Medical Specialties Commons^™

Nci Multi-Omics Mislabeling Challenge: A Machine Learning Approach, Yeshwant Chillakuru, Arjun Panda, Sindhu Kubendran, Norman Lee

GW Research Days 2016 - 2020

Sample mislabeling is a pervasive problem in biomedical research, especially large-scale multi-omics studies, contributing to errors and leading to false conclusions. The Food and Drug Administration (FDA) and the National Cancer Institute Clinical Proteomic Tumor Analysis Consortium (NCI-CPTA) have launched a data science challenge to address this problem. We developed a novel machine learning based approach that combines traditional machine learning with learning from cancer genomics literature to identify mislabeled tumors in the NCI-CPTA Multi-omics Mislabeling Challenge.

The training data contained a sample of a tumor from 80 different patients, each containing features on gender, microsatellite instability (MSI) status, and …

Tumor Surveillance Using Liquid Biome In Pediatric High Grade Gliomas, Erin Bonner, Eshini Panditharatna, Madhuri Kambhampati, Stefaan Van Gool, Wilfried Stuecker, Roger J. Packer, Javad Nazarian

GW Research Days 2016 - 2020

Immunotherapy is currently being used to treat pediatric brain cancer, though its efficacy in treating patients with diffuse intrinsic pontine glioma (DIPG), the deadliest pediatric brain tumor, has not been evaluated. MRI is the gold standard for monitoring tumor response to therapy, but is limited by pseudoresponse and psuedoprogression: post-treatment, immune cells infiltrate the primary tumor causing transient tumor enlargement, which falsely resembles tumor progression on MRI. Thus, it is critical to develop more accurate approaches to monitor tumor response to immunotherapy. Here, we use a liquid biopsy platform we have already established to monitor tumor response to therapy, to …

Mutations In Braf Are Associated With Higher Levels Of Immune Infiltrates In Microsatellite-Stable Colon Cancer, Jake Rubin, Eduard Porta Parto

GW Research Days 2016 - 2020

While BRAF is among the most well-established oncogenes in human cancers, more recently it has garnered attention for its role in suppressing antitumor immunity, especially in melanoma. Because tumor-infiltrating lymphocyte (TIL) density is strongly prognostic in colorectal cancer (CRC)⁷, we decided to investigate the connection between TIL density and the BRAF-activating V600E mutation in CRC.

We used ESTIMATE to quantify immune infiltrate in samples from the TCGA colon adenocarcinoma (COAD) dataset (n = 216). This is an algorithm that uses the gene-expression signature of 141 immune-related genes to infer the presence of immune cells in the tumor infiltrate. …

Is The Force Awakened? Publication Trends In Oncology Big Data As Phase Ii Cancerlinq Is Launched, Hind Rafei, Benjamin Viernes, Angelike P. Liappis, Dalia Abdelaziz Mobarek

GW Research Days 2016 - 2020

Background: The American Society of Clinical Oncology launched CancerLinQ project in 2010 to provide real-time data collection, mining and visualization, clinical decision support, and quality feedback. Creation of a big data software platform is currently underway to power the CancerLinQ in the phase II of the project. This would allow for evidence driven practice and rapid learning for cancer care providers. Additionally, adequate knowledge about the utility of Big Data to encourage provider utilization in high Impact Factor (IF) journals is needed. We aimed to assess trends and quality of Big Data published in Oncology.

Methods: Peer-reviewed English …

Circulating Mirna Biomarkers In Early Breast Cancer Detection Following Mammography, Alexa Lean, Jialu Lucy Yang, Xiaohui Tan, Christine B. Teal, Rachel F. Brem, Sidney W. Fu

GW Research Days 2016 - 2020

The currently accepted stepwise model of breast tumorigenesis assumes a gradual transition from normal breast epithelial cells to atypical ductal hyperplasia (ADH), to ductal carcinoma in situ (DCIS) and then to invasive ductal carcinoma (IDC). Percutaneous core needle biopsy (CNB) is the standard technique following an abnormal mammographic finding. However, CNB is less reliable in differentiating simple ADH (sADH) from ADH component coexisted with advanced lesions such as DCIS and/or IDC (cADH). Therefore, to identify and validate novel reliable molecular biomarkers is essential in order to improve the efficiency of therapeutic recommendations, as well as to minimize anxiety and unnecessary …

Identifying Venous Thromboembolism In Cancer Patients Using Veterans Affairs Administrative Data, Noah Ravenborg, Najeebah A. Bade, Dalia Abdelaziz Mobarek

GW Research Days 2016 - 2020

Identifying Venous Thromboembolism in Cancer Patients Using Veterans Affairs Administrative Data

Noah Ravenborg1, Najeebah A. Bade, M.D.2, Dalia Abdelaziz Mobarek, M.D.1, 2, 3

1 George Washington University School of Medicine and Health Sciences, Washington, D.C. 2 Department of Medicine, Section of Hematology, Veterans Affairs Medical Center, Washington, D.C., 3 Department of Medicine, Section of Hematology & Medical Oncology, George Washington University Medical Center, Washington, D.C. Noah Ravenborg Cell phone: (310)-804-0848, Email: nravenborg@gwu.edu, MS2

IMPORTANCE: The validity of administrative data in identifying diagnoses within the Veterans Affairs (VA) database, including viral hepatitis, cirrhosis, H. pylori, and cancer metastasis has been reported. …