Medicine and Health Sciences Commons^™

Landmark Mediation Survival Analysis Using Longitudinal Surrogate, Jie Zhou, Xun Jiang, H Amy Xia, Brian P Hobbs, Peng Wei

Faculty, Staff and Student Publications

Clinical cancer trials are designed to collect radiographic measurements of each patient's baseline and residual tumor burden at regular intervals over the course of study. For solid tumors, the extent of reduction in tumor size following treatment is used as a measure of a drug's antitumor activity. Statistical estimation of treatment efficacy routinely reduce the longitudinal assessment of tumor burden to a binary outcome describing the presence versus absence of an objective tumor response as defined by RECIST criteria. The objective response rate (ORR) is the predominate method for evaluating an experimental therapy in a single-arm trial. Additionally, ORR is …

Loss Of Mmr And Tgfbr2 Increases The Susceptibility To Microbiota-Dependent Inflammation-Associated Colon Cancer, Elena Tosti, Ana S Almeida, Tam T T Tran, Mariel Barbachan E Silva, Pilib Ó Broin, Robert Dubin, Ken Chen, Amanda P Beck, Andrew S Mclellan, Eduardo Vilar, Aaron Golden, Paul W O'Toole, Winfried Edelmann

Faculty, Staff and Student Publications

Background and aims: Mutations in DNA mismatch repair (MMR) genes are causative in Lynch syndrome and a significant proportion of sporadic colorectal cancers (CRCs). MMR-deficient (dMMR) CRCs display increased mutation rates, with mutations frequently accumulating at short repetitive DNA sequences throughout the genome (microsatellite instability). The TGFBR2 gene is one of the most frequently mutated genes in dMMR CRCs. Therefore, we generated an animal model to study how the loss of both TGFBR2 signaling impacts dMMR-driven intestinal tumorigenesis in vivo and explore the impact of the gut microbiota.

Methods: We generated VCMsh2/Tgfbr2 mice in which Msh2loxP and Tgfbr2loxP alleles are …

Recent Advances On Dna Base Flipping: A General Mechanism For Writing, Reading, And Erasing Dna Modifications, Ren Ren, John R Horton, Samuel Hong, Xiaodong Cheng

Faculty, Staff and Student Publications

The modification of DNA bases is a classic hallmark of epigenetics. Four forms of modified cytosine-5-methylcytosine, 5-hydroxymethylcytosine, 5-formylcytosine, and 5-carboxylcytosine-have been discovered in eukaryotic DNA. In addition to cytosine carbon-5 modifications, cytosine and adenine methylated in the exocyclic amine-N4-methylcytosine and N6-methyladenine-are other modified DNA bases discovered even earlier. Each modified base can be considered a distinct epigenetic signal with broader biological implications beyond simple chemical changes. Since 1994, several crystal structures of proteins and enzymes involved in writing, reading, and erasing modified bases have become available. Here, we present a structural synopsis of writers, readers, and erasers of the modified …

A Phase I, Open-Label, Dose-Escalation Study Of The Ox40 Agonist Ivuxolimab In Patients With Locally Advanced Or Metastatic Cancers, Adi Diab, Omid Hamid, John A Thompson, Willeke Ros, Ferry A L M Eskens, Toshihiko Doi, Siwen Hu-Lieskovan, Samuel J Klempner, Bishu Ganguly, Catherine Fleener, Xiao Wang, Tenshang Joh, Ken Liao, Shahram Salek-Ardakani, Carrie Turich Taylor, Jeffrey Chou, Anthony B El-Khoueiry

Faculty, Staff and Student Publications

PURPOSE: Stimulation of effector T cells is an appealing immunotherapeutic approach in oncology. OX40 (CD134) is a costimulatory receptor expressed on activated CD4

PATIENTS AND METHODS: Adult patients (

RESULTS: The most common all-causality adverse events were fatigue (46.2%), nausea (28.8%), and decreased appetite (25.0%). Of 31 treatment-related adverse events, 30 (96.8%) were grade ≤2. No dose-limiting toxicities occurred. Ivuxolimab exposure increased in a dose-proportionate manner from 0.3 to 10 mg/kg. Full peripheral blood target engagement occurred at ≥0.3 mg/kg. Three (5.8%) patients achieved a partial response, and disease control was achieved in 56% of patients. Increased CD4

CONCLUSIONS: Ivuxolimab …

Inhibition Of The Cd47-Sirpα Axis For Cancer Therapy: A Systematic Review And Meta-Analysis Of Emerging Clinical Data, Ji Son, Rodney Cheng-En Hsieh, Heather Y Lin, Kate J Krause, Ying Yuan, Amadeo B Biter, James Welsh, Michael A Curran, David S Hong

Faculty, Staff and Student Publications

CD47-SIRPα interaction acts as a "don't eat me" signal and is exploited by cancer to downregulate innate and adaptive immune surveillance. There has been intense interest to develop a mechanism of blockade, and we aimed to analyze the emerging data from early clinical trials. We performed a systematic review and meta-analysis of relevant databases and conference abstracts including clinical trials using CD47 and/or SIRPα inhibitors in cancer treatment. Nonlinear mixed models were applied for comparison of response and toxicity. We retrieved 317 articles, 24 of which were eligible. These included 771 response-evaluable patients with hematologic (47.1%) and solid tumors (52.9%). …

Cell-Directed Aptamer Therapeutic Targeting For Cancers Including Those Within The Central Nervous System, Jun Wei, Renduo Song, Aria Sabbagh, Anantha Marisetty, Neal Shukla, Dexing Fang, Hinda Najem, Martina Ott, James Long, Lijie Zhai, Maciej S Lesniak, Charles David James, Leonidas Platanias, Michael Curran, Amy B Heimberger

Faculty, Staff and Student Publications

Osteopontin (OPN) is produced by tumor cells as well as by myeloid cells and is enriched in the tumor microenvironment (TME) of many cancers. Given the roles of OPN in tumor progression and immune suppression, we hypothesized that targeting OPN with aptamers that have high affinity and specificity could be a promising therapeutic strategy. Bi-specific aptamers targeting ligands for cellular internalization were conjugated to siRNAs to suppress OPN were created, and therapeutic leads were selected based on target engagement and

Comparison Of Psma-Based 18f-Dcfpyl Pet/Ct And Pelvic Multiparametric Mri For Lesion Detection In The Pelvis In Patients With Prostate Cancer, Trinh T Nguyen, Priya R Bhosale, Guofan Xu, Tinsu Pan, Peng Wei, Yang Lu

Faculty, Staff and Student Publications

Purpose: To directly compare the performance of pelvic mpMRI versus recently approved and increasingly used PSMA-based 18F-DCFPyL PET/CT in intermediate-high risk and biochemical recurrent prostate cancer patient cohort while exploring their potential differing applications in specific clinical scenarios.

Methods: A retrospective analysis was performed on patients who had 18F-DCFPyL PET/CT and pelvic mpMRI done from September 2021 to January 2022 at a single institution. The inclusion criteria were paired exams within a 3-month interval. Exclusion criteria were intervening treatment between exams, a change in PSA by more than 50% and absolute difference more than 1 ng/mL, or concurrent history of …

Checkpoint Inhibitors As Immunotherapy For Fungal Infections: Promises, Challenges, And Unanswered Questions, Sebastian Wurster, Stephanie S Watowich, Dimitrios P Kontoyiannis

Faculty, Staff and Student Publications

Opportunistic fungal infections have high mortality in patients with severe immune dysfunction. Growing evidence suggests that the immune environment of invasive fungal infections and cancers share common features of immune cell exhaustion through activation of immune checkpoint pathways. This observation gave rise to several preclinical studies and clinical case reports describing blockade of the Programmed Cell Death Protein 1 and Cytotoxic T-Lymphocyte Antigen 4 immune checkpoint pathways as an adjunct immune enhancement strategy to treat opportunistic fungal infections. The first part of this review summarizes the emerging evidence for contributions of checkpoint pathways to the immunopathology of fungal sepsis, opportunistic …

A Yeast Model For Trichohepatoenteric Syndrome Suggests Strong Loss Of Ski2 Function In Most Causative Mutations, Luisa J Orlando, Matthew K Yim, Thomson Hallmark, Michael Cotner, Sean J Johnson, Ambro Van Hoof

Faculty, Staff and Student Publications

The intestinal and immune disorder trichohepatoenteric syndrome (THES) is characterized by mutations in human Ski2 and Ski3, also known as SKIV2L and TTC37, respectively. The mechanism by which these mutations leads to the immunodeficiency, chronic diarrhea, failure to thrive and liver disease associated with THES is unknown. To what degree THES patient mutations in Ski2 affect Ski2 function and how the differences in Ski2 function could lead to varying patient outcomes has not been studied. Here, we assayed function of THES ski2 mutants in the yeast homolog. Our results show that most THES patient mutations cause severe dysfunction in Ski2. …

An Autoencoder-Based Deep Learning Method For Genotype Imputation, Meng Song, Jonathan Greenbaum, Joseph Luttrell, Weihua Zhou, Chong Wu, Zhe Luo, Chuan Qiu, Lan Juan Zhao, Kuan-Jui Su, Qing Tian, Hui Shen, Huixiao Hong, Ping Gong, Xinghua Shi, Hong-Wen Deng, Chaoyang Zhang

Faculty, Staff and Student Publications

Genotype imputation has a wide range of applications in genome-wide association study (GWAS), including increasing the statistical power of association tests, discovering trait-associated loci in meta-analyses, and prioritizing causal variants with fine-mapping. In recent years, deep learning (DL) based methods, such as sparse convolutional denoising autoencoder (SCDA), have been developed for genotype imputation. However, it remains a challenging task to optimize the learning process in DL-based methods to achieve high imputation accuracy. To address this challenge, we have developed a convolutional autoencoder (AE) model for genotype imputation and implemented a customized training loop by modifying the training process with a …

Recurrent Hgnet-Mn1 Altered (Astroblastoma Mn1-Altered) Of The Foramen Magnum: Case Report And Molecular Classification, Sricharan Gopakumar, Malcolm F Mcdonald, Himanshu Sharma, Claudio E Tatsui, Gregory N Fuller, Ganesh Rao

Faculty, Staff and Student Publications

Background: Astroblastoma is a rare primary brain tumor of unclear origin, often occurring in young patients less than 30-years-old. It typically arises supratentorially and is diagnosed based on histological features including vascular hyalinization and perivascular pseudorosettes. Recent molecular characterization of primary CNS high-grade neuroepithelial tumors with meningioma I alteration (HGNET-MN1) found that HGNET-MN1 and tumors with morphological signatures of astroblastoma clustered together. Further analysis revealed such astroblastomas have MN1 alteration and the 2021 WHO classification of tumors of the CNS now recognizes astroblastoma MN1-altered as a new entity.

Case description: Here, we present the case of …

Modeling Recurrence In Idiopathic Subglottic Stenosis With Mobile Peak Expiratory Flow, Kyle Kimura, Liping Du, Lynn D Berry, Li-Ching Huang, Sheau-Chiann Chen, David O Francis, Alexander Gelbard

Faculty, Staff and Student Publications

OBJECTIVES/HYPOTHESIS: We sought to establish normative peak expiratory flow (PEF) data for patients with idiopathic subglottic stenosis (iSGS), evaluate whether immediate changes in PEF after a procedure predict long-term treatment response, and test if a decline in longitudinal PEF is associated with disease recurrence.

STUDY DESIGN: International, prospective, 3-year multicenter cohort study of 810 patients with untreated, newly diagnosed, or previously treated iSGS.

METHODS: iSGS patients consented and enrolled in the North American Airway Collaborative (NoAAC) iSGS

RESULTS: Within the NoAAC iSGS1000 cohort, 810 patients participated in a 3-year, prospective study comparing surgical treatment efficacy and 385 had appropriate PEF …

Associations Of High-Sensitivity Troponin And Natriuretic Peptide Levels With Outcomes After Intensive Blood Pressure Lowering: Findings From The Sprint Randomized Clinical Trial, Jarett D Berry, Vijay Nambi, Walter T Ambrosius, Haiying Chen, Anthony A Killeen, Addison Taylor, Robert D Toto, Elsayed Z Soliman, John W Mcevoy, Ambarish Pandey, Parag H Joshi, Stefan Blankenberg, Dalane W Kitzman, Christie M Ballantyne, James A De Lemos

Faculty, Staff and Students Publications

IMPORTANCE: Elevated high-sensitivity cardiac troponin T (hscTnT) and N-terminal pro-B-type natriuretic peptide (NTproBNP) levels are associated with risk of heart failure (HF) and mortality among individuals in the general population. However, it is unknown if this risk is modifiable.

OBJECTIVE: To test the hypothesis that elevated hscTnT and NTproBNP levels would identify individuals with the greatest risk for mortality and HF and the largest benefit associated with intensive systolic blood pressure (SBP) lowering.

DESIGN, SETTING, AND PARTICIPANTS: This is a nonprespecified post hoc analysis of the multicenter, prospective, randomized clinical Systolic Blood Pressure Intervention Trial (SPRINT), conducted from October 20, …

Nrf1 Association With Auts2-Polycomb Mediates Specific Gene Activation In The Brain, Sanxiong Liu, Kimberly A Aldinger, Chi Vicky Cheng, Takae Kiyama, Mitali Dave, Hanna K Mcnamara, Wukui Zhao, James M Stafford, Nicolas Descostes, Pedro Lee, Stefano G Caraffi, Ivan Ivanovski, Edoardo Errichiello, Christiane Zweier, Orsetta Zuffardi, Michael Schneider, Antigone S Papavasiliou, M Scott Perry, Jennifer Humberson, Megan T Cho, Astrid Weber, Andrew Swale, Tudor C Badea, Chai-An Mao, Livia Garavelli, William B Dobyns, Danny Reinberg

Faculty, Staff and Student Publications

The heterogeneous family of complexes comprising Polycomb repressive complex 1 (PRC1) is instrumental for establishing facultative heterochromatin that is repressive to transcription. However, two PRC1 species, ncPRC1.3 and ncPRC1.5, are known to comprise novel components, AUTS2, P300, and CK2, that convert this repressive function to that of transcription activation. Here, we report that individuals harboring mutations in the HX repeat domain of AUTS2 exhibit defects in AUTS2 and P300 interaction as well as a developmental disorder reflective of Rubinstein-Taybi syndrome, which is mainly associated with a heterozygous pathogenic variant in CREBBP/EP300. Moreover, the absence of AUTS2 or mutation in its …

Artificial Intelligence Algorithms For Medical Imaging And Healthcare, Jonathan William Stubblefield

Student Theses and Dissertations

In this dissertation, we studied several applications of artificial intelligence applications to healthcare. In the first chapter, we examined a machine learning algorithm for classifying patients presenting to the emergency department with acute respiratory distress syndrome (ARDS). Patients presenting with this life-threatening condition require a quick and accurate assessment of whether the condition is infectious or cardiac in etiology as the treatments for these etiologies of ARDS differ significantly. We used a transfer learning approach to develop our model. The model used a combination of clinical data and a chest x-ray as its input and achieved an accuracy 0.675 on …

Enhance Representation Learning Of Clinical Narrative With Neural Networks For Clinical Predictive Modeling, Yuqi Si

Dissertations and Theses (Open Access)

Medicine is undergoing a technological revolution. Understanding human health from clinical data has major challenges from technical and practical perspectives, thus prompting methods that understand large, complex, and noisy data. These methods are particularly necessary for natural language data from clinical narratives/notes, which contain some of the richest information on a patient. Meanwhile, deep neural networks have achieved superior performance in a wide variety of natural language processing (NLP) tasks because of their capacity to encode meaningful but abstract representations and learn the entire task end-to-end. In this thesis, I investigate representation learning of clinical narratives with deep neural networks …

Secondary Use Of Structured Electronic Health Records Data: From Observational Studies To Deep Learning-Based Predictive Modeling, Laila Bekhet

Dissertations and Theses (Open Access)

With the wide adoption of electronic health records (EHRs), researchers, as well as large healthcare organizations, governmental institutions, insurance, and pharmaceutical companies have been interested in leveraging this rich clinical data source to extract clinical evidence and develop predictive algorithms. Large vendors have been able to compile structured EHR data from sites all over the United States, de-identify these data, and make them available to data science researchers in a more usable format. For this dissertation, we leveraged one of the earliest and largest secondary EHR data sources and conducted three studies of increasing scope. In the first study, which …

Perspectives From The Society For Pediatric Research: Advice On Sustaining Science And Mentoring During Covid-19, Catherine S Forster, Suong T Nguyen, Weston T Powell, Daniel J Moore, Jacqueline Ho, Melvin B Heyman, Tara L Wenger, Fernando Gonzalez, Margaret Hostetter, Andrew Nowalk, Caroline E Rassbach, Debra Boyer, Pnina Weiss, Rebecca L Blankenburg, Jordan S Orange, Kate G Ackerman, Audrea M Burns, National Pediatric Physician-Scientist Collaborative Workgroup

Faculty, Staff and Students Publications

The COVID-19 pandemic will leave an indelible mark on the careers of current medical trainees. Given the disruptions to medical education, economic impact on institutions, and the uncertainties around future job prospects, trainees are facing unprecedented challenges. This situation is especially concerning for futures of pediatric physician-scientist trainees, where concerns regarding maintaining the pipeline were well documented prior to the emergence of COVID-19. In this Perspectives article, we leverage the unique expertise of our workgroup to address concerns of physician-scientist trainees and to provide suggestions on how to navigate career trajectories in the post-COVID-19 era. We identified and addressed four …

Invariant Natural Killer T-Cell Subsets Have Diverse Graft-Versus-Host-Disease-Preventing And Antitumor Effects, Kristina Maas-Bauer, Juliane K Lohmeyer, Toshihito Hirai, Teresa Lopes Ramos, Furqan M Fazal, Ulrike M Litzenburger, Kathryn E Yost, Jessica V Ribado, Neeraja Kambham, Arielle S Wenokur, Po-Yu Lin, Maite Alvarez, Melissa Mavers, Jeanette Baker, Ami S Bhatt, Howard Y Chang, Federico Simonetta, Robert S Negrin

Faculty, Staff and Students Publications

Invariant natural killer T (iNKT) cells are a T-cell subset with potent immunomodulatory properties. Experimental evidence in mice and observational studies in humans indicate that iNKT cells have antitumor potential as well as the ability to suppress acute and chronic graft-versus-host-disease (GVHD). Murine iNKT cells differentiate during thymic development into iNKT1, iNKT2, and iNKT17 sublineages, which differ transcriptomically and epigenomically and have subset-specific developmental requirements. Whether distinct iNKT sublineages also differ in their antitumor effect and their ability to suppress GVHD is currently unknown. In this work, we generated highly purified murine iNKT sublineages, characterized their transcriptomic and epigenomic landscape, …

Comprehensive Characterization Of Covid-19 Patients With Repeatedly Positive Sars-Cov-2 Tests Using A Large Us Electronic Health Record Database, Xiao Dong, Yujia Zhou, Xiao-Ou Shu, Elmer V Bernstam, Rebecca Stern, David M Aronoff, Hua Xu, Loren Lipworth

Faculty, Staff and Student Publications

In the absence of genome sequencing, two positive molecular tests for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) separated by negative tests, prolonged time, and symptom resolution remain the best surrogate measure of possible reinfection. Using a large electronic health record database, we characterized clinical and testing data for 23 patients with repeatedly positive SARS-CoV-2 PCR test results ≥60 days apart, separated by ≥2 consecutive negative test results. The prevalence of chronic medical conditions, symptoms, and severe outcomes related to coronavirus disease 19 (COVID-19) illness were ascertained. The median age of patients was 64.5 years, 40% were Black, and 39% …

A Comparison Of Machine Learning Classifiers For Pediatric Epilepsy Using Resting-State Functional Mri Latency Data, Ryan D Nguyen, Matthew D Smyth, Liang Zhu, Ludovic P Pao, Shannon K Swisher, Emmett H Kennady, Anish Mitra, Rajan P Patel, Jeremy E Lankford, Gretchen Von Allmen, Michael W Watkins, Michael E Funke, Manish N Shah

Faculty, Staff and Student Publications

Epilepsy affects 1 in 150 children under the age of 10 and is the most common chronic pediatric neurological condition; poor seizure control can irreversibly disrupt normal brain development. The present study compared the ability of different machine learning algorithms trained with resting-state functional MRI (rfMRI) latency data to detect epilepsy. Preoperative rfMRI and anatomical MRI scans were obtained for 63 patients with epilepsy and 259 healthy controls. The normal distribution of latency z-scores from the epilepsy and healthy control cohorts were analyzed for overlap in 36 seed regions. In these seed regions, overlap between the study cohorts ranged from …

First-In-Human Segmental Esophageal Reconstruction Using A Bioengineered Mesenchymal Stromal Cell-Seeded Implant, Johnathon M Aho, Saverio La Francesca, Scott D Olson, Fabio Triolo, Jeff Bouchard, Laura Mondano, Sumati Sundaram, Christina Roffidal, Charles S Cox, Louis M Wong Kee Song, Sameh M Said, William Fodor, Dennis A Wigle

Faculty, Staff and Student Publications

INTRODUCTION: Resection and reconstruction of the esophagus remains fraught with morbidity and mortality. Recently, data from a porcine reconstruction model revealed that segmental esophageal reconstruction using an autologous mesenchymal stromal cell-seeded polyurethane graft (Cellspan esophageal implant [CEI]) can facilitate esophageal regrowth and regeneration. To this end, a patient requiring a full circumferential esophageal segmental reconstruction after a complex multiorgan tumor resection was approved for an investigational treatment under the Food and Drug Administration Expanded Access Use (Investigational New Drug 17402).

METHODS: Autologous adipose-derived mesenchymal stromal cells (Ad-MSCs) were isolated from the Emergency Investigational New Drug patient approximately 4 weeks before …

Standardizing New Diagnostic Tests To Facilitate Rapid Responses To The Covid-19 Pandemic, Xiao Dong

Dissertations and Theses (Open Access)

In order to enhance the data interoperability, an expeditious and accurate standardization solution is highly desirable for naming rapidly emerging novel lab tests, and thus diminishes confusion in early responses to pandemic outbreaks. This is a preliminary study to explore the roles and implementation of medical informatics technology, especially natural language processing and ontology methods, in standardizing information about emerging lab tests during a pandemic, thereby facilitating rapid responses to the pandemic. The ultimate goal of this study is to develop an informatics framework for rapid standardization of lab testing names during a pandemic to better prepare for future public …

Deep Learning-Based Mixed-Dimensional Gaussian Mixture Model For Characterizing Variability In Cryo-Em, Muyuan Chen, Steven J Ludtke

Faculty, Staff and Students Publications

Structural flexibility and/or dynamic interactions with other molecules is a critical aspect of protein function. Cryogenic electron microscopy (cryo-EM) provides direct visualization of individual macromolecules sampling different conformational and compositional states. While numerous methods are available for computational classification of discrete states, characterization of continuous conformational changes or large numbers of discrete state without human supervision remains challenging. Here we present e2gmm, a machine learning algorithm to determine a conformational landscape for proteins or complexes using a three-dimensional Gaussian mixture model mapped onto two-dimensional particle images in known orientations. Using a deep neural network architecture, e2gmm can automatically resolve the …

Left Ventricular Recovery With Explantation Of Continuous-Flow Left Ventricular Assist Device After 5 Years Of Support, Andre Critsinelis, Chitaru Kurihara, Masashi Kawabori, Tadahisa Sugiura, Andrew B Civitello, Jeffrey A Morgan

Faculty, Staff and Students Publications

Mechanical circulatory support may result in sufficient myocardial recovery to allow for explantation of the left ventricular assist device (LVAD). The duration of support associated with left ventricular recovery has generally been 6-12 months. In this report, we present a patient in whom the left ventricle recovered after 5 years of support with a LVAD. Our report demonstrates that long-term monitoring for left ventricular recovery is prudent and may allow for late device explantation.

The Synergy Of Bet Inhibitors With Aurora A Kinase Inhibitors In Mycn-Amplified Neuroblastoma Is Heightened With Functional Tp53, Joanna S Yi, Oscar Sias-Garcia, Nicole Nasholm, Xiaoyu Hu, Amanda Balboni Iniguez, Matthew D Hall, Mindy Davis, Rajarshi Guha, Myrthala Moreno-Smith, Eveline Barbieri, Kevin Duong, Jessica Koach, Jun Qi, James E Bradner, Kimberly Stegmaier, William A Weiss, W Clay Gustafson

Faculty, Staff and Students Publications

Amplification of MYCN is a poor prognostic feature in neuroblastoma (NBL) indicating aggressive disease. We and others have shown BET bromodomain inhibitors (BETi) target MYCN indirectly by downregulating its transcription. Here we sought to identify agents that synergize with BETi and to identify biomarkers of resistance. We previously performed a viability screen of ∼1,900 oncology-focused compounds combined with BET bromodomain inhibitors against MYCN-amplified NBL cell lines. Reanalysis of our screening results prominently identified inhibitors of aurora kinase A (AURKAi) to be highly synergistic with BETi. We confirmed the anti-proliferative effects of several BETi+AURKAi combinations in MYCN-amplified NBL cell lines. Compared …

Digital Technology Needs In Maternal Mental Health: A Qualitative Inquiry, Alexandra Zingg, Laura Carter, Deevakar Rogith, Amy Franklin, Sudhakar Selvaraj, Jerrie Refuerzo, Sahiti Myneni

Faculty, Staff and Student Publications

Digital technologies offer many opportunities to improve mental healthcare management for women seeking pre- and-postnatal care. They provide a discrete, practical medium that is well-suited for the sensitive nature of mental health. Women who are more prone to experiencing peripartum depression (PPD), such as those of low-socioeconomic background or in high-risk pregnancies, can benefit the most from such technologies. However, current digital interventions directed towards this population provide suboptimal support, and their responsiveness to end user needs is quite limited. Our objective is to understand the digital terrain of information needs for low-socioeconomic status women with high-risk pregnancies, specifically within …

Deep Learning Predicts Chromosomal Instability From Histopathology Images, Zhuoran Xu, Akanksha Verma, Uska Naveed, Samuel F. Bakhoum, Pegah Khosravi, Olivier Elemento

Publications and Research

Chromosomal instability (CIN) is a hallmark of human cancer yet not readily testable for patients with cancer in routine clinical setting. In this study, we sought to explore whether CIN status can be predicted using ubiquitously available hematoxylin and eosin histology through a deep learning-based model. When applied to a cohort of 1,010 patients with breast cancer (Training set: n = 858, Test set: n = 152) from The Cancer Genome Atlas where 485 patients have high CIN status, our model accurately classified CIN status, achieving an area under the curve of 0.822 with 81.2% sensitivity and 68.7% specificity in …

Med-Bert: Pretrained Contextualized Embeddings On Large-Scale Structured Electronic Health Records For Disease Prediction, Laila Rasmy, Yang Xiang, Ziqian Xie, Cui Tao, Degui Zhi

Faculty, Staff and Student Publications

Deep learning (DL)-based predictive models from electronic health records (EHRs) deliver impressive performance in many clinical tasks. Large training cohorts, however, are often required by these models to achieve high accuracy, hindering the adoption of DL-based models in scenarios with limited training data. Recently, bidirectional encoder representations from transformers (BERT) and related models have achieved tremendous successes in the natural language processing domain. The pretraining of BERT on a very large training corpus generates contextualized embeddings that can boost the performance of models trained on smaller datasets. Inspired by BERT, we propose Med-BERT, which adapts the BERT framework originally developed …

Soluble Angiotensin-Converting Enzyme 2, Cardiac Biomarkers, Structure, And Function, And Cardiovascular Events (From The Atherosclerosis Risk In Communities Study), Aliza Hussain, Olive Tang, Caroline Sun, Xiaoming Jia, Elizabeth Selvin, Vijay Nambi, Aaron Folsom, Gerardo Heiss, Faiez Zannad, Thomas Mosley, Salim S Virani, Josef Coresh, Eric Boerwinkle, Bing Yu, Jonathan W Cunningham, Amil M Shah, Scott D Solomon, James A De Lemos, Ron C Hoogeveen, Christie M Ballantyne

Faculty, Staff and Students Publications

Membrane-bound angiotensin-converting enzyme 2 is important in regulation of the renin-angiotensin-aldosterone system, but the association of cleaved soluble ACE2 (sACE2) with cardiovascular disease (CVD) is unclear. We evaluated the association of sACE2 with cardiac biomarkers, structure, and function and cardiovascular events in the Atherosclerosis Risk in Communities Study. sACE2 was measured in a subset of 497 participants (mean age 78±5.4 years, 53% men, 27% black); Cox regression analyses assessed prospective associations of sACE2 with time to first CVD event at median 6.1-year follow-up. sACE2 was higher in men, blacks, and participants with prevalent CVD, diabetes, or hypertension. Higher sACE2 levels …