuffee, Karrington Perry, Shennel Brown, Anasua Banerjee, Erik Armstrong, Stephen Beebe, Hirendra Banerjee

Bioelectrics Publications

Triple Negative Breast Cancer (TNBC) is a malignant cancer with a very high mortality rate around the world. African American(AA) women are 28% more likely to die from triple-negative breast cancer (TNBC) than white women with the same diagnosis. AA patients are also more likely to be diagnosed at a later stage of the disease and have the lowest survival rates for any stage of diagnosis; There are very few existing anti TNBC drugs with therapeutic efficacy hence newer anti TNBC drug design and investigation is needed. Carbon Nano Tubes(CNT) in recent years have shown effective anti-cancer properties in various …

Quantification Of Antiviral Drug Tenofovir (Tfv) By Surface-Enhanced Raman Spectroscopy (Sers) Using Cumulative Distribution Functions (Cdfs), Marguerite R. Butler, Jana Hrncirova, Meredith Clark, Sucharita Dutta, John B. Cooper

Chemistry & Biochemistry Faculty Publications

Surface-enhanced Raman spectroscopy (SERS) is an ultrasensitive spectroscopic technique that generates signal-enhanced fingerprint vibrational spectra of small molecules. However, without rigorous control of SERS substrate active sites, geometry, surface area, or surface functionality, SERS is notoriously irreproducible, complicating the consistent quantitative analysis of small molecules. While evaporatively prepared samples yield significant SERS enhancement resulting in lower detection limits, the distribution of these enhancements along the SERS surface is inherently stochastic. Acquiring spatially resolved SERS spectra of these dried surfaces, we have shown that this enhancement is governed by a power law as a function of analyte concentration. Consequently, by definition, …

Differences In Urine Creatinine And Osmolality Between Black And White Americans After Accounting For Age, Moisture Intake, Urine Volume, And Socioeconomic Status, Patrick B. Wilson, Ian P. Winter, Josie Burdin

Exercise Science Faculty Publications

Urine osmolality is used throughout research to determine hydration levels. Prior studies have found black individuals to have elevated urine creatinine and osmolality, but it remains unclear which factors explain these findings. This cross-sectional, observational study sought to understand the relationship of self-reported race to urine creatinine and urine osmolality after accounting for age, socioeconomic status, and fluid intake. Data from 1,386 participants of the 2009–2012 National Health and Nutrition Examination Survey were utilized. Age, poverty-to-income ratio (PIR), urine flow rate (UFR), fluid intake, estimated lean body mass (LBM), urine creatinine, and urine osmolality were measured. In a sex-specific manner, …

Hsp70 Is A Critical Regulator Of Hsp90 Inhibitor's Effectiveness In Preventing Hcl-Induced Chronic Lung Injury And Pulmonary Fibrosis, Ruben M. L. Colunga Biancatelli, Pavel A. Solopov, Tierney Day, Betsy Gregory, Michael Osei-Nkansah, Christiana Dimitropoulou, John D. Catravas

Bioelectrics Publications

Exposure to hydrochloric acid (HCl) can provoke acute and chronic lung injury. Because of its extensive production for industrial use, frequent accidental exposures occur, making HCl one of the top five chemicals causing inhalation injuries. There are no Food and Drug Administration (FDA)-approved treatments for HCl exposure. Heat shock protein 90 (HSP90) inhibitors modulate transforming growth factor-β (TGF-β) signaling and the development of chemical-induced pulmonary fibrosis. However, little is known on the role of Heat Shock Protein 70 (HSP70) during injury and treatment with HSP90 inhibitors. We hypothesized that administration of geranylgeranyl-acetone (GGA), an HSP70 inducer, or gefitinib (GFT), an …

Influences Of Athletic Trainers' Return-To-Activity Assessments For Patients With An Ankle Sprain, Ryan S. Mccann, Cailee E. Welch Bacon, Ashley M. B. Suttmiller, Phillip A. Gribble, Julie M. Cavallario

Rehabilitation Sciences Faculty Publications

Context: Athletic trainers (ATs) inconsistently apply rehabilitation-oriented assessments (ROASTs) when deciding return-to-activity readiness for patients with an ankle sprain. Facilitators and barriers that are most influential to ATs' assessment selection remain unknown.

Objective: To examine facilitators of and barriers to ATs' selection of outcome assessments when determining return-to-activity readiness for patients with an ankle sprain.

Design: Cross-sectional study.

Setting: Online survey.

Patients or other participants: We sent an online survey to 10 000 clinically practicing ATs. The survey was accessed by 676 individuals, of whom 574 submitted responses (85% completion rate), and 541 respondents met the inclusion criteria.

Main outcome …

Heterogeneity In The Role Of Emergency Physicians And Treatment Of Acute Atrial Fibrillation In Emergency Departments— Results Of The International Atrial Fibrillation Background (Afib) Study, Markus Holmberg, Ville Hällberg, Hjalti M. Björnsson, Timothy H. Rainer, Colin A. Graham, Marc B. Sabbe, Wilhelm Behringer, Gayle Galletta, Hans Domanovits, Harri Pikkarainen, Bruce M. Lo, Christopher Laurent, Pascal Vanelderen, Ari Palomäki

Department of Emergency Medicine Faculty Publications

The consept of emergency departments (EDs) with specialized teams of emergency physicians originated in the United Kingdom and the United States during the 1970s and was expanded across most European countries in the twenty-first century. Among the various cardiac arrhythmias encountered in EDs, atrial fibrillation (AF) is the most prevalent, contributing to ED congestion. Existing guidelines offer multiple treatment options for acute-onset AF occurring within 48 hours. The aim of The Atrial Fibrillation Background Study is to evaluate treatment strategies, practices and the role of emergency physicians in managing acute-onset AF in Western medical tradition across Europe, the United States …

Machine Learning As A Tool For Early Detection: A Focus On Late-Stage Colorectal Cancer Across Socioeconomic Spectrums, Hadiza Galadima, Rexford Anson-Dwamena, Ashley Johnson, Ghalib Bello, Georges Adunlin, James Blando

Community & Environmental Health Faculty Publications

Purpose: To assess the efficacy of various machine learning (ML) algorithms in predicting late-stage colorectal cancer (CRC) diagnoses against the backdrop of socio-economic and regional healthcare disparities. Methods: An innovative theoretical framework was developed to integrate individual- and census tract-level social determinants of health (SDOH) with sociodemographic factors. A comparative analysis of the ML models was conducted using key performance metrics such as AUC-ROC to evaluate their predictive accuracy. Spatio-temporal analysis was used to identify disparities in late-stage CRC diagnosis probabilities. Results: Gradient boosting emerged as the superior model, with the top predictors for late-stage CRC diagnosis being anatomic site, …

Unraveling The Complex Interactions Among Lung Cancer, Copd, Cardiovascular Disease, And Pulmonary Fibrosis: Overlapping Risks, Converging Pathways, And Integrated Care Approaches, Daisy Umutoni, Mayowa Soloman Owolabi, Sakariyau Adio Waheed

Chemistry & Biochemistry Faculty Publications

Background: The coexistence of lung cancer, chronic obstructive pulmonary disease (COPD), cardiovascular disease (CVD), and pulmonary fibrosis poses significant challenges in clinical management due to shared risk factors, overlapping pathogenic mechanisms, and the complexity of co-managing multimorbid conditions. Smoking, environmental exposures, and genetic predispositions are critical shared risk factors, while common molecular mechanisms such as oxidative stress, chronic inflammation, and aberrant tissue remodeling contribute to the pathogenesis of these diseases. This review comprehensively examines the prevalence, shared mechanisms, and clinical implications of these comorbid conditions, emphasizing the importance of integrated management strategies to improve patient outcomes. We further highlight research …

Diagnostic Certainty During In-Person And Telehealth Autism Evaluations, Natasha N. Ludwig, Calliope Holingue, Ji Su Hong, Luther G. Kalb, Danika Pfeiffer, Rachel Reetzke, Deepa Menon

Speech-Language Pathology Faculty Publications

Background

Many diagnostic evaluations abruptly shifted to telehealth during the COVID-19 pandemic; however, little is known about the impact on diagnosis patterns for children evaluated for autism spectrum disorder (ASD). The purpose of this clinical research study was to examine (1) the frequency of diagnoses evaluated beyond ASD; (2) the frequency of diagnoses made, including ASD; and (3) clinician diagnostic certainty for all diagnoses evaluated for children who received an evaluation due to primary concerns about ASD via telehealth during the pandemic compared to those evaluated in person before the pandemic at an ASD specialty clinic.

Methods

The sample included …

Machine-Learning-Enabled Diagnostics With Improved Visualization Of Disease Lesions In Chest X-Ray Images, Md. Fashiar Rahman, Tzu-Liang (Bill) Tseng, Michael Pokojovy, Peter Mccaffrey, Eric Walser, Scott Moen, Alex Vo, Johnny C. Ho

Mathematics & Statistics Faculty Publications

The class activation map (CAM) represents the neural-network-derived region of interest, which can help clarify the mechanism of the convolutional neural network’s determination of any class of interest. In medical imaging, it can help medical practitioners diagnose diseases like COVID-19 or pneumonia by highlighting the suspicious regions in Computational Tomography (CT) or chest X-ray (CXR) film. Many contemporary deep learning techniques only focus on COVID-19 classification tasks using CXRs, while few attempt to make it explainable with a saliency map. To fill this research gap, we first propose a VGG-16-architecture-based deep learning approach in combination with image enhancement, segmentation-based region …

St-Elevation In Avr With Diffuse St-Segment Depression: Need For Urgent Catheterization?, Bruce M. Lo, Megyn K. Christensen, Katherine E. Schaffer, Theodore J. Tzavaras

Department of Emergency Medicine Faculty Publications

Case Presentation: A 33 year old female with a history of antiphospholipid syndrome presented with exertional chest pain and ST-elevation in aVR with diffuse ST-depression. An emergent catheterization was performed which showed an isolated 99% stenosis in the left main coronary artery. The remaining coronary arteries were without any stenosis. Successful stent placement was performed, and the patient was discharged without complications.

Discussion: Previous guidelines suggested that ST-elevation with diffuse ST-depression should be treated as a STEMI-equivalent involving the left-main or proximal left anterior descending coronary artery. However recent data suggests that the majority of these cases may not involve …

Cumulative Distribution Function And Spatially Resolved Surface-Enhanced Raman Spectroscopy For The Quantitative Analysis Of Emtricitabine, Jana Hrncirova, Marguerite R. Butler, Sucharita Dutta, Meredith R. Clark, John B. Cooper

Chemistry & Biochemistry Faculty Publications

Surface-enhanced Raman spectroscopy (SERS) has exceptional analytical sensitivity and selectivity. However, SERS irreproducibility presents an obstacle when using it for precise quantitative measurements. In this study, colloidal nanoparticles evaporated to dryness are used as a SERS active surface for the detection of the HIV drug emtricitabine (FTC; trade name Emtriva). Despite the irreproducibility of the SERS resulting from the stochastic process of evaporation, using a SERS scanning instrument, the SERS enhancement factors of spatially resolved spectra have a well-defined distribution of signals for a given analyte concentration. This distribution follows a power law function ranging from weak (very abundant signals) …

Socioeconomic Status And Health Disparities Drive Differences In Accelerometer-Derived Physical Activity In Fatty Liver Disease And Significant Fibrosis, Lucia Tabacu, Sajag Swami, Mark Ledbetter, Mohamad S. Siddiqui, Ekaterina Smirnova

Mathematics & Statistics Faculty Publications

Background and aims

The cornerstone of clinical management of patients with nonalcoholic fatty liver disease (NAFLD) are lifestyle changes such as increasing physical activity (PA) aimed at improving cardiometabolic risk. To inform NAFLD prevention and treatment guidelines we aimed to: (i) quantify the role of PA on lowering the risk for NAFLD and fibrosis; (ii) characterize NAFLD and fibrosis association with PA in the context of socioeconomic environment.

Methods

A sample of 2648 participants from the NHANES 2003–2006 was selected to develop survey weighted multivariable logistic regression models for predicting NAFLD and significant fibrosis, diagnosed non-invasively via fatty liver index …

Successful Management Of Spontaneous Unilateral Twin Ectopic Pregnancy With Two-Step Dose Of Methotrexate, Lauren A. Forbes, Navya Nuthivana, Renee Morales

Department of Obstetrics & Gynecology Faculty Publications

The incidence of unilateral tubal twin pregnancy is 1/20,000–1/250,000 with about 100 reported cases. Four of the six cases that were medically managed were successful. A 24-year-old female presented to the emergency department (ED) with vaginal bleeding and abdominal cramping. She was hemodynamically stable without signs of an acute abdomen. Laboratory evaluation revealed she was pregnant with a serum beta-human chorionic gonadotropin (b-hCG) of 798 mIU/mL. Transvaginal ultrasound (TVUS) revealed a single left tubal pregnancy with a yolk sac. The patient elected medical management with body surface area (BSA)–based intramuscular (IM) methotrexate (MTX). On Day 4, the patient returned to …

Reliability And Minimal Detectable Change Of The Mx3 Hydration Testing System, Ian Winter, Josie Burdin, Patrick B. Wilson

Exercise Science Faculty Publications

Assessing hydration status outside of laboratories can be challenging given that most hydration measures are invasive, stationary, costly, or have questionable validity. This study investigated the within-day, test-retest reliability, and minimal detectable change (MDC) of the MX3 Hydration Testing System (MX3 Diagnostics), a relatively low cost, noninvasive, and portable method to measure saliva osmolality. Seventy-five adults (44 men, 31 women; 29.6±10.8 yr, 171.1±9.2 cm, 79.1±15.4 kg) presented two saliva samples approximately 3 to 5 minutes apart. Fluid intake was avoided for at least 5 minutes prior to sample collections. For each sample collection, a researcher used the MX3 to tap …

A Scoping Review Of Population Diversity In The Common Genomic Aberrations Of Clear Cell Renal Cell Carcinoma, Sean S. Kumar, Ninad Khandekar, Komal Dani, Saina R. Bhatt, Vinay Duddalwar, Anishka D'Souza

Department of Medicine Faculty Publications

Introduction: Previous literature has shown that clear cell renal cell carcinoma (ccRCC) is becoming a more prevalent diagnosis and that the incidence and mortality differ both regionally and racially. While the molecular profiles for ccRCC are studied regionally through biopsy and sequencing techniques, the genomic landscape and ccRCC diversity data are not well-studied. We conducted a review of the known genomic data on 6 of the most clinically relevant DNA biomarkers in ccRCC: Von Hippel-Landau (vHL), Polybromo-1 (PBRM1), Breast Cancer Gene 1-Associated Protein 1 (BAP1), Histone-Lysine N-Methyltransferase Domain-Containing 2 (SETD2), Mammalian Target of Rapamycin (mTOR), and Lysine-Specific Demethylase 5C (KDM5C). …

Positive Airway Pressure And Mask Factors Affective Adherence In Patients With Obstructive Sleep Apnea, Rutvi Sheth, Michel Audette, Soham Sheth

Electrical & Computer Engineering Faculty Publications

Purpose: Sleep apnea is a major risk factor for cardiovascular disorders. CPAP (Continuous Positive Airway Pressure) therapy is the main treatment for sleep apnea. However, adherence with CPAP remains a concern. Although there are various factors attributed to failure of CPAP therapy, mask related factors are not well studied.

Methods: The study recruited patients with obstructive sleep apnea using CPAP from neurology outpatient clinic at Progressive Neurology and Sleep Center. An IRB (Institutional Review Board) approved questionnaire was administered to evaluate factors affecting CPAP compliance.

Results: The study recruited 24 patients. It showed that almost 50% of the patients did …

Adversarial Training Based Domain Adaptation Of Skin Cancer Images, Syed Qasim Gilani, Muhammad Umair, Maryam Naqvi, Oge Marques, Hee-Cheol Kim

Electrical & Computer Engineering Faculty Publications

Skin lesion datasets used in the research are highly imbalanced; Generative Adversarial Networks can generate synthetic skin lesion images to solve the class imbalance problem, but it can result in bias and domain shift. Domain shifts in skin lesion datasets can also occur if different instruments or imaging resolutions are used to capture skin lesion images. The deep learning models may not perform well in the presence of bias and domain shift in skin lesion datasets. This work presents a domain adaptation algorithm-based methodology for mitigating the effects of domain shift and bias in skin lesion datasets. Six experiments were …

Investigation Of The Effect Of Preparation Parameters On The Structural And Mechanical Properties Of Gelatin/Elastin/Sodium Hyaluronate Scaffolds Fabricated By The Combined Foaming And Freeze-Drying Techniques, Mansour Qamash, S. Misagh Imani, Meisam Omidi, Ciara Glancy, Lobat Tayebi

Electrical & Computer Engineering Faculty Publications

This paper aimed to evaluate the effects of different preparation parameters, including agitation speed, agitation time, and chilling temperature, on the structural and mechanical properties of a novel gelatin/elastin/sodium hyaluronate tissue engineering scaffold, recently developed by our research group. Fabricated using a combination of foaming and freeze-drying techniques, the scaffolds were assessed to understand how these parameters influence their morphology, internal microstructure, porosity, mechanical properties, and degradation behavior. The fabrication process used in this study involved preparing a homogeneous aqueous solution containing 8% gelatin, 2% elastin, and 0.5% sodium hyaluronate (w/v), which was then subjected to mechanical agitation at speeds …

Advancing Chronic Kidney Disease Prediction Through Machine Learning And Deep Learning With Feature Analysis, Shiddarth Dey Tusar, S. M. Ahad Ali Chowdhury, Md. Jalal Uddin Chowdhury, Rana M. Pir, H. M. Nur A. Alam, Muhammad Rezaur Rahman, Md. Nural Absar Siddiky, Muhammad Enayetur Rahman

Electrical & Computer Engineering Faculty Publications

Chronic Kidney Diesease (CKD) is a significant health issue, ranking as the fourth leading cause of mortality worldwide. The traditional diagnosis and treatment process, reliant on medical experts, is time-consuming. Therefore, thereis an urgent need for more efficient diagnostic methods to improve patient outcomes and reduce mortality rates. In this study, we employ Machine Learning (ML) and Deep Learning (DL) techniques to predict CKD based on important features. Feature analysis was performed using a correlation matrix and the LASSO algo-rithm to identify the most relevant features for model training. We evaluated several ML and DL classifiers, including Logistic Regression (LR), …

Integrated Machine Learning And Deep Learning Models For Cardiovascular Disease Risk Prediction: A Comprehensive Comparative Study, Shadman Mahmood Khan Pathan, Sakan Binte Imran

Electrical & Computer Engineering Faculty Publications

Cardiovascular Diseases (CVDs) pose a significant global health challenge, necessitating accurate risk prediction for effective preventive measures. This comprehensive comparative study explores the performance of traditional Machine Learning (ML) and Deep Learning (DL) models in predicting CVD risk, utilizing a meticulously curated dataset derived from health records. Rigorous preprocessing, including normalization and outlier removal, enhances model robustness. Diverse ML models (Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbor, Decision Tree, and Gradient Boosting) are compared with a Long Short-Term Memory (LSTM) neural network for DL. Evaluation metrics include accuracy, ROC AUC, computation time, and memory usage. Results identify the …

Ai And Ml-Based Risk Assessment Of Chemicals: Predicting Carcinogenic Risk From Chemical-Induced Genomic Instability, Ajay Vikram Singh, Preeti Bhardwaj, Peter Laux, Prachi Pradeep, Madleen Busse, Andreas Luch, Akihiko Hirose, Christopher J. Osgood, Michael W. Stacey

Biological Sciences Faculty Publications

Chemical risk assessment plays a pivotal role in safeguarding public health and environmental safety by evaluating the potential hazards and risks associated with chemical exposures. In recent years, the convergence of artificial intelligence (AI), machine learning (ML), and omics technologies has revolutionized the field of chemical risk assessment, offering new insights into toxicity mechanisms, predictive modeling, and risk management strategies. This perspective review explores the synergistic potential of AI/ML and omics in deciphering clastogen-induced genomic instability for carcinogenic risk prediction. We provide an overview of key findings, challenges, and opportunities in integrating AI/ML and omics technologies for chemical risk assessment, …

Image-To-Mesh Conversion Method For Multi-Tissue Medical Image Computing Simulations, Fotis Drakopoulos, Yixun Liu, Kevin Garner, Nikos Chrisochoides

Computer Science Faculty Publications

Converting a three-dimensional medical image into a 3D mesh that satisfies both the quality and fidelity constraints of predictive simulations and image-guided surgical procedures remains a critical problem. Presented is an image-to-mesh conversion method called CBC3D. It first discretizes a segmented image by generating an adaptive Body-Centered Cubic mesh of high-quality elements. Next, the tetrahedral mesh is converted into a mixed element mesh of tetrahedra, pentahedra, and hexahedra to decrease element count while maintaining quality. Finally, the mesh surfaces are deformed to their corresponding physical image boundaries, improving the mesh’s fidelity. The deformation scheme builds upon the ITK open-source library …