Digital Commons Network^™

Live Imaging Of Microglia During Sleeping Sickness Reveals Early And Heterogeneous Inflammatory Responses, Nestor L Uzcategui, Sena Güçer, Cris Richter, Annika Speidel, Elizabeta Zirdum, Michael Duszenko, Olga Garaschuk, Katherine Figarella

Faculty, Staff and Student Publications

INTRODUCTION: Invasion of the central nervous system (CNS) is the most serious consequence of

METHODS: To further address this issue, we implanted a cranial window on the cortex of B6.129P2(Cg)-

RESULTS AND DISCUSSION: We uncovered an early involvement of microglia that precedes invasion of the CNS by the parasite. We accomplished a detailed characterization of the progressive sequence of events that correlates with microglial morphological changes and microgliosis. Our findings unveiled a heterogeneous microglial response in places of initial homeostatic disruption near brain barriers and pointed out an exceptional capability of microglia to hamper parasite proliferation inside the brain. We …

A Novel Humanized Chi3l1 Blocking Antibody Attenuates Acetaminophen-Induced Liver Injury In Mice, Leike Li, Yankai Wen, Daniel Wrapp, Jongmin Jeong, Peng Zhao, Wei Xiong, Constance Lynn Atkins, Zhao Shan, Deng Hui, Jason S Mclellan, Ningyan Zhang, Cynthia Ju, Zhiqiang An

Faculty, Staff and Student Publications

Acetaminophen (APAP) overdose is a leading cause of acute liver injury in the USA. The chitinase 3-like-1 (Chi3l1) protein contributes to APAP-induced liver injury (AILI) by promoting hepatic platelet recruitment. Here, we report the development of a Chi3l1-targeting antibody as a potential therapy for AILI. By immunizing a rabbit successively with the human and mouse Chi3l1 proteins, we isolated cross-reactive monoclonal antibodies (mAbs) from single memory B cells. One of the human and mouse Chi3l1 cross-reactive mAbs was humanized and characterized in both

Childhood Acute Poisoning At Haiphong Children's Hospital: A 10-Year Retrospective Study, Sang Ngoc Nguyen, Lam Tung Vu, Ha Thai Nguyen, Le My Thi Nguyen

Faculty, Staff and Student Publications

INTRODUCTION: Children are most often harmed by acute poisoning, which may cause disability or even death. This demonstrates the critical necessity for epidemiologic studies specific to each nation and area since they aid in developing plans for the prevention of acute poisoning. There are no data or outdated data on acute poisoning in children in Vietnam. This research would partly fill this existing gap and compare the trend with other places across the globe.

METHODS: A retrospective study was conducted in the 10-year period from 2012 to 2021 in Haiphong Children's Hospital, Vietnam.

RESULTS: There were 771 children hospitalized due …

Spatial And Temporal Organization Of The Genome: Current State And Future Aims Of The 4d Nucleome Project, Clara Agudo-Rios, Amber Rogers, Isaiah King, Virali Bhagat, Le My Tu Nguyen, Carlos Córdova-Fletes, Diego Krapf, Jerome F Strauss, Lena Arévalo, Gina Esther Merges, Hubert Schorle, Eduardo R S Roldan, Maria Eugenia Teves

Faculty, Staff and Student Publications

Protamines (PRM1 and PRM2) are small, arginine-rich, nuclear proteins that replace histones in the final stages of spermiogenesis, ensuring chromatin compaction and nuclear remodeling. Defects in protamination lead to increased DNA fragmentation and reduced male fertility. Since efficient sperm production requires the translocation of protamines from the cytoplasm to the nucleus, we investigated whether SPAG17, a protein crucial for intracellular protein trafficking during spermiogenesis, participates in protamine transport. Initially, we assessed the protein-protein interaction between SPAG17 and protamines using proximity ligation assays, revealing a significant interaction originating in the cytoplasm and persisting within the nucleus. Subsequently, immunoprecipitation and mass spectrometry …

Associative Learning Contributes To The Persistence Of Fatigue-Like Behavior In Male Mice In A Model Of Cancer Survivorship, Elisabeth G Vichaya, Josephine K Darpolor, Phillip S Gross, Jessica M Molkentine, Daniel W Vermeer, Paola D Vermeer, John H Lee, Cullen M Taniguchi, Robert Dantzer

Faculty, Staff and Student Publications

Persistent fatigue is a debilitating side effect that impacts a significant proportion of cancer survivors for which there is not yet an FDA-approved treatment. While certainly a multi-factorial problem, persistent fatigue could be due, in part, to associations learned during treatment. Therefore, we sought to investigate the role of associative learning in the persistence of fatigue using a preclinical model of cancer survivorship. For this purpose, we used a murine model of human papilloma virus-related head and neck cancer paired with a curative regimen of cisplatin-based chemoradiation in male C57BL/6J mice. Fatigue-like behavior was assessed by measuring variations in voluntary …

Small Molecule Inhibitor Of Tau Self-Association In A Mouse Model Of Tauopathy: A Preventive Study In P301l Tau Jnpl3 Mice, Eliot J Davidowitz, Patricia Lopez, Heidy Jimenez, Leslie Adrien, Peter Davies, James G Moe

Faculty, Staff and Student Publications

Advances in tau biology and the difficulties of amyloid-directed immunotherapeutics have heightened interest in tau as a target for small molecule drug discovery for neurodegenerative diseases. Here, we evaluated OLX-07010, a small molecule inhibitor of tau self-association, for the prevention of tau aggregation. The primary endpoint of the study was statistically significant reduction of insoluble tau aggregates in treated JNPL3 mice compared with Vehicle-control mice. Secondary endpoints were dose-dependent reduction of insoluble tau aggregates, reduction of phosphorylated tau, and reduction of soluble tau. This study was performed in JNPL3 mice, which are representative of inherited forms of 4-repeat tauopathies with …

Artificial Intelligence-Driven Meta-Analysis Of Brain Gene Expression Identifies Novel Gene Candidates And A Role For Mitochondria In Alzheimer’S Disease, Caitlin A Finney, Fabien Delerue, Wendy A Gold, David A Brown, Artur Shvetcov

Faculty, Staff and Student Publications

Alzheimer's disease (AD) is the most common form of dementia. There is no treatment and AD models have focused on a small subset of genes identified in familial AD. Microarray studies have identified thousands of dysregulated genes in the brains of patients with AD yet identifying the best gene candidates to both model and treat AD remains a challenge. We performed a meta-analysis of microarray data from the frontal cortex (n = 697) and cerebellum (n = 230) of AD patients and healthy controls. A two-stage artificial intelligence approach, with both unsupervised and supervised machine learning, combined with a functional …

A Unified Mediation Analysis Framework For Integrative Cancer Proteogenomics With Clinical Outcomes, Licai Huang, James P Long, Ehsan Irajizad, James D Doecke, Kim-Anh Do, Min Jin Ha

Faculty, Staff and Student Publications

MOTIVATION: Multilevel molecular profiling of tumors and the integrative analysis with clinical outcomes have enabled a deeper characterization of cancer treatment. Mediation analysis has emerged as a promising statistical tool to identify and quantify the intermediate mechanisms by which a gene affects an outcome. However, existing methods lack a unified approach to handle various types of outcome variables, making them unsuitable for high-throughput molecular profiling data with highly interconnected variables.

RESULTS: We develop a general mediation analysis framework for proteogenomic data that include multiple exposures, multivariate mediators on various scales of effects as appropriate for continuous, binary and survival outcomes. …

Sparse Tree-Based Clustering Of Microbiome Data To Characterize Microbiome Heterogeneity In Pancreatic Cancer, Yushu Shi, Liangliang Zhang, Kim-Anh Do, Robert Jenq, Christine B Peterson

Faculty, Staff and Student Publications

There is a keen interest in characterizing variation in the microbiome across cancer patients, given increasing evidence of its important role in determining treatment outcomes. Here our goal is to discover subgroups of patients with similar microbiome profiles. We propose a novel unsupervised clustering approach in the Bayesian framework that innovates over existing model-based clustering approaches, such as the Dirichlet multinomial mixture model, in three key respects: we incorporate feature selection, learn the appropriate number of clusters from the data, and integrate information on the tree structure relating the observed features. We compare the performance of our proposed method to …

Erratum: Cxcl12-Mediated Monocyte Transmigration Into Brain Perivascular Space Leads To Neuroinflammation And Memory Deficit In Neuropathic Pain, Chun-Lin Mai, Zhi Tan, Ya-Nan Xu, Jing-Jun Zhang, Zhen-Hua Huang, Dong Wang, Hui Zhang, Wen-Shan Gui, Jun Zhang, Zhen-Jia Lin, Ying-Tong Meng, Xiao Wei, Ying-Tao Jie, Peter M Grace, Long-Jun Wu, Li-Jun Zhou, Xian-Guo Liu

Faculty, Staff and Student Publications

In the original Figure 7E of our article, the authors mistakenly reused the GFAP immunostaining representative image of the Vehi+Sham group for the anti-CXCL12+Sham group. This is because an error occurred in converting the original purple fluorescence of GFAP for each group to red fluorescence during preparation of representative pictures of Figure 7E. Unfortunately, this error was not found in multiple revisions. The correct version of Figure 7E is shown below. The correction made in this Erratum does not affect the results and conclusions in this study. The authors apologize for any inconvenience the errors may have caused.

Late Effects Of Craniospinal Irradiation Using Electron Spinal Fields For Pediatric Patients With Cancer, Brian De, Marcus A Florez, Ethan B Ludmir, Moshe H Maor, Susan L Mcgovern, Mary Frances Mcaleer, David R Grosshans, Eric L Chang, Anita Mahajan, Arnold C Paulino

Faculty, Staff and Student Publications

Purpose: For children, craniospinal irradiation (CSI) with photons is associated with significant toxic effects. The use of electrons for spinal fields is hypothesized to spare anterior structures but the long-term effects remain uncertain. We studied late effects of CSI using electrons for spinal radiation therapy (RT).

Methods and materials: Records of 84 consecutive patients treated with CSI using electrons for the spine at a single institution between 1983 and 2014 were reviewed. Median age at RT was 5 (range, 1-14) years. The most common histologies were medulloblastoma/primitive neuroectodermal tumor (59%) and ependymoma (8%). The median prescribed dose to the entire …

Protective Role Of Colitis In Inflammatory Arthritis Via Propionate-Producing Bacteroides In The Gut, Hoh-Jeong Shon, Yu-Mi Kim, Kyeong Seog Kim, Jin-Ouk Choi, Sang-Hyun Cho, Sujin An, Se-Hyeon Park, Yong-Joon Cho, Joo-Hong Park, Sang-Uk Seo, Joo-Youn Cho, Wan-Uk Kim, Donghyun Kim

Faculty, Staff and Student Publications

OBJECTIVES: To investigate whether and how inflammatory disease in the intestine influences the development of arthritis, considering that organ-to-organ communication is associated with many physiological and pathological events.

METHODS: First, mice were given drinking water containing dextran sodium sulfate (DSS) and then subjected to inflammatory arthritis. We compared the phenotypic symptoms between the cohoused and separately-housed mice. Next, donor mice were divided into DSS-treated and untreated groups and then cohoused with recipient mice. Arthritis was then induced in the recipients. The fecal microbiome was analyzed by 16S rRNA amplicon sequencing. We obtained type strains of the candidate bacteria and generated …

Chronic Kidney Disease Prediction Using Boosting Techniques Based On Clinical Parameters, Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, Saurav Mallik, Zhongming Zhao

Faculty, Staff and Student Publications

Chronic kidney disease (CKD) has become a major global health crisis, causing millions of yearly deaths. Predicting the possibility of a person being affected by the disease will allow timely diagnosis and precautionary measures leading to preventive strategies for health. Machine learning techniques have been popularly applied in various disease diagnoses and predictions. Ensemble learning approaches have become useful for predicting many complex diseases. In this paper, we utilise the boosting method, one of the popular ensemble learnings, to achieve a higher prediction accuracy for CKD. Five boosting algorithms are employed: XGBoost, CatBoost, LightGBM, AdaBoost, and gradient boosting. We experimented …

Accurate Prediction Of Functional Effect Of Single Amino Acid Variants With Deep Learning, Houssemeddine Derbel, Zhongming Zhao, Qian Liu

Faculty, Staff and Student Publications

The assessment of functional effect of amino acid variants is a critical biological problem in proteomics for clinical medicine and protein engineering. Although natively occurring variants offer insights into deleterious variants, high-throughput deep mutational experiments enable comprehensive investigation of amino acid variants for a given protein. However, these mutational experiments are too expensive to dissect millions of variants on thousands of proteins. Thus, computational approaches have been proposed, but they heavily rely on hand-crafted evolutionary conservation, limiting their accuracy. Recent advancement in transformers provides a promising solution to precisely estimate the functional effects of protein variants on high-throughput experimental data. …

Optimal Ranking And Directional Signature Classification Using The Integral Strategy Of Multi-Objective Optimization-Based Association Rule Mining Of Multi-Omics Data, Saurav Mallik, Soumita Seth, Amalendu Si, Tapas Bhadra, Zhongming Zhao

Faculty, Staff and Student Publications

No abstract provided.

3pnmf-Mkl: A Non-Negative Matrix Factorization-Based Multiple Kernel Learning Method For Multi-Modal Data Integration And Its Application To Gene Signature Detection\, Saurav Mallik, Anasua Sarkar, Sagnik Nath, Ujjwal Maulik, Supantha Das, Soumen Kumar Pati, Soumadip Ghosh, Zhongming Zhao

Faculty, Staff and Student Publications

In this current era, biomedical big data handling is a challenging task. Interestingly, the integration of multi-modal data, followed by significant feature mining (gene signature detection), becomes a daunting task. Remembering this, here, we proposed a novel framework, namely, three-factor penalized, non-negative matrix factorization-based multiple kernel learning with soft margin hinge loss (3PNMF-MKL) for multi-modal data integration, followed by gene signature detection. In brief, limma, employing the empirical Bayes statistics, was initially applied to each individual molecular profile, and the statistically significant features were extracted, which was followed by the three-factor penalized non-negative matrix factorization method used for data/matrix fusion …

Predictive Modeling Using Shape Statistics For Interpretable And Robust Quality Assurance Of Automated Contours In Radiation Treatment Planning, Zachary T Wooten, Cenji Yu, Laurence E Court, Christine B Peterson

Faculty, Staff and Student Publications

Deep learning methods for image segmentation and contouring are gaining prominence as an automated approach for delineating anatomical structures in medical images during radiation treatment planning. These contours are used to guide radiotherapy treatment planning, so it is important that contouring errors are flagged before they are used for planning. This creates a need for effective quality assurance methods to enable the clinical use of automated contours in radiotherapy. We propose a novel method for contour quality assurance that requires only shape features, making it independent of the platform used to obtain the images. Our method uses a random forest …

Grid Cells, Border Cells, And Discrete Complex Analysis, Yuri Dabaghian

Faculty, Staff and Student Publications

We propose a mechanism enabling the appearance of border cells-neurons firing at the boundaries of the navigated enclosures. The approach is based on the recent discovery of discrete complex analysis on a triangular lattice, which allows constructing discrete epitomes of complex-analytic functions and making use of their inherent ability to attain maximal values at the boundaries of generic lattice domains. As it turns out, certain elements of the discrete-complex framework readily appear in the oscillatory models of grid cells. We demonstrate that these models can extend further, producing cells that increase their activity toward the frontiers of the navigated environments. …

Pediatric Diarrhea Patients Living In Urban Areas Have A Higher Incidence Of Clostridioides Difficile Infection, Ayodele T Adesoji, Osaro Mgbere, Charles Darkoh

Faculty, Staff and Student Publications

Clostridioides difficile infection (CDI) is a major cause of antibiotic-associated diarrhea and an unappreciated contributor to child mortality in low- and middle-income countries where the diagnosis may be difficult. There is little information about the prevalence of CDI among infants, children, and adolescents in Africa. Using a cross-sectional design, seventy-six samples were collected from pediatric patients presenting with diarrhea, including infants (≤ 2 years old), children (2-12 years), and adolescents (13 ≤17 years) from three hospitals between January and December 2019. Demographic data, medical history, and prior antibiotic use were recorded. Toxigenic culture and PCR were used to detect and …

Population-Based Assessment Of The Burden Of Covid-19 Infection In African Countries: A First-Year Report Card And Public Health Implications, Osaro Mgbere, Ogbonna Collins Nwabuko, Olajumoke A Olateju, Omolola E Adepoju, Winston Liaw, Charles Darkoh, Ekere James Essien

Faculty, Staff and Student Publications

BACKGROUND: The COVID-19 pandemic constitutes a global health threat and poses a major burden on the African continent. We assessed the real-world burden of COVID-19 infection in African Union (AU) member states to determine the distributional patterns of epidemiological measures during the first 1 year of the pandemic.

METHODS: This retrospective cross-sectional study utilized COVID-19 data from publicly available data repositories of the African Center for Disease Control and Prevention and

RESULTS: A total of 3.21 million cases were reported during the 1-year period, with 2.6 million recoveries, 536,784 cases remaining active, and 77,486 deaths. Most countries (49.1%,

CONCLUSION: Understanding …

Evolutionary Aspects Of Infections: Inflammation And Sickness Behaviors, Robert Dantzer

Faculty, Staff and Student Publications

Sickness behavior was conceptualized initially as the behavioral counterpart of the fever response to infectious pathogens. It helps to raise body temperature to its higher setpoint and to maintain it at this new level and it has the additional benefit of enabling a weakened organism to protect itself from other dangers. The discovery of the behavioral effects of proinflammatory cytokines produced by activated immune cells provided a cellular and molecular basis to this phenomenon. The administration of cytokines or cytokine inducers like lipopolysaccharide to healthy rodents allowed to reveal the similarities and differences between inflammation-induced sickness behavior and the fever …

Inhibition Of Nox2 Or Nlrp3 Inflammasome Prevents Cardiac Remote Ischemic Preconditioning, Sandra Benavides, Rodrigo Palavecino, Jaime A Riquelme, Luis Montecinos, José Pablo Finkelstein, Paulina Donoso, Gina Sánchez

Faculty, Staff and Student Publications

Introduction: Short episodes of ischemia-reperfusion (IR) in the heart (classical ischemic preconditioning, IPC) or in a limb (remote ischemic preconditioning, RIPC) before a prolonged ischemic episode, reduce the size of the infarct. It is unknown whether IPC and RIPC share common mechanisms of protection. Animals KO for NOX2, a superoxide-producing enzyme, or KO for NLRP3, a protein component of inflammasome, are not protected by IPC. The aim of this study was to investigate if NOX2 or NLRP3 inflammasome are involved in the protection induced by RIPC. Methods: We preconditioned rats using 4 × 5 min periods of IR in the …

Endothelial Activation Impairs The Function Of Small Extracellular Vesicles, Nicolas Herrera-Zelada, Úrsula Zúñiga-Cuevas, Andrés Ramírez-Reyes, Ignacio Norambuena-Soto, Leslye Venegas-Zamora, Mayarling F Troncoso, Alejandra Hernández, Gina Sánchez, Zully Pedrozo, Sergio Lavandero, Jaime A Riquelme

Faculty, Staff and Student Publications

Small extracellular vesicles are nanosized vesicles (30-200 nm) that can ferry proteins, nucleic acids, and lipids between cells and therefore, have significant potential as biomarkers, drug delivery tools or therapeutic agents. SEVs of endothelial origin have been shown to -among other functions-reduce in vitro ischemia/reperfusion (I/R) injury in cardiomyocytes, but whether a pro-inflammatory state of the endothelium impairs the functionality of these SEVs remains to be elucidated. To test this, human umbilical vein endothelial cells cells were treated with TNF-α 10 ng/mL and the expression of the pro-inflammatory parameters VCAM-1, ICAM-1 and eNOS were determined by Western blot. SEVs were …

Targeting Mcl-1 Protein To Treat Cancer: Opportunities And Challenges, Shady I Tantawy, Natalia Timofeeva, Aloke Sarkar, Varsha Gandhi

Faculty, Staff and Student Publications

Evading apoptosis has been linked to tumor development and chemoresistance. One mechanism for this evasion is the overexpression of prosurvival B-cell lymphoma-2 (BCL-2) family proteins, which gives cancer cells a survival advantage. Mcl-1, a member of the BCL-2 family, is among the most frequently amplified genes in cancer. Targeting myeloid cell leukemia-1 (MCL-1) protein is a successful strategy to induce apoptosis and overcome tumor resistance to chemotherapy and targeted therapy. Various strategies to inhibit the antiapoptotic activity of MCL-1 protein, including transcription, translation, and the degradation of MCL-1 protein, have been tested. Neutralizing MCL-1's function by targeting its interactions …

Reactome Pathway Analysis From Whole-Blood Transcriptome Reveals Unique Characteristics Of Systemic Sclerosis Patients At The Preclinical Stage, Chiara Bellocchi, Xuan Wang, Marka A Lyons, Maurizio Marchini, Maurizio Lorini, Vincenzo Carbonelli, Nicola Montano, Shervin Assassi, Lorenzo Beretta

Faculty, Staff and Student Publications

OBJECTIVE: This study aims to characterize differential expressed pathways (DEP) in subjects with preclinical systemic sclerosis (PreSSc) characterized uniquely by Raynaud phenomenon, specific autoantibodies, and/or capillaroscopy positive for scleroderma pattern.

METHODS: Whole-blood samples from 33 PreSSc with clinical prospective data (baseline and after 4 years of follow-up) and 16 matched healthy controls (HC) were analyzed for global gene expression transcriptome analysis via RNA sequencing. Functional Analysis of Individual Microarray Expression method annotated Reactome individualized pathways. ANOVA analysis identified DEP whose predictive capability were tested in logistic regression models after extensive internal validation.

RESULTS: At 4 years, 42.4% subjects progressed (evolving …

The Rising Tide Of Revisional Surgery: Tracking Changes In Index Cases Among Bariatric-Accredited Fellowships, Lincoln N Strickland, Erika Y Faraoni, Wei Ruan, Xiaoyi Yuan, Holger K Eltzschig, Jennifer M Bailey-Lundberg

Faculty, Staff and Student Publications

Pancreatic ductal adenocarcinoma (PDAC) is characterized by a dense desmoplastic stroma that impedes drug delivery, reduces parenchymal blood flow, and suppresses the anti-tumor immune response. The extracellular matrix and abundance of stromal cells result in severe hypoxia within the tumor microenvironment (TME), and emerging publications evaluating PDAC tumorigenesis have shown the adenosine signaling pathway promotes an immunosuppressive TME and contributes to the overall low survival rate. Hypoxia increases many elements of the adenosine signaling pathway, resulting in higher adenosine levels in the TME, further contributing to immune suppression. Extracellular adenosine signals through 4 adenosine receptors (Adora1, Adora2a, Adora2b, Adora3). Of …

Cytological Diagnosis Of Pilomatrixoma And Its Diagnostic Pitfalls, Sabina Khan, Inara Abeer, Musharraf Husain, Sujata Jetley

Faculty, Staff and Student Publications

BACKGROUND: Pilomatrixoma (PMX) is a relatively uncommon benign cutaneous neoplasm arising from skin adnexa. It presents as a subcutaneous asymptomatic nodule mostly in the head and neck region and is frequently misdiagnosed by the clinicians. Although easily diagnosed on histopathology, the cytologic features of PMX are less distinctive, depending on the stage and evolution of disease and may mimic other benign or even malignant lesions.

AIM: To study the cyto-morphological features of this uncommon neoplasm and identify its potential diagnostic pitfalls on fine needle aspiration cytology (FNAC).

MATERIAL AND METHODS: Archival records of histopathologically diagnosed Pilomatrixoma were analyzed during study …

Chronic Restraint Stress Impairs Voluntary Wheel Running But Has No Effect On Food-Motivated Behavior In Mice, Kiersten Scott, Thien Trong Phan, Nabila Boukelmoune, Cobi J Heijnen, Robert Dantzer

Faculty, Staff and Student Publications

Chronic restraint stress is known to cause significant alterations of mitochondrial biology. However, its effects on effort-based behavior and the sensitivity of these effects to treatments that restore mitochondrial function have not been assessed. Based on the hypothesis that the behavioral consequences of this stressor should be more severe for an energy demanding activity than for an energy procuring activity, we compared the effects of chronic restraint stress on the performance of male mice trained to use a running wheel or to nose poke for a food reward in an operant conditioning cage. In accordance with our hypothesis, we observed …

Henry Gas Solubility Optimization Double Machine Learning Classifier For Neurosurgical Patients, Diana T Mosa, Amena Mahmoud, John Zaki, Shaymaa E Sorour, Shaker El-Sappagh, Tamer Abuhmed

Faculty, Staff and Student Publications

This study aims to predict head trauma outcome for Neurosurgical patients in children, adults, and elderly people. As Machine Learning (ML) algorithms are helpful in healthcare field, a comparative study of various ML techniques is developed. Several algorithms are utilized such as k-nearest neighbor, Random Forest (RF), C4.5, Artificial Neural Network, and Support Vector Machine (SVM). Their performance is assessed using anonymous patients' data. Then, a proposed double classifier based on Henry Gas Solubility Optimization (HGSO) is developed with Aquila optimizer (AQO). It is implemented for feature selection to classify patients' outcome status into four states. Those are mortality, morbidity, …

Radiographic Response To Neoadjuvant Therapy In Pleural Mesothelioma Should Serve As A Guide For Patient Selection For Cytoreductive Operations, Nathaniel Deboever, Nicolas Zhou, Daniel J Mcgrail, Katarzyna Tomczak, Jacqueline L Oliva, Hope A Feldman, Edwin Parra, Jianjun Zhang, Percy P Lee, Mara B Antonoff, Wayne L Hofstetter, Reza J Mehran, Ravi Rajaram, David C Rice, Jack A Roth, Stephen S Swisher, Ara A Vaporciyan, Mehmet Altan, Annikka Weissferdt, Anne S Tsao, Cara L Haymaker, Boris Sepesi

Faculty, Staff and Student Publications

BACKGROUND: Malignant pleural mesothelioma (MPM) is associated with poor prognosis despite advances in multimodal therapeutic strategies. While patients with resectable disease may benefit from added survival with oncologic resection, patient selection for mesothelioma operations often relies on both objective and subjective evaluation metrics. We sought to evaluate factors associated with improved overall survival (OS) in patients with mesothelioma who underwent macroscopic complete resection (MCR).

METHODS: Patients with MPM who received neoadjuvant therapy and underwent MCR were identified in a prospectively maintained departmental database. Clinicopathologic, blood-based, and radiographic variables were collected and included in a Cox regression analysis (CRA). Response to …