Transcript No Slide Title - School of Engineering

CSE4904 Computer Science Design Lab
CSE
4904
Prof. Steven A. Demurjian, Sr.
Computer Science & Engineering Department
The University of Connecticut
191 Auditorium Road, Box U-155
Storrs, CT 06269-2155
[email protected]
http://www.engr.uconn.edu/~steve
(860) 486 - 4818
1
Course Goals

CSE
4904
CSE4904: The “First” Project Based Course
 Objective of Course
 Expand Knowledge on Emerging Disciplines
 Learn about New/Innovative Technology/Standards
 Transition from Requirements to Design to
Development
 Work as a Loosely Organized Group
 You Make Decisions, Resolve Problems, etc.
 You “Apply” your Coursework/Experiences

What is Instructor’s Role?
 Provide a Set of Potential Project Topics
 Serve as Manager - Organize Meetings, Available
for Questions, etc.
2
Expand Knowledge on Emerging Disciplines

CSE
4904




Biomedical Informatics/Health Information
Technology Rapidly Emerging Discipline
Cutting Edge, Incredible Career and Research
Opportunities
Improve Practice of Medicine Through Informatics
 Patient Managed
 Patient Care
 Hospital Based
 Research (Genomics/Trials)
What is Biomedical Informatics?
Where is the Future?
3
What is Informatics?

CSE
4904


Informatics is:
 Management/Processing of Data
 From Multiple Sources/Contexts
Informatics
 Classification (Ontologies),
Collection, Storage, Analysis,
People
Dissemination
Informatics is Multi-Disciplinary
 Computing (Model, Store,
Mine, Process Information)
Information
Technology
 Social Science (HCI)
 Statistics (Analysis)
Informatics Can Apply to Multiple
Domains:
Adapted from Shortcliff textbook
 Pharmacology, Nursing,
Medicine, Biology, etc.
 Business, Fine Arts, Humanities
4
What is Biomedical Informatics (BMI)?

CSE
4904
BMI is Information and its Usage Associated with the
Research and Practice of Medicine Including:
 Clinical Informatics for Patient Care
 Medical Record + Personal Health Record

Bioinformatics for Research/Biology to Bedside
 From Genomics to Proteomics

Public Health Informatics (State and Federal)
 Tracking Trends in Public Sector

Clinical Research Informatics
 Deidentified Repositories and Databases
 Facilitate Epidemiological Research and Ongong
Clinical Studies (Drug Trails, Data Analysis, etc.)

Clinical Informatics, Pharmacy Informatics,
Consumer Health Informatics, Nursing Informatics
5
BMI & T1 Research (Bench  Clinical)

CSE
4904



Transfer of Knowledge from Laboratory or Bench to
Clinical Trials
Move Genomic Research from Bench (Lab) to
Clinical Trial (or Genetic/Test Intervention)
Transfer in Lab/Bench Research to Pre-Clinical and
Early Clinical Human Subject Research
Informatics Support via:
 Simulations, Super & Grid Computing
 Data Mining, Data Reduction, Data Analysis
 Database Interoperability, GUIs
6
BMI & Clinical Research (Trials)

CSE
4904


Applying Clinical Research Results via Trials with
Patients on Medication, Devices, Treatment Plans
Multi-Phased Process for Clinical Trials:
 Phase I: First Stage – 20-80 Healthy Patients
 Phase II: Second Stage – 20-300 Patients
 Phase III: Multi-Center Trials – 300-3000
 Phase IV: Monitoring of Drug After Approval
Informatics Support via:
 Electronic Multi-Site IRB, Collaboration Tools
 Clinical Trials Recruitment and Management
 Multi-Site Clinical Research Data Repository
7
BMI & T2 Research (Clinical  Community)

CSE
4904

Translating “Successful” Clinical Trials into Practice
and the Community
 Improvements in Practice
 New Evidence-Based Guidelines or Care Models
 Phase III Success Translated to Health Providers
Informatics Support for:
 Disseminating Education Materials to Providers &
Patients to Track Acceptance, Collect Outcomes
 Includes Tools from Clinical Research (Trials)
8
BMI & Clinical Practice

CSE
4904


Tracking all Information for Patient and his/her Care
 Medical Record, Medical Tests (Lab, Diagnostic,
Scans, etc.), Prescriptions
Dealing with Patients – Direct Medical Care
 Hospital or Clinic, Physician’s Office
 Testing Facility, Insurance/Reimbursement
Informatics Support via:
 Electronic Medical Record
 Linking/Accessing Data Repositories
 Collaborative and Secure (HIPPA) Web Portals
9
What is UConn Doing in this Area?

CSE
4904

NIH’s CTSA Program: Transform the Way Clinical
and Translational Science Research is Conducted
 From Bench to Clinical Research to Translational
Research to the Bedside and Back Again
 36+ Academic Medical Centers Awarded to Date
see: http://www.ctsaweb.org/
Under President Mike Hogan’s Leadership
 UConn Submitted a CTSA Proposal in Oct 2008
 Formed CICaTS: Connecticut Institute for Clinical
and Translational Science (Sept. 29th 09)
 University Initiative with Partners
 John Dempsey, St. Francis, Hartford Hospital, CCMC,
Hospital for Central CT, Institute for Living, etc.

http://cicats.uchc.edu/
10
CICATS

CSE
4904


Official Launching:
 Tuesday September 29, 10:30am-1:30pm
 UConn Global Business Learning Center, Hartford
 Speakers Include: Pres. M. Hogan, Provost P.
Nichols, and Dean Cato Laurencin (Med School)
Mission:
 to educate and nurture new scientists
 to increase clinical and translational
research being conducted at UCHC, regional
hospitals, UConn Storrs, and healthcare
organizations throughout greater Hartford
 to work collaboratively with regional stakeholders
to combat the leading causes of morbidity,
mortality, disability, and health disparities
CICATS will have Biomedical Informatics Center
11
Increasing Biomedical Informatics Expertise

CSE
4904


Grow “Our Own” Biomedical Informatics Faculty
 Announced Provost Initiative in mid-July 2009
 $100,000 Committed for Faculty Training Costs
and Associated Release Time
Three On-Line Program Options:
 AMIA 10x10 Health Informatics Program
http://www.amia.org/10x10
 MS Program in BMI (Oregon H&S, UIllinois, etc.)
 Certificate Program in BMI
8 UConn Faculty (7 UCHC/1 Storrs) took Course
12
Eminent Faculty Search in BMI

CSE
4904


Soon to be Approved (this week) Dual Campus
Eminent Faculty Search for Biomedical Informatics
 7 to 9 total Faculty
 Recruitment of “Leader” for BMI Center and
Faculty at All Levels
Seeking Profiles that Include:
 Clinical, Medical, and/or Health Informatics who
are Medical Professions (MD Likely) with a Track
Record in Informatics
 Computing and/or Information Science PhDs with
Medical, Clinical, or Health Background/Training
This year – Senior Leader (UCHC) and multiple
Positions
13
Biomedical Informatics in CICATS
CSE
4904
14
GAANN: Advanced Computing
CSE
4904
Graduate Assistants in Areas of National Need
Proposal Funded by: US Dept. of Education
PI: R. Ammar
co-PIs: S. Demurjian, S. Rajasekaran, J.H. Cui, and S. Zhou
Advanced Computing Spans:
Biomedical Informatics (BMI)
Underwater Sensor Networks (UWSN)
15
Advanced Computing and its Focal Areas
Advanced Computing
Ammar (CSE)
CSE
4904
Biomedical Informatics
Demurjian (CSE) and Rajasekaran (CSE)
AC-FA1
Bio/Genome
Informatics:
Super Computing
Ammar (CSE)
Graveley (GDB)
Gryk (MMSB)
Huang (CSE)
Kuo (STAT)
Mandoiu (CSE)
Moraru (CCAM)
Rajasekaran (CSE)
Schiller (MMSB)
Shin (CSE)
Wu (CSE)
AC-FA2
Medical Informatics:
Data Warehousing
and Data Mining
Agresta (DFM)
Aseltine (PHDS)
Demurjian (CSE)
Harel (ST)
Huang (CSE)
Kim (CSE)
Mandoiu (CSE)
Rajasekaran (CSE)
Shin (CSE)
AC-FA3
Underwater Sensor Networks
Cui (CSE) and Zhou (ECE)
AC-FA4
AC-FA5
Security and
Networks
Architectures
and Protocols
Systems and
Devices
Demurjian (CSE)
Kiayias (CSE)
Russell (CSE)
Shvartsman (CSE)
Ammar (CSE)
Bagtzoglou (CEE)
Cui (CSE)
Fei (CSE)
Kim (CSE)
Liu (CEE)
Rajasekaran (CSE)
Torgerson(MS)
Shi (CSE)
Zhou (ECE)
Wang (CSE)
Auster (MS)
Cui (CSE)
Chandy (ECE)
Fei (ECE)
Li (CEE)
Lei (CMBE)
Pattipati (ECE)
Shi (CSE)
Zhou (ECE)
Wang (ECE)
Willett (ECE)
Ammar (CSE)
Cui (CSE)
Wang (CSE)
Shi (CSE)
16
GAANN Funding

CSE
4904

Support for Five Doctoral Students (each for 3 years)
each of whom Must be US Citizen.
One Student will be Funded in the Areas of
 BMI
 Bio/Genome Informatics: Supercomputing
 Medical Informatics: Warehouses and Mining

UWSN
 Architecture and Protocols
 Systems and Devices
5th student in Security and Networks will be in
either BMI or UWSN
Educational Program for GAANN includes Research,
Training in Teaching, etc., to Prepare Graduates to be
Faculty Members


17
Learn about New/Emerging Technology

CSE 
4904



Explore Smartphone Technologies and Applications
Four Smartphone Platforms
 Android
 Blackberry
 iPhone
 Microsoft
All with Differing APIs
 Java
 Java
 Objective C
 .NET
How do we Develop Applications?
How can we Link to Web and Existing BMI Apps?
18
Learn about New/Emerging Technology

CSE
4904
Personal Health Records (PHR) are Patient Controlled
Repositories
 Google Health (www.google.com/health)
 Accessible via Java API
 XML-Based Interface

Microsoft HealthVault (www.healthvault.com/)
 Accessible via .Net Infrastructure

Electronic Medical Records (EMRs) are Health
Provided Controlled Repositories
 General Electric Centricity EMR
 Version 9.2 – Secure Web Services
19
Project Focus this Semester

CSE
4904


Smartphone Applications that Interact with Google
Health (or MS Health Vault) and GE Centricity
Focus on Observations for Daily Living (ODLs)
What are ODLs?
 Patient Provided Information
 Related to their Chronic Diseases or Health Goals
 Augment Typical Information Provided at MD
Visit
 Continuous Input
 Clinical Decision Support to Spot Problem Trends
 Intervene Before Event Occurs
 Monitor Progress Towards Goal (e.g., weigh loss)
20
Two Types of ODLs

CSE
4904

Passive – Once Initiated, Collects Data
 Accelerometer
 Pedometer
 Pill Bottle that Sends a Time Stamp Message (over
Bluetooth?) to SmartPhone
Active – Patient Initiated
 Providing Information via Smartphone on:






Diabetes (Glucose, Weight, Insulin)
Asthma (Peak Flow, use of Inhaler)
Heart Disease (Pulse, BP, Diet)
Pain, Functional status, Fatigue, etc.
From Basic to Sophisticated!
All ODLs will have Help (Usability) and Education
(Disease) Capability Built in.
21
Overall Architecture
CSE
4904
Providers
Centricity EMR
Web/Application
Server
SQL Server
Database
Patients
Client Side Technologies
https, html, Ajax, XML
Server Side Technologies
Java, JSP, Hibernate,
Relational Database, XML
Database
Repository
Google
Health
Patient Demographics
and ODLs
Figure 1: Architecture Diagram of the Proposed System.
22
Possible ODLs

CSE
4904
Multi-Media Support Repository: It has been found in a
number of settings, that people with chronic diseases may be
able to cope with their pain, fatigue, etc., through the use of
audio clips, video clips, or pictures that mean something too
them. For example, for one person it may be pictures and clips
of family and loved ones, for another person it may be popular
music, for yet another inspirational speeches, and so on. The
intent is to develop a Smartphone application that is capable of
tracking a repository of audio, video, and pictures, categorized
by Topic, Title, and/or Keywords. The system will track a
complete historical record for each participant, noting the
selections that are being utilized along with their date-time
stamp and frequency. There will be the ability to have a
favorites list of most frequently used selections, as well as for
each participant to upload their own audio/videos for her own
use. The intent is to also have a version of this application that
could cache selections with the memory of the Smartphone to
reduce download times, particularly for those selections chosen
most frequently.
23
Possible ODLs

CSE
4904
Pedometer or Accelerometer: For either of these
applications, you will need to have an actual
Smartphone that has motion sensors. The idea would
be that these applications would be initiated by a
patient to collect information associated with walking
(pedometer) or movement (accelerometer) for a fixed
period of time.
24
Possible ODLs

CSE
4904
Discrete Measurement of Symptom/Condition:
Historically, pain scales have been used extensively in
medical settings (just to a Google Search on “pain
scale” images). This type of scale can be generalized
to collect information related to pain, fatigue, mobility,
adherence to medication, and so on. Note that some of
these ODLs may be regularly schedule (e.g., the
smartphone beeps a reminder), triggered as the result
of a contact to the patient (e.g., an automated call or
email to the smartphone), or initiated by the user. The
numerical values are tracked for each individual to
capture all of the values entered. This would be a
simplistic ODL based on a scale (1 to 10, Good to
Bad, etc.) rather than any actual collection of
medical/personal data.
25
Possible ODLs

CSE
4904
Discrete Measurement of Symptom/Condition:
Historically, pain scales have been used extensively in
medical settings (just to a Google Search on “pain
scale” images). This type of scale can be generalized
to collect information related to pain, fatigue, mobility,
adherence to medication, and so on. Note that some of
these ODLs may be regularly schedule (e.g., the
smartphone beeps a reminder), triggered as the result
of a contact to the patient (e.g., an automated call or
email to the smartphone), or initiated by the user. The
numerical values are tracked for each individual to
capture all of the values entered. This would be a
simplistic ODL based on a scale (1 to 10, Good to
Bad, etc.) rather than any actual collection of
medical/personal data.
26
Possible ODLs

CSE
4904
Synching Information with PHR/EMR: For this
application, you need to consider the information that
is stored in a PHR and/or EMR, and develop
Smartphone applications that provide a means for
patients to enter the information which can then be
synchronized with the PHR/EMR. For example,
Google Health lets a user maintain his/her
prescriptions, but it is not set up to handle nutritional
supplements and other home remedies. A application
could support the data entry of this information, which
would then be synchronized into Google Health, and if
the user is also a patient with data in the EMR
Centricity, a second step would synchronize to this
repository using its secure web services. A different
application could also be considered to handle side
effects and reactions to medications, food, allergens.
27
Possible ODLs

CSE
4904
Scanning/Recognition: For this application, it may
be possible to leverage the digital camera in a cell
phone to take a “picture” of a medication and/or
nutritional supplement label that can be then uploaded
to the web into the PHR or EMR. The idea would be
for the patient to be able to create a pictorial
representation of medications/supplements, that would
also be supplemented with their complete dosing
information (size, frequency, etc.). This would
involve being able to capture perhaps multiple images
from the same medication/supplement and meld them
together.
28
Possible ODLs

CSE
4904
Futuristic: Are you really Ambitious?
 Link Commercial Glucose Meter to SmartPhone
 Digital Camera on Smartphone to Scan Bar Codes
on Supplements and/or Medications
 May Involve OCR

Hooking up Sensors through Smartphones
 Pulse, BP, etc.
 Treadmill or Exercise Equipment
GPS and Smartphones? For Movement?
Many of these will need to store data in PHR/EMR


29
Course Process and Overview

CSE 
4904







Identify Problem – by Thursday, 9am
Requirements Specification – by 3rd Class
 User-Interface Driven Design
 Screen Shots and User Process
 Chosen Technologies and Platforms
Interactions and Feedback
Explore Development Alternatives/Platforms
Detailed Development and Testing
Implementation and Integration
Team Interactions and Dynamics
Setting and Meeting Milestones
Evaluating Success/Failure
30
Class Materials

CSE4904 Web Site at …

CSE
4904
www.engr.uconn.edu/~steve/Cse4904/cse4904.html
All Course Materials Available On-Line
 Communication by Email
 Available in Afternoons and by Appointment
Other Important Class Materials – Background on
 Health Information Technology
 Software Design, Java, Requirements Definition
 Unified Modeling Language (UML)


31
Milestones with Dates - Subject to Change

CSE 
4904







Project Proposal – 3 days after 1st class
Presentation of Goals/Objectives/Focus – 2nd Class
Requirements Specification – 3rd Class
Revised Requirements Specification – 4th class
Overall Design and Prototyping/Management Plan – 5th class
Prototype Report 1/Presentation – 8th class
Prototype Report 2/Presentation – 11th class
Prototype Report 3/Presentation –13th class
End of Semester (last day of classes)

Final Report/User Manual

Final Student Assessment

Solution/Materials in Source Code Repository
32
Documentation Packages/Requirements

CSE
4904



Development Environment/Source Code Control
 Use of IDE (e.g., Visual Studio, Eclipse, etc.)
 Source Code Control (Subversion)
 Web Page for Each Team/Project?
All Project Specifications (Written Documents) Must
be Done using: MS Word 03 or 07
All Project Presentations Must be Done Using
Powerpoint (PPT)
 Utilize Samples on Web Page for UML and CT
Insurance Dept. Link for Guide
Submit Both Hard Copy and Electronic Versions
 Hard Copy Produced on Laser Printer
 Electronic as a Directory zipped
 TeamNameProjX.zip
33
Project/Team Web Page/Documentation

CSE
4904


Should Each Team Develop a Web Page for their
Project????
 See Links for Former Projects as Examples
 Use To Post On-Going Documents
Augment Web Page with Detailed Design Documents
 Together CC Generates Documentation
 Frame Based HTML Resembles Java Doc
 Make Sure you Select “All” Diagrams
Documentation of Java with Java Doc
 Utilize Together Architect
 Utilize IDE
34
Today’s Tasks

CSE 
4904



Individual or Teams?
Choosing Teams – At Most 2 Team Members
 Self-Organized Teams
 Instructor Sets Teams
Meet & Brainstorming
 Remainder of Class
 Exchange Email and Phone Numbers
First Project Due – 3 days after first class at 9am Expect Feedback by End of Day
First Project Presentation – 2nd class
 5 to 10 minutes per team
 Copy of Slides/Create & Post on Web Page
35