Dec
7
9:00 AM09:00

Informatics Workshop: Statistical Modeling & Machine Learning: Artificial Intelligence for Clinical Data Mining

  • GW Science & Engineering Hall, 7th floor room 7750 (map)
  • Google Calendar ICS

Statistical Modeling & Machine Learning:

Artificial Intelligence for Clinical Data Mining

with

Liz Workman, PhD, Eduardo Trujillo-Rivera, PhD &

Yijun Shao, PhD

This FREE, one-day workshop will introduce three methods of AI data analysis in a beginner-friendly environment through a mix of theory and hands-on practice.

You will get the basics on: Statistical Regression, Support Vector Machines and Deep Neural Networks.

* Seating is limited * RSVP early *

Please register at http://j.mp/2P789oP. 

Lunch will be provided!

We welcome Clinicians, Researchers and Graduate Students

A basic understanding of statistics and/or programming (any language) will be helpful (not required)

Attendees will need to bring a laptop

View Event →
ResearchMatch Training
Dec
5
1:00 PM13:00

ResearchMatch Training

  • GW, Science & Engineering Hall, Room 7750 (map)
  • Google Calendar ICS

ResearchMatch is an NIH-funded, national registry that brings together researchers and 130,000+ volunteers who are interested in learning more about research studies. Used nationally by over 6,000 researchers this novel platform has been helpful in recruiting research participants across many research areas, and has been particularly useful for research involving rare disease, surveys, and healthy volunteers.

You have free access to these tools through the CTSI-CN, and can use them for Feasibility or actual Recruitment. This training will give you the basics so you can be all set!

Register here: http://j.mp/2xQs2FY

View Event →
REDCap Training Session 102 (GW)
Dec
5
10:00 AM10:00

REDCap Training Session 102 (GW)

  • GW, Science & Engineering Hall, Room 7750 (map)
  • Google Calendar ICS

REDCap 102: Surveys, Longitudinal Studies & Applications

To register, please click on this link: https://cri-datacap.org/surveys/?s=HyPAG5m9YT

What is REDCap?

·         Research Electronic Data Capture (REDCap) is a web-based system for data collection that allows users to build and manage online surveys and databases quickly and securely.

·         Data entry operators or people taking online surveys enter data in any web browser, either locally or from remote locations.

Why REDCap?

 ·         Easy and intuitive to design, develop, and use data collection forms/screens

·         Screen layouts are clear and simply to navigate

·         REDCap provides audit trails for tracking the history of data entry and revision

·         REDCap permits downloads of data to Excel, PDF, SAS, Stata, R, and SPSS

·         Free use for members of the CTSI-CN or member institutions

View Event →
REDCap Training Session 101 (GW)
Dec
4
1:00 PM13:00

REDCap Training Session 101 (GW)

  • GW, Science & Engineering Hall, Room 7750 (map)
  • Google Calendar ICS

REDCap 101: Database Design

View Event →
Informatics Seminar Series (GW/Webex)
Dec
4
12:00 PM12:00

Informatics Seminar Series (GW/Webex)

  • Science & Engineering Hall, Conference Room 2000 (map)
  • Google Calendar ICS

Title: Relationship between acute and chronic kidney disease using VA national data

Presenter: Richard Amdur, PhD

Webex: https://bit.ly/2p6664I

JOIN US FOR A ROUND TABLE LUNCH FROM 1 TO 2PM!

Abstract: Until recently, it was thought that patients who survived an episode of acute kidney injury (AKI) and returned to a normal kidney functioning (as measured by serum creatinine) would have little or no chronic kidney problems as a result. By examining large longitudinal patient samples, we and other VA researchers showed that this was not the case. We developed and validated prediction models to identify AKI patients at high risk for progression to chronic kidney disease (CKD) and end-stage renal failure (ESRD). We also showed that episodes of AKI raised the risk of later cardiovascular disease events (MI, stroke, death). Finally, we proposed a method for measuring variability in kidney functioning that was mathematically independent of slope of CKD progression, and that was a powerful predictor of CKD progression, even in initially healthy patients. Overall, our work and that of other VA researcher over the past 10 years has helped to inform a new understanding of the complex inter-relationship between AKI and CKD.

 

View Event →
Informatics Seminar Series (GW/Webex)
Nov
13
12:00 PM12:00

Informatics Seminar Series (GW/Webex)

  • Science & Engineering Hall, Conference Room 2000 (map)
  • Google Calendar ICS

Title: Reconstruction of clone- and haplotype-specific cancer genomes karyotypes from tumor mixtures

Presenter: Sergey Aganezov, PhD, CBI

Webex: https://bit.ly/2xbnbOl

JOIN US FOR A ROUND TABLE LUNCH from 1 to 2pm!

Abstract: We introduce a novel method, Reconstructing Cancer Karotypes (RCK), for reconstructing one or more rearranged cancer genomes, or clones, that best explain the read alignments from a bulk tumor sample. RCK leverages specific evolutionary constraints on the somatic mutation process in cancer in order to reduce ambiguity in the deconvolution of admixed DNA sequence data into multiple haplotype-specific cancer clones. In particular, RCK relies on the infinite sites assumption that a genome rearrangement is highly unlikely to occur at the same nucleotide position more than once during somatic evolution. Earlier methods for analyzing cancer genome rearrangements (e.g.PREGO,Weaver,andReMixT) rely on weaker forms on the infinite sites assumption that do not account for the diploid nature of the human genome and the presence of multiple clones within a tumor. As a result, we show that these other methods can yield highly improbable reconstructions.

 

View Event →
Workshop: Rapid Biomedical Knowledge Base Construction from Text
Nov
6
to Nov 7

Workshop: Rapid Biomedical Knowledge Base Construction from Text

  • Stanford University, Stanford, CA (map)
  • Google Calendar ICS

Do you want to automatically identify biomarkers reported within the scientific literature that are related to a particular disease?

Do you have a large collection of text-based documents (e.g., articles, webpages, reports, catalogs) from which you want to create a database of experimentally derived parameters, like P53 concentration levels or tissue stiffness?

Do you want to analyze clinical notes to extract patient-reported functional capabilities related to a given treatment?

The Mobilize Center, an NIH Big Data to Knowledge Center of Excellence, invites you to participate in our upcoming workshop on rapidly creating biomedical knowledge bases from unstructured data. You will learn how to use a tool called Snorkel to automatically extract information from data sources, such as the scientific literature and clinical notes.

DETAILS
 
When:   November 6-7, 2018
Where:  Stanford University, Stanford, CA
Registration: The workshop is free to attend, but registration is required and space is limited. 
Travel Awards: Travel awards are available. Please visit the workshop webpage for more information. 
Deadline for Applications:  Friday, September 21st, 2018
 
DESCRIPTION

Over 80% of the data available in the world today is currently unreadable by computers. These “dark data” are unstructured and include a wide range of invaluable information sources, from the text of scientific articles to the notes written by your doctor. Transforming these data into a form readable by machines is called knowledge base construction and is a vital process for unlocking the potential found in these resources.
 
Current approaches for automatically building knowledge bases require large, labeled datasets for training. These gold standard datasets are difficult to come by, particularly in biomedicine, limiting our ability to create new knowledge bases that can be analyzed.
 
Snorkel was created in response to this challenge. Developed in Christopher Re’s lab at Stanford University, Snorkel constructs knowledge bases from “dark data.” And unlike other approaches, which require precisely labeled data to train and build the models, Snorkel can work with just a set of user-input rules. 

On the first day, participants will learn about the Snorkel workflow through brief lectures and hands-on activities. On the second day, participants will utilize their new knowledge to apply Snorkel to a real-world problem using the scientific literature or electronic health record data.

INTENDED AUDIENCE

This workshop is designed for individuals who are interested in applying state-of-the-art machine reading approaches to extracting information from the text and tables of documents. You do not need to know anything about machine reading or machine learning, but you should have some basic Python programming skills.

To learn more and apply, visit http://mobilize.stanford.edu/events/snorkelworkshop2018/
 
Application deadline:  Friday, September 21st, 2018

View Event →
MEEGID XIV: 14th International Conference on Molecular Epidemiology and Evolutionary Genetics of Infectious Diseases
Nov
6
to Nov 9

MEEGID XIV: 14th International Conference on Molecular Epidemiology and Evolutionary Genetics of Infectious Diseases

  • Google Calendar ICS

Upcoming MEEGID XIV: 14th International Conference on Molecular Epidemiology and Evolutionary Genetics of Infectious Diseases. Our very own Dr. Keith Crandall will be speaking about "Computational approaches to microbiome characterization and infectious disease dynamics" at the conference!

Dates: 6-9 November 2018

Location: Sitges, Spain

Register: www.elsevier.com/meegid-conference/

View Event →
Georgetown ICBI 7th Annual Big Data in Biomedicine Symposium
Oct
26
9:00 AM09:00

Georgetown ICBI 7th Annual Big Data in Biomedicine Symposium

  • Google Calendar ICS

Register Today for the Georgetown ICBI 7th Annual Big Data in Biomedicine Symposium! 

Spaces are filling up fast!  Register Today!

Click Here to Register

Georgetown ICBI 7th Annual Big Data in Biomedicine Symposium: Health Data Science & Informatics

Friday October 26th 2018

Spotlight speakers:

Melissa Haendel, PhD

Neal Meropol, MD

The ICBI's 7th Annual Big Data in Biomedicine Symposium will be held on Friday, October 26, 2018 at the Georgetown University Conference Center.

This one-day event will include talks by academic, industry, and government leaders in clinical and translational sciences who will highlight technologies, applications of informatics science and tools to advance precision medicine.

Dr. Melissa Haendel, Director of Translational Data Science, Oregon Health & Science University & Dr. Neal Meropol, Vice President of Research Oncology at Flatiron Health will be this year's spotlight speakers. Planned sessions include:Rise of the Digital Citizen Real World Evidence and Clinical OutcomesNext Generation Data CommonsEducating the Next Generation of Health Data ScientistsPoster SessionSpecial Networking SessionThe Symposium is free for academic and government participants and will showcase exciting advances in the areas of health data analytics, informatics and related state-of-the-art technologies, and will bring together a dynamic community of innovators, research scientists, clinicians, program managers, educators, and students to exchange ideas and learn new methodologies. 

The event also offers an opportunity to network with colleagues during the evening reception and compete for the best poster award
*** ABSTRACT DEADLINE EXTENDED TO OCTOBER 12, 2018 *** For more information about the Symposium
CLICK HERE

View Event →
Genomics Core Open House
Oct
22
8:00 AM08:00

Genomics Core Open House

  • GW Science & Engineering Hall (map)
  • Google Calendar ICS

Please join us for the launch of our Genomics Core in the GW Milken Institute School of Public Health! The program will include:

8:00am   - Breakfast Reception
8:30am   - Ribbon Cutting Celebration 
9:00am   - Guided Tours of the Genomics Lab
10:00am - Keynote address by Illumina: "Multi-omics approaches – utilizing NGS for DNA, expression and epigenetics studies"

A grab-and-go lunch will be provided, and ample opportunity for networking!

Please register using this link: http://connect.gwu.edu/site/Calendar?id=116354&view=RSVP

Visit our Genomics Core website: https://www.gwgenomics.org

View Event →
ResearchMatch Training
Oct
10
1:00 PM13:00

ResearchMatch Training

  • GW, Science & Engineering Hall, Room 7750 (map)
  • Google Calendar ICS

ResearchMatch is an NIH-funded, national registry that brings together researchers and 130,000+ volunteers who are interested in learning more about research studies. Used nationally by over 6,000 researchers this novel platform has been helpful in recruiting research participants across many research areas, and has been particularly useful for research involving rare disease, surveys, and healthy volunteers.

You have free access to this tool through the CTSI-CN, and can use it for Feasibility or actual Recruitment. This training will give you the basics so you can be all set!

Register here: https://cri-datacap.org/surveys/?s=NYTL8AAPX9

View Event →
REDCap Training Session 102 (GW)
Oct
10
10:00 AM10:00

REDCap Training Session 102 (GW)

  • GW, Science & Engineering Hall, Room 7750 (map)
  • Google Calendar ICS

REDCap 102: Surveys, Longitudinal Studies & Applications

To register, please click on this link: https://cri-datacap.org/surveys/?s=HyPAG5m9YT

What is REDCap?

·         Research Electronic Data Capture (REDCap) is a web-based system for data collection that allows users to build and manage online surveys and databases quickly and securely.

·         Data entry operators or people taking online surveys enter data in any web browser, either locally or from remote locations.

Why REDCap?

 ·         Easy and intuitive to design, develop, and use data collection forms/screens

·         Screen layouts are clear and simply to navigate

·         REDCap provides audit trails for tracking the history of data entry and revision

·         REDCap permits downloads of data to Excel, PDF, SAS, Stata, R, and SPSS

·         Free use for members of the CTSI-CN or member institutions

View Event →
REDCap Training Session 101 (GW)
Oct
9
1:00 PM13:00

REDCap Training Session 101 (GW)

  • GW, Science & Engineering Hall, Room 7750 (map)
  • Google Calendar ICS

REDCap 101: Database Design

View Event →
Oct
3
12:00 PM12:00

Science Webinar Series

  • Google Calendar ICS

New complimentary webinar from Science:

Driving precision medicine through biostatistics: Translating multiomics biomarker data into breakthrough knowledge

You are invited to hear our panel of experts on October 3, 2018, in this live, online educational seminar. For more information and complimentary registration visit: webinar.sciencemag.org

Date: Wednesday, October 3, 2018
Time: 12 noon Eastern, 9 a.m. Pacific, 5 p.m. UK, 6 p.m. Central Europe
Duration: 1 hour

About This Webinar 

In order to provide better treatment for patients and more effective, targeted drugs, it is vital to understand disease mechanisms and to identify informative markers for patient susceptibility, disease progression, treatment response, and individual drug tolerance. The move to more stratified medicine is a key paradigm for global health care, but also an enormous challenge for biologists and data scientists. Technological developments are enabling larger studies that can rapidly deliver huge quantities of data—their translation into meaningful, actionable biological understanding is essential, but often difficult. Genomics and proteomics are increasingly combined to characterize the role of specific biomarkers in disease, uncover novel biological pathways, provide rationales for drug target selection, and develop new, more efficacious therapies. These large-scale, multiomics studies generate complex datasets that highlight an important example of the big-data problem. At the same time, the credibility of scientific research is facing challenges from the so-called “replication crisis,” raising questions about how we judge the significance of the data we obtain. Thus, biostatisticians play an increasingly critical role in interpreting and quality-assuring the outcome of such studies, throughout the process of biomarker discovery, validation, clinical implementation, and drug development. Our panelists will share their experiences in applying biostatistics to large datasets in order to facilitate more confident development of novel therapeutics, and to drive precision medicine.  

During the webinar, the speakers will:

• Describe their biostatistical approaches to analyzing large, complex datasets
• Illustrate how biostatistical analysis can translate complex data into biological insights
• Discuss how biomarkers can be leveraged to identify unique underlying biological mechanisms and personalize patient treatment
• Answer your questions during the live broadcast!


Participants:

Eric Fauman, Ph.D.
Pfizer
Cambridge, MA

Jasper Tromp, M.D., Ph.D.
University Medical Centre Groningen
Groningen, Netherlands

Register at:
webinar.sciencemag.org

Questions? E-mail: . 

Produced by the Science/AAAS Custom Publishing Office and sponsored by Olink Proteomics.

View Event →
Informatics Seminar Series (GW/Webex)
Oct
2
12:00 PM12:00

Informatics Seminar Series (GW/Webex)

  • Science & Engineering Hall, Conference Room 2000 (map)
  • Google Calendar ICS

Title: Helping the Public Evaluate Health Information Credibility in the Era of “Fake Health News”

Presenter: Alla Keselman, PhD

Webex: https://bit.ly/2p6cFoc

Abstract: With the emergence of new Web media platforms and the ubiquity of social media, critical evaluation of online health information has taken on a new dimension and urgency. At the same time, many established information quality evaluation guidelines address information characteristics other than the content (e.g., authority, currency) and do not address information presented via novel Web technologies. This talk will describe a research program that develops a methodological approach for analyzing diverse online health information sources. It will also present a window into the universe of non-evidence-based online health information, particularly as it pertains to the possibility of curing type 2 diabetes. The presentation will use the above evaluation criteria to describe how these sites portray complexity of type 2 diabetes, characterize healthcare establishment, use language and emotional cues, discuss medical research, and convey certainty. It will also address the potential role of technology in supporting users in the changing digital health ecosystem.

 

View Event →
Sep
26
11:00 AM11:00

Docker Webinar for the Public Sector: Containers in Production - What's Driving Enterprise Adoption of the Container Platform

  • Google Calendar ICS

Containers in Production - What's Driving Enterprise Adoption of the Container Platform

Date: Wednesday, September 26th

Time: 11 AM PDT / 2 PM EDT

Guest speaker from IDC Research, Gary Chen, will discuss why organizations are turning to container platforms to support increasingly diverse IT environments, bolster security and governance, and jumpstart their digital transformation initiatives.   Register for this webinar  and hear Gary discuss the container adoption trends from IDC's Container Infrastructure Survey.

View Event →
Sep
19
11:00 AM11:00

Docker Security for the Public Sector

  • Google Calendar ICS

Docker Security for the Public Sector

Date: Thursday, September 19th

Time: 11 AM PDT / 2 PM EDT

If you’re a CISO, ISSO, or a security professional itching to learn more about the benefits containers provide for your agency’s or program’s security posture, than this webinar is for you! Register for this webinar for a primer about how Docker provides a secure container platform and software lifecycle management for all your applications and how Docker can help your agency satisfy FISMA and other regulatory requirements. 

View Event →
REDCap Training Session 102 (CNMC)
Sep
18
2:00 PM14:00

REDCap Training Session 102 (CNMC)

  • CNMC, Technology Training Room 1 on P2 level (map)
  • Google Calendar ICS

REDCap 102: Surveys, Longitudinal Studies & Applications

To register, please click on this link: https://cri-datacap.org/surveys/?s=HyPAG5m9YT

What is REDCap?

·         Research Electronic Data Capture (REDCap) is a web-based system for data collection that allows users to build and manage online surveys and databases quickly and securely.

·         Data entry operators or people taking online surveys enter data in any web browser, either locally or from remote locations.

Why REDCap?

 ·         Easy and intuitive to design, develop, and use data collection forms/screens

·         Screen layouts are clear and simply to navigate

·         REDCap provides audit trails for tracking the history of data entry and revision

·         REDCap permits downloads of data to Excel, PDF, SAS, Stata, R, and SPSS

·         Free use for members of the CTSI-CN or member institutions

View Event →
REDCap Training Session 101 (CNMC)
Sep
11
2:00 PM14:00

REDCap Training Session 101 (CNMC)

  • CNMC, Technology Training Room 1 on P2 level (map)
  • Google Calendar ICS

REDCap 101: Database Design

View Event →
Informatics Seminar Series (GW/Webex)
Sep
4
12:00 PM12:00

Informatics Seminar Series (GW/Webex)

  • Science & Engineering Hall, Conference Room 2000 (map)
  • Google Calendar ICS

Title: An End-to-End Deep Learning Architecture for Extracting Protein-Protein Interactions Affected by Genetic Mutations

Presenter: Tung Tran, PhD candidate

Webex: https://bit.ly/2w1WMTl

Abstract: As part of the BioCreative VI Track IV we built a supervised relation extraction model capable of taking a test article and returning a list of interacting protein pairs identified by their Entrez Gene IDs. Such pairs represent proteins participating in a binary protein-protein interaction (PPI) relation where the interaction is additionally affected by a genetic mutation (PPIm). In this study, we explored a PPIm relation extraction by deploying a three-component pipeline involving deep learning-based named entity recognition and relation classification models along with a knowledge-based approach for gene normalization. We propose several recall-focused improvements to our original challenge entry which placed 2nd in the competition. On exact matching, the new system achieved test results of 37.78% micro-F1 with a precision of 38.22% and recall of 37.34% which corresponds to an improvement by approximately 3 micro-F1 points. When matching on HomoloGene IDs, we report similarly competitive test results at 46.17% micro-F1 with a precision and recall of 46.67% and 45.59%, corresponding to an improvement of more than 8 micro-F1 points over the prior best result.

 

View Event →
REDCap Training Session 102 (GW)
Aug
22
11:00 AM11:00

REDCap Training Session 102 (GW)

  • GW, Science & Engineering Hall, Room 7750 (map)
  • Google Calendar ICS

REDCap 102: Surveys, Longitudinal Studies & Applications

To register, please click on this link: https://cri-datacap.org/surveys/?s=HyPAG5m9YT

What is REDCap?

·         Research Electronic Data Capture (REDCap) is a web-based system for data collection that allows users to build and manage online surveys and databases quickly and securely.

·         Data entry operators or people taking online surveys enter data in any web browser, either locally or from remote locations.

Why REDCap?

 ·         Easy and intuitive to design, develop, and use data collection forms/screens

·         Screen layouts are clear and simply to navigate

·         REDCap provides audit trails for tracking the history of data entry and revision

·         REDCap permits downloads of data to Excel, PDF, SAS, Stata, R, and SPSS

·         Free use for members of the CTSI-CN or member institutions

View Event →
Informatics Seminar Series (GW/Webex)
Aug
21
12:00 PM12:00

Informatics Seminar Series (GW/Webex)

  • Milken Institute School of Public Health, Conference Room 201 (map)
  • Google Calendar ICS

Title: Characterization of Critically Ill Patients: A Clinical Application of the Health Facts Data Set

Presenter: Anita K. Patel, MD, & Eduardo Trujillo-Rivera, PhD

Webex: https://bit.ly/2Mgugrz

Abstract: Using the Health Facts EMR data, critically ill pediatric patients that had at least one admission to the Intensive Care Unit (ICU) were characterized in terms of the number of hours they were administered with drugs usually administrated when either intubated or in mechanical ventilation. The study analyzed the vectors containing the number of hours each combination of medicines was administered to each patient during different periods of ICU admission and floor admission, using a class of Bayesian regression models with the Dirichlet-Multinomial distribution for the response and random effects to capture the inherent variability of each encounter and hospital, adjusting for demographic information. During this seminar, we will describe the process of cohort and records selection, the model and the interpretation of the parameters, and the results of the characterization. We will also explain how the model can be used for treatment comparisons for similar patients in different hospitals.

 

View Event →
REDCap Training Session 101 (GW)
Aug
21
11:00 AM11:00

REDCap Training Session 101 (GW)

  • GW, Science & Engineering Hall, Room 7750 (map)
  • Google Calendar ICS

REDCap 101: Database Design

View Event →
REDCap Training Session 102 (CNMC)
Jul
26
1:00 PM13:00

REDCap Training Session 102 (CNMC)

  • CNMC, Technology Training Room 1 on P2 level (map)
  • Google Calendar ICS

REDCap 102: Surveys, Longitudinal Studies & Applications

To register, please click on this link: https://cri-datacap.org/surveys/?s=HyPAG5m9YT

What is REDCap?

·         Research Electronic Data Capture (REDCap) is a web-based system for data collection that allows users to build and manage online surveys and databases quickly and securely.

·         Data entry operators or people taking online surveys enter data in any web browser, either locally or from remote locations.

Why REDCap?

 ·         Easy and intuitive to design, develop, and use data collection forms/screens

·         Screen layouts are clear and simply to navigate

·         REDCap provides audit trails for tracking the history of data entry and revision

·         REDCap permits downloads of data to Excel, PDF, SAS, Stata, R, and SPSS

·         Free use for members of the CTSI-CN or member institutions

View Event →
REDCap Training Session 101 (CNMC)
Jul
25
1:00 PM13:00

REDCap Training Session 101 (CNMC)

  • CNMC, Technology Training Room 1 on P2 level (map)
  • Google Calendar ICS

REDCap 101: Database Design

View Event →
REDCap Training Session 102 (GW)
Jul
11
11:00 AM11:00

REDCap Training Session 102 (GW)

  • GW, Science & Engineering Hall, Room 7750 (map)
  • Google Calendar ICS

REDCap 102: Surveys, Longitudinal Studies & Applications

To register, please click on this link: https://cri-datacap.org/surveys/?s=HyPAG5m9YT

What is REDCap?

·         Research Electronic Data Capture (REDCap) is a web-based system for data collection that allows users to build and manage online surveys and databases quickly and securely.

·         Data entry operators or people taking online surveys enter data in any web browser, either locally or from remote locations.

Why REDCap?

 ·         Easy and intuitive to design, develop, and use data collection forms/screens

·         Screen layouts are clear and simply to navigate

·         REDCap provides audit trails for tracking the history of data entry and revision

·         REDCap permits downloads of data to Excel, PDF, SAS, Stata, R, and SPSS

·         Free use for members of the CTSI-CN or member institutions

View Event →
Informatics Seminar Series (GW/Webex)
Jul
10
12:00 PM12:00

Informatics Seminar Series (GW/Webex)

  • Milken Institute School of Public Health, Conference Room 201 (map)
  • Google Calendar ICS

Title: Clinical Outcome Prediction through Deep Learning

Presenter: Yijun Shao, PhD

Webex: https://bit.ly/2KUKX6T

Abstract: Accurately predicting clinical outcomes in advance can benefit both healthcare providers and patients, though it remains a challenging task. Artificial Intelligence (AI) has recently generated much excitement due to the breakthroughs made by Deep Neural Networks (DNNs) on many tasks such as image classification and speech recognition. Inspired by those developments, there has been great interest in applying DNNs to the biomedical domain. In this seminar, I will present a DNN-based predictive modeling approach applied to two clinical use cases. DNN models are usually considered as black boxes which would hinder their acceptance by clinicians. Therefore, we also developed a novel method for explaining the predictions of our DNN models.

 

View Event →
REDCap Training Session 101 (GW)
Jul
10
11:00 AM11:00

REDCap Training Session 101 (GW)

  • GW, Science & Engineering Hall, Room 7750 (map)
  • Google Calendar ICS

REDCap 101: Database Design

View Event →
REDCap Training Session 102 (GW)
Jun
6
11:00 AM11:00

REDCap Training Session 102 (GW)

  • GW, Science & Engineering Hall, Room 7750 (map)
  • Google Calendar ICS

REDCap 102: Surveys, Longitudinal Studies & Applications

To register, please click on this link: https://cri-datacap.org/surveys/?s=HyPAG5m9YT

What is REDCap?

·         Research Electronic Data Capture (REDCap) is a web-based system for data collection that allows users to build and manage online surveys and databases quickly and securely.

·         Data entry operators or people taking online surveys enter data in any web browser, either locally or from remote locations.

Why REDCap?

 ·         Easy and intuitive to design, develop, and use data collection forms/screens

·         Screen layouts are clear and simply to navigate

·         REDCap provides audit trails for tracking the history of data entry and revision

·         REDCap permits downloads of data to Excel, PDF, SAS, Stata, R, and SPSS

·         Free use for members of the CTSI-CN or member institutions

View Event →
Informatics Seminar Series (GW/Webex)
Jun
5
12:00 PM12:00

Informatics Seminar Series (GW/Webex)

  • Science & Engineering Hall, room 2000 (map)
  • Google Calendar ICS

Title: The FABRIC environment: Architectural features and Big Data Analytics

Presenter: Don DuRousseau, Director of Research Technology, GW

Webex: https://bit.ly/2sjA5bu

Abstract: The Flexible Architecture for Building Research Informatics Collaborations (FABRIC) is an informatics platform (in development) which offers a service oriented research toolbox that investigators, clinicians, and patient advocates can use to easily access a wide array of data repositories integrated with customizable query tools. This cloud environment is able to support the rapid formation of dedicated cross-domain research teams, the sharing of raw and de-identified datasets in secured enclaves, and the access to a suite of advanced analytics tools commonly used throughout clinical translational research (CTR). This seminar will focus on some of the architectural features of FABRIC, its connection to the Colonial One HPC cluster, and the integration of the HealthFacts database. 

 

View Event →