Call Girls Whitefield Just Call 7001305949 Top Class Call Girl Service Available
2013 dec bgu_israel_luciano_dec_22
1. Semantic eHealth:
Getting more out of biomedical data using
Semantic Technology
Instructors:
Joanne S. Luciano, PhD
Rensselaer Polytechnic Institute, University of California, Irvine, USA
Eitan Rubin, PhD
Ben-Gurion University
December 22-25, 2013
Ben-Gurion University of the Negev, Israel
1
2. Instructor
Interests
Understand the role genetics plays in
the development of diseases
Novel methods for disease
stratification using genetic analysis
as predictors of treatment outcomes.
Research
Improved methods for computational
target prioritization in genetic
association studies
Lecturer,
Department of Microbiology and
Immunology
Faculty of Health Sciences
An end-user programming language
for biologists
Email: erubin@bgu.ac.il
2
3. Instructor
Interests
Use and Develop Technology.
Infrastructure and Analytics to
Advance Science and Increase its
Utility to Improve Health Outcomes
BioPAX, TMO, InfluenzO
Research
Joanne S. Luciano
Deputy Director
Web Science Research Center
Email: jluciano@uci.edu
General Framework for Ontology
Evaluation
Systems Biology and Medicine Major Depressive Disorder (MDD)
Medicine, Health, Wellbeing
3
4. Timeline
(earlier work: 10 years in Software Research & Development and Product Development)
World Congress on
Neural Networks,
July 11-15, 1993,
Portland, Oregon
SIG
Mental Function
and
Dysfunction
Sam Levin
Thesis Proposal
Approved
1995
PhD
US Patents
No. 6,063,028
Awarded
Patents Offered
at Ocean Tomo
Auction
Chicago, IL
BioPAX EMPWR
1997
U Pitt
Greg Siegle
Collaboration
Patents Sold
to Advanced
Biological
Laboratories
Belgium
Center for
Multidisciplinary
Yuezhang Research
Xiao
and
Master’s
Depression
Thesis
(RPI) Treatment
Selection
2001 2006
2008 2009 2010 2011 2012
1996
1993 1994
2000
Jackie Samson,
Linked Data
Mc Lean
W3C HCLS
Poster
2013
Hospital
Brendan Ashby
BioDASH
Presented
Depression
Rensselaer Master’sThesis
EPOS
ISMB 1997
Research
(RPI)
(RPI)
PSB
Workshop Neural Modeling 1998 US Patent No.
6,317,73
of Cognitive and Brain
Awarded
Disorders
4
?
13. Research Goals
Properly diagnose and properly
match patient with the best individualized
treatment option available, including
non-drug treatments
Illuminate recovery
course
(personalized)
13
13
38. Data, Not Programs
Data Dictionaries:
Without a data
dictionary, a
database
management
system [or any
program] cannot
access data from
the database.”1
Duh!
38
1. Webopedia. “Data Dictionary.” Available online at www.webopedia.com/TERM/d/data_dictionary.html.
38
39. Data, Not Programs
Data Dictionaries:
Without a data
dictionary, a
database
management
system [or any
program] cannot
access data from
the database.”1
Duh!
39
1. Webopedia. “Data Dictionary.” Available online at www.webopedia.com/TERM/d/data_dictionary.html.
39
Semantic eHealth: getting more out of biomedical data using Semantic Technology
Short Course — Offered 22-25 December 2013
http://tw.rpi.edu/web/event/SemanticEHealth
Joanne S. Luciano, PhD
Rensselaer Polytechnic Institute
Eitan Rubin, PhD
FOHS, Ben-Gurion University of the Negev
Description
In this course we will introduce a set of advanced tools that can be used to integrate bio-medical data and use it to answer clinical questions. The course introduces the new field of data science, with an emphasis on how it relates to biomedical research. It provides the knowledge of the standards and best practices that enable integration across the web and data mining at web scale.
Students will learn how to build computer-based applications that can automatically integrate bio-medical data and how they can be used to ask and answer questions. Using datasets that can be found freely on the web or data generated in the lab, we will show how to convert them to formats that enable easy integration, and how to use semantic technology to describe how the data are related to enable automatic integration and visualization of the data.
In addition, we will (1) introduce the CRISP-DM process of knowledge mining and the Semantic Web Development Methodology; (2) explain the problems of data integration from three aspects, i.e. technically, ontologically, and domain specific, (3) we will demonstrate how each of these data integration problems can be approached; and (4) we will help student realize how to utilize knowledge mining in their own research.
Credit
Graduate students will receive 1 credit point for the course. Grading will be on a pass/fail basis only.
Course Outline (preliminary!)
Sunday, June 14
22/12/2013, 11:15-14:00, Building M8, room 08
23/12/2013, 14:15-17:00, Building M8, room 08
25/12/2013, 09:15-12:00, Building M8, room 002
(Three more 2-h lectures will be announced in the coming weeks)
Prerequisites
Prior knowledge of programming is NOT required.
Intended Audience
The course should be appropriate for M.Sc student and above.
To register and for additional details, please contact Eitan Rubin
IF YOU ARE REGISTERING, PLEASE USE THE FOLLOWING AT THE TITLE OF YOUR EMAIL: Registration -Semantic eHealth
---
I became aware of the difficulties of conducting multidisciplinary research. In particular, its huge negative impact on health care.
At that time, it was easy to recognize how data in the form of images, such as PET scans and fMRIs contributed to our knowledge and understanding, but it was not so obvious how data and modeling also contributed the same, if not more.
At the Tetherless world and in my role as the Deputy Director of the Web Science Research Center, I continue to explore these issues and to hopefully discover solutions.
---
BioPathways played a leading role in the creation of BioPAX-
BioPAX first sem web application in life scinces which formed part of basis for the arguremt to create a hcls group.
BioPathways Consortium
Co-organize
BioPAX
Co-founded – Obtained initial funding from DoE, and 2nd year to fund workshop
W3C
Semantic Web for Health Care and Life Sciences
Helped create
BioRDF – move bio-clinical data to RDF / DEMO
Organization of workshops, Journal special issue
BioDASH Demo – Highlighted by TBL BioIT May 2005
Siderean Demo – Highlighted by TBL –ISWC Oct 2005
OWL-WG, Infectious Disease Ontology
Participate – lead collaboration on Influezna Ontology to support research and surveillance
BioPAX
Pathway means different things to different people
Signaling pathway
Metabolic pathway
Gene regulatory pathway
An ontology to support integration and exchange of biological pathway data of different types (and formats)
bridge the gap between basic and clinical sciences, to ensure that basic research discoveries of potential relevance to patient care are effectively applied
Translational medicine aims broadly at the rapid transformation of laboratory findings into clinically focused applications – ‘from bench to bedside and back’. There has long been a consensus that there is a pressing need to bridge the gap between basic and clinical sciences, to ensure that basic research discoveries of potential relevance to patient care are effectively applied. This is a formidable challenge to implement and some of the key problems stem from the lack of appropriate frameworks and models that link clinically relevant information (in particular that related to multi-scale pathways and networks) to the knowledge obtained across multiple disciplines, experimental platforms and biological systems.
Bedside graphic: http://www.blogthecoast.com/rainbow/3980%20hospital%20room.jpg
Mental Disorders in America from: http://www.nimh.nih.gov/health/publications/the-numbers-count-mental-disorders-in-america/index.shtml
Mental disorders are common in the United States and internationally. An estimated 26.2 percent of Americans ages 18 and older — about one in four adults — suffer from a diagnosable mental disorder in a given year.1 When applied to the 2004 U.S. Census residential population estimate for ages 18 and older, this figure translates to 57.7 million people.2Even though mental disorders are widespread in the population, the main burden of illness is concentrated in a much smaller proportion — about 6 percent, or 1 in 17 — who suffer from a serious mental illness.1 In addition, mental disorders are the leading cause of disability in the U.S. and Canada for ages 15-44.3 Many people suffer from more than one mental disorder at a given time. Nearly half (45 percent) of those with any mental disorder meet criteria for 2 or more disorders, with severity strongly related to comorbidity.1
In the U.S., mental disorders are diagnosed based on the Diagnostic and Statistical Manual of Mental Disorders, fourth edition (DSM-IV).4
Mood Disorders
Mood disorders include major depressive disorder, dysthymic disorder, and bipolar disorder.
* Approximately 20.9 million American adults, or about 9.5 percent of the U.S. population age 18 and older in a given year, have a mood disorder.1
* The median age of onset for mood disorders is 30 years.5
* Depressive disorders often co-occur with anxiety disorders and substance abuse.5
Major Depressive Disorder
* Major Depressive Disorder is the leading cause of disability in the U.S. for ages 15-44.3
* Major depressive disorder affects approximately 14.8 million American adults, or about 6.7 percent of the U.S. population age 18 and older in a given year.1
* While major depressive disorder can develop at any age, the median age at onset is 32.5
* Major depressive disorder is more prevalent in women than in men.6
References
1. Kessler RC, Chiu WT, Demler O, Walters EE. Prevalence, severity, and comorbidity of twelve-month DSM-IV disorders in the National Comorbidity Survey Replication (NCS-R). Archives of General Psychiatry, 2005 Jun;62(6):617-27.
2. U.S. Census Bureau Population Estimates by Demographic Characteristics. Table 2: Annual Estimates of the Population by Selected Age Groups and Sex for the United States: April 1, 2000 to July 1, 2004 (NC-EST2004-02) Source: Population Division, U.S. Census Bureau Release Date: June 9, 2005. http://www.census.gov/popest/national/asrh/
3. The World Health Organization. The World Health Report 2004: Changing History, Annex Table 3: Burden of disease in DALYs by cause, sex, and mortality stratum in WHO regions, estimates for 2002. Geneva: WHO, 2004.
4. American Psychiatric Association. Diagnostic and Statistical Manual on Mental Disorders, fourth edition (DSM-IV). Washington, DC: American Psychiatric Press, 1994.
5. Kessler RC, Berglund PA, Demler O, Jin R, Walters EE. Lifetime prevalence and age-of-onset distributions of DSM-IV disorders in the National Comorbidity Survey Replication (NCS-R). Archives of General Psychiatry. 2005 Jun;62(6):593-602.
6. Kessler RC, Berglund P, Demler O, Jin R, Koretz D, Merikangas KR, Rush AJ, Walters EE, Wang PS. The epidemiology of major depressive disorder: results from the National Comorbidity Survey Replication (NCS-R). Journal of the American Medical Association, 2003; Jun 18;289(23):3095-105.
Neural networks are modeling tools that can help us understand
processes. They are used to identify patterns and to understand how
individual patterns are generated. We use neural networks of ordinary
differential equations to help us understand the effects of treatment
on the pattern of recovery. First I will tell you about the how we
constructed our neural network model architecture. Then I will show
you how differential equations give us greater ability in the study
depression recovery. A differential equation is a way of applying
algebra and calculus to describe the relationships between the rates
of change of the quantaties we're interested in.
Skipping over the trials and tribulations of identifying an appropriate problem, I will first say that having come from industry I was aware of customer needs. In this context it meant that the research questions, guidance and judgment about whether we were being useful would come from the clinicians, not from the theorists.
The far reaching goal of the research aims at individual treatment. What is now called personalized medicine. This is because not every treatment works on every person. Because treatment choices are made by trial end error, the second goal aims to identify the correct treatment for a given individual. The third goal aims to get to the first two through a better understanding the underlying dynamics of depression. It focuses on the course of the recovery process because the research is grounded in clinical data and there are no data on depression before the diagnosis of depression is made. So outcome and recovery data were all we had to work with.
Two approaches were undertaken, one that took advantage of baseline and outcome data ant the other that took advantage of the limited time course (repeated measure) data available through the course of a clinical trial.
This was the first time these advanced methods were applied to clinical data.
We did this because depression a big problem, lots suffer, sometimes fatal and is number one cost to business
Currently up to practioner - not objective - not based on individual symptomatology -- one size fits all, can do better.
Before my PhD Defense, this work was recognized at an NIH sponsored workshop in 1996. I was honored, when the book came out several months later to find that the Editors had chosen to place my model on the cover of the book. I was also pleased that the placed it over an fMRI image because in fact, my model included hypotheses linking clinical symptoms and brain region activity.