All public logs
Jump to navigation
Jump to search
Combined display of all available logs of HIVE Lab. You can narrow down the view by selecting a log type, the username (case-sensitive), or the affected page (also case-sensitive).
- 18:38, 28 August 2025 Lorikrammer talk contribs created page Model Training and Validation (Created page with "The initial cohort of models submitted along with the initial release of the PredictMod platform were built using a wide variety of techniques for handling every stage, from data ingestion through modeling. Such techniques included: K-nearest neighbors, Synthetic Neighbor Oversampling Technique (SMOTE), and Leave-One-Out-Cross-Validation (LOOCV) (for data sampling and harmonization); conditional Generative Adversarial Networks (cGANs), SMOTE, multivariate kernel density...") Tag: Visual edit
- 18:23, 28 August 2025 Lorikrammer talk contribs created page Augmenting real data with synthetic data (Created page with "In biomedical research, small sample sizes often pose challenges for developing robust machine learning models and evaluating computational scalability. To overcome this limitation, we have designed an algorithm that utilizes conditional Generative Adversarial Networks (cGANs) to generate synthetic data, effectively expanding available datasets. While synthetic data may not always improve model accuracy, it provides researchers with the ability to assess computational ef...") Tag: Visual edit
- 18:09, 28 August 2025 Lorikrammer talk contribs created page File:Automated Pipeline Screenshot.png
- 18:09, 28 August 2025 Lorikrammer talk contribs uploaded File:Automated Pipeline Screenshot.png
- 18:04, 28 August 2025 Lorikrammer talk contribs created page File:Model visualization screenshot.png
- 18:04, 28 August 2025 Lorikrammer talk contribs uploaded File:Model visualization screenshot.png
- 17:55, 28 August 2025 Lorikrammer talk contribs created page File:Login screenshot.png
- 17:54, 28 August 2025 Lorikrammer talk contribs uploaded File:Login screenshot.png
- 17:52, 28 August 2025 Lorikrammer talk contribs created page File:Image.png
- 17:52, 28 August 2025 Lorikrammer talk contribs uploaded File:Image.png
- 11:56, 22 April 2025 Lorikrammer talk contribs uploaded a new version of File:GW-FEAST Dataset Overview.png
- 19:40, 16 April 2025 Lorikrammer talk contribs created page AI-READI Dataset Overview (Created page with "The '''AI-READI dataset''' is a comprehensive collection of data aimed at advancing research on '''Type 2 Diabetes Mellitus (T2DM)''' and its progression. This dataset plays a pivotal role in understanding the dynamics of T2DM by integrating clinical, behavioral, environmental, and wearable data sources to enable cutting-edge research in machine learning, AI, and healthcare. The project seeks to not only predict the onset and progression of T2DM but also explore the tran...") Tag: Visual edit
- 17:39, 16 April 2025 Lorikrammer talk contribs created page PredictMod Automated Pipeline (Created page with "← <small>Go Back to the PredictMod Home Page.</small> == Overview == We have created an [https://hivelab.biochemistry.gwu.edu/predictmod/automated-pipeline automated model training pipeline] for researchers who have a significant collection of data without the programming expertise required to create and train such models. Such researchers may use this automated pipeline to directly upload data. Upon upload of training data, the PredictMod platform pe...") Tag: Visual edit
- 17:05, 16 April 2025 Lorikrammer talk contribs created page PredictMod BCOs (Created page with "← <small>Go Back to the PredictMod Home Page.</small> PredictMod utilizes [https://wiki.biocomputeobject.org/About BioCompute Objects (BCOs)] to ensure standardized documentation of machine learning pipelines. BioCompute Objects were created as an IEEE standard for standardizing and sharing computations and analyses. In PredictMod, BCOs are used to fully describe all details of a model, including the data set used for training and associated provenanc...") Tag: Visual edit
- 14:45, 11 April 2025 Lorikrammer talk contribs created page Database of Genotypes and Phenotypes (dbGaP) Data (Created page with "Content will be added shortly.") Tag: Visual edit
- 14:44, 11 April 2025 Lorikrammer talk contribs created page Synthea Data (Created page with "Content will be added shortly.") Tag: Visual edit
- 14:38, 11 April 2025 Lorikrammer talk contribs created page GW-FEAST Frequently Asked Questions (FAQ) (Created page with "Frequently asked questions (FAQs) for the GW-FEAST portal will be updated shortly.") Tag: Visual edit
- 15:48, 21 March 2025 Lorikrammer talk contribs uploaded a new version of File:GW-FEAST architecture.png
- 15:43, 21 March 2025 Lorikrammer talk contribs uploaded a new version of File:GW-FEAST architecture.png
- 18:45, 20 March 2025 Lorikrammer talk contribs uploaded a new version of File:GW-FEAST architecture.png
- 14:27, 20 March 2025 Lorikrammer talk contribs created page GWDC De-identification Tool (Created page with "← <small>Go Back to the GW-FEAST Home Page.</small> The High-performance Integrated Virtual Environment (HIVE) de-identification tool is used to de-identify all GW-FEAST data sources prior to harmonization. A process overview is detailed below (authored by Dr. Robel Kahsay, Mazumder Lab, Department of Biochemistry and Molecular Medicine, School of Medicine and Health Sciences, The George Washington University). == HIVE De-identification Tool Diagram == [...")
- 14:20, 20 March 2025 Lorikrammer talk contribs created page GW-FEAST Data De-identification (Created page with "← <small>Go Back to the GW-FEAST Home Page.</small> All GW-FEAST datasets housed within the secure data environment are de-identified. This process varies slightly between data sources and each data source has it's own versioned de-identification tool and protocol. Our implementation follows the ''Safe Harbor'' recommended deidentification protocol with modifications based on the ''Expert Determination'' method. == HIVE De-identification Tool == The High...") Tag: Visual edit
- 13:44, 20 March 2025 Lorikrammer talk contribs created page HIVE De-identification Tool (Created page with "The High-performance Integrated Virtual Environment (HIVE) de-identification tool is used to de-identify all GW-FEAST data sources prior to harmonization. A process overview is detailed below (authored by Dr. Robel Kahsay, Mazumder Lab, Department of Biochemistry and Molecular Medicine, School of Medicine and Health Sciences, The George Washington University). == De-identification of Tabular Data: A Process Overview == === Introduction === The need for de-identifying s...") Tag: Visual edit
- 20:19, 13 March 2025 Lorikrammer talk contribs created page GW-FEAST Data (Created page with "== Data Sources == The GW-FEAST Book of Data contains data types, access restrictions, and de-identification protocols for each data source of the GW-FEAST project. All datasets are comprehensively documented using BioCompute Objects (BCOs), an Institute for Electrical and Electronics Engineers (IEEE) standard currently in use at the United States (US) Food and Drug Administration. BCOs foster transparency and reproducibility in bioinformatics pipelines. All BCOs for the...") Tag: Visual edit: Switched
- 20:01, 13 March 2025 Lorikrammer talk contribs created page File:GW-FEAST architecture.png
- 20:01, 13 March 2025 Lorikrammer talk contribs uploaded File:GW-FEAST architecture.png
- 19:58, 13 March 2025 Lorikrammer talk contribs created page File:GW-FEAST Dataset Overview.png
- 19:58, 13 March 2025 Lorikrammer talk contribs uploaded File:GW-FEAST Dataset Overview.png
- 19:48, 13 March 2025 Lorikrammer talk contribs created page GW Data Commons (GWDC) Data (Created page with "== Introduction == The GW Data Commons (GWDC) data houses EMR data from GW Medical Faculty Associates (MFA) Caboodle Warehouse. It currently contains two prostate cancer datasets. Pending approval from the GW Institutional Review Board (IRB), it will house electronic medical records (EMR) data on multiple cancer types for 900,000+ MFA patients. == De-identification == Data have been thoroughly de-identified pursuant to the HIPAA Safe Harbor provision. == Dataset Inform...") Tag: Visual edit
- 19:40, 13 March 2025 Lorikrammer talk contribs uploaded a new version of File:Nbcc deidn tool v1.0.png
- 19:37, 13 March 2025 Lorikrammer talk contribs created page File:NBCC sample data.xlsx
- 19:37, 13 March 2025 Lorikrammer talk contribs uploaded File:NBCC sample data.xlsx
- 19:34, 13 March 2025 Lorikrammer talk contribs created page File:Nbcc schema.png
- 19:34, 13 March 2025 Lorikrammer talk contribs uploaded File:Nbcc schema.png
- 19:25, 13 March 2025 Lorikrammer talk contribs created page File:Nbcc deidn tool v1.0.png
- 19:25, 13 March 2025 Lorikrammer talk contribs uploaded File:Nbcc deidn tool v1.0.png
- 18:40, 13 March 2025 Lorikrammer talk contribs created page File:Nbcc deidn v1.0.jpg
- 18:40, 13 March 2025 Lorikrammer talk contribs uploaded File:Nbcc deidn v1.0.jpg
- 18:29, 13 March 2025 Lorikrammer talk contribs created page National Breast Cancer Coalition (NBCC) Data (Created page with "== Introduction == The National Breast Cancer Coalition (NBCC) data contains twelve terabytes of -omics data for 26,546 participants. This data contains a cohort of 575 breast cancer patients and 3,479 patient family members. The original data was collected through the DNA.Land project (<nowiki>PMID 29374253</nowiki>) and is currently housed on the GW-FEAST data browser. Access to this data is restricted and must be approved by NBCC on a case-by-case basis through the NB...") Tag: Visual edit
- 18:09, 13 March 2025 Lorikrammer talk contribs created page File:Gwdc sample data.xlsx
- 18:09, 13 March 2025 Lorikrammer talk contribs uploaded File:Gwdc sample data.xlsx
- 18:09, 13 March 2025 Lorikrammer talk contribs created page File:Nbcc sample data.xlsx
- 18:09, 13 March 2025 Lorikrammer talk contribs uploaded File:Nbcc sample data.xlsx
- 16:29, 13 March 2025 Lorikrammer talk contribs created page GW-FEAST De-identified Data Templates (Created page with "The following de-identified, single patient data templates are available for download.") Tag: Visual edit
- 20:28, 12 March 2025 Lorikrammer talk contribs created page File:AIME Poster.png
- 20:28, 12 March 2025 Lorikrammer talk contribs uploaded File:AIME Poster.png
- 20:21, 12 March 2025 Lorikrammer talk contribs created page PredictMod Publications & Multimedia (Created page with "<small> Go Back to the PredictMod Home Page. </small> == PredictMod Publications == * Krammer L, Aggarwal V, Bhuiyan U, McNeely P, Mazumder R. PredictMod: a machine learning-based platform for predicting and sharing intervention outcomes in patients. Poster presented at: 22nd International Conference on Artificial Intelligence in Medicine; July 9-12, 2024; Salt Lake City, Utah, USA. * Wu J, Singleton SS, Bhuiyan, Krammer L, Mazumder R. Multi-omics approa...") Tag: Visual edit: Switched
- 19:57, 12 March 2025 Lorikrammer talk contribs created page About PredictMod (Created page with "== About the PredictMod Project == PredictMod (https://hivelab.biochemistry.gwu.edu/predictmod) is an application designed to provide clinicians with a powerful decision making tool that enhances clinical understanding of patient-level data. Through the use of the open-source PredictMod platform, clinicians, patients, and researchers will access predictive ML models based on real-world data. The platform empowers users with limited experience in bioinformatics to leverag...") Tag: Visual edit
- 19:52, 12 March 2025 Lorikrammer talk contribs created page PredictMod Model Submission (Created page with "<small> Go Back to PredictMod Project. = Model submission guidelines = You've recently created a fantastic new AI/ML model. Congratulations! We will be happy to help you share it throughout the broader clinical practice and research communities. There are just a few more steps to follow before we get to that goal. == Required components == There are a few things we require in order to host any new models in our ecosystem. === 1. Dependencies. === We wil...") Tag: Visual edit
- 19:46, 12 March 2025 Lorikrammer talk contribs created page PredictMod ML Pipeline Tutorial (Created page with "<small> Go Back to PredictMod Project. </small><h1>Integration of a Machine Learning-based Approach for Predictive Clinical Decision-making using Python</h1> <h2>Summary</h2> <h3>Part I. Machine Learning Using Python</h3> <ol> <li>What is Python?</li> <li>Objectives</li> <li>Methodology of the Machine Learning Algorithms</li> <li>Software Installation</li> <li>Downloading the Input Files for Synthetic Da...") Tag: Visual edit: Switched