Detection and Analysis

Slides:



Advertisements
Similar presentations
One of the most important aspects of any CME activity is evaluation, or outcomes measurement. CME Compliance: Evaluation Measuring the educational outcomes.
Advertisements

Logistic Regression Psy 524 Ainsworth.
Towards Twitter Context Summarization with User Influence Models Yi Chang et al. WSDM 2013 Hyewon Lim 21 June 2013.
Data Mining Methodology 1. Why have a Methodology  Don’t want to learn things that aren’t true May not represent any underlying reality ○ Spurious correlation.
Statistical control of multiple-stream processes — a literature review Eugenio K. Epprecht PUC-Rio Rio de Janeiro, Brazil ISQC Syney1.
Creating an Effective Test Instrument(Revised). Test Goals  Decide if goals need a test to be met.  Ensure that the test will certify learners knowledge.
Proactive Learning: Cost- Sensitive Active Learning with Multiple Imperfect Oracles Pinar Donmez and Jaime Carbonell Pinar Donmez and Jaime Carbonell Language.
TM Breakout Sessions Interactive and discussion-oriented Six major topic areas Sign up sheets Moderator designated for each session Recorder needed Discussion.
CSC 380 Algorithm Project Presentation Spam Detection Algorithms Kyle McCombs Bridget Kelly.
Chapter 11 Artificial Intelligence and Expert Systems.
Report on Intrusion Detection and Data Fusion By Ganesh Godavari.
Population-Wide Anomaly Detection Weng-Keen Wong 1, Gregory Cooper 2, Denver Dash 3, John Levander 2, John Dowling 2, Bill Hogan 2, Michael Wagner 2 1.
Syndromic Surveillance in Georgia: A Grassroots Approach February 22, 2006 Erin L. Murray Karl Soetebier Georgia Division of Public Health.
“To Ignore or Not to Ignore?” Follow-up to Statistically Significant Signals" Biosurveillance Information Exchange Working Group Reflections from San Diego.
The Impact of Healthcare Informatics on the Organization Vikas Arya HSCI 740 Wednesday, August 05, 2015Wednesday, August 05, 2015Wednesday, August 05,
WAC/ISSCI Automated Anomaly Detection Using Time-Variant Normal Profiling Jung-Yeop Kim, Utica College Rex E. Gantenbein, University of Wyoming.
Compliance System Validation - An Audit Based Approach December 2012 Uday Gulvadi, CPA, CIA, CISA, CAMS Director - Internal Audit, Risk and Compliance.
Means Tests Hypothesis Testing Assumptions Testing (Normality)
Intrusion Detection Jie Lin. Outline Introduction A Frame for Intrusion Detection System Intrusion Detection Techniques Ideas for Improving Intrusion.
© 2014 by McGraw-Hill Education. This is proprietary material solely for authorized instructor use. Not authorized for sale or distribution in any manner.
Current Environment/Challenges Many statistical signals (few with meaning) – easy to get lost in data and signals Many statistical signals (few with meaning)
Chapter 8 Hypothesis Testing I. Chapter Outline  An Overview of Hypothesis Testing  The Five-Step Model for Hypothesis Testing  One-Tailed and Two-Tailed.
11 C H A P T E R Artificial Intelligence and Expert Systems.
Thesis Proposal PrActive Learning: Practical Active Learning, Generalizing Active Learning for Real-World Deployments.
DataLyzer software Training. Introduction The purpose of this PPT is to give you quick information on the functionality of DataLyzer and to guide you.
Report on Intrusion Detection and Data Fusion By Ganesh Godavari.
Introduction Complex and large SW. SW crises Expensive HW. Custom SW. Batch execution Structured programming Product SW.
Analyzing over-the-counter medication purchases for early detection of epidemics and bio-terrorism by Anna Goldenberg Advisor: Rich Caruana Note: Sponsored.
Project Portfolio Management Business Priorities Presentation.
1 Data Mining: Concepts and Techniques (3 rd ed.) — Chapter 12 — Jiawei Han, Micheline Kamber, and Jian Pei University of Illinois at Urbana-Champaign.
Chapter 8 Hypothesis Testing I. Significant Differences  Hypothesis testing is designed to detect significant differences: differences that did not occur.
Automatic Discovery and Processing of EEG Cohorts from Clinical Records Mission: Enable comparative research by automatically uncovering clinical knowledge.
Intrusion Detection Systems Paper written detailing importance of audit data in detecting misuse + user behavior 1984-SRI int’l develop method of.
1 Chapter 18: Selection and training n Selection and Training: Last lines of defense in creating a safe and efficient system n Selection: Methods for selecting.
Multiscale Tools for Networking Vinay J. Ribeiro Ph.D. Thesis Proposal.
Differences Among Groups
Infectious Disease Surveillance & National/Health Security Michael A. Stoto CNSTAT Workshop on Vital Data for National Needs April 30, 2008, Washington.
Educational Communication & E-learning
Detection & monitoring of ADR
Training on Infection Prevention and Control
Turning Best Practice into Common Practice Connecting Michigan for Health Lansing, MI June 8, 2017 Ewa Matuszewski.
Introduction to Load Balancing:
A New Look to Statistics in the Classroom
Hypothesis Testing: One Sample Cases
Soliciting Reader Contributions to Software Tutorials
Introduction Characteristics Advantages Limitations
Machine Learning for Cloud Security
Intensity-scale verification technique
Professor Robert L. Heider, PE
Data Mining: Concepts and Techniques (3rd ed.) — Chapter 12 —
GEOGRAPHY OF LEISURE AND RECREATION
ComQuol: Service Focused Outcomes
Employee Contributions: Determining Individual Pay
Roland Kwitt & Tobias Strohmeier
Exploring the Limit Locator Tool
DMAIC Analyze, Improve, Control
One Health Early Warning Alert
Monitoring vs Evaluation
A survey of network anomaly detection techniques
Developing a Plan for Financial Sustainability
Software Quality Assurance
Spread Spectrum Watermarking
Privacy Protection for Social Network Services
Autonomous Medicine: Computer-Assisted Diagnosis Cancer Detection
Network-Wide Routing Oblivious Heavy Hitters
THEORY OF CHANGE VS. LOGICAL FRAMEWORK
Injury epidemiology- Participatory action research and quantitative approaches in small populations Lorann Stallones, PhD Professor and Director, Colorado.
Tom Savel, MD Lead – Grid Technologies Medical Officer NCPHI, CDC
Adaptive Leadership for Sustainable Networks
Rod Olete, RN Sustained Health Initiatives of the Philippines (SHIP)
Presentation transcript:

Detection and Analysis Perspectives of Both Data Monitors and Algorithm Developers

Data Monitors Turbulence Varied skill sets Turnover Training Varied skill sets Limited understanding of algorithms Overworked and few Feedback to providers critical

Developers Interaction and feedback from users is important Iteration Critical for developers to know users problems Limited understanding of public health operations Expense of false positive to users

Available Detection Methods BioSense, Essence, RODS, Red Bat… Cusum, Smart Scores, RLS, EWMA, Wavelet, … Spatial scan statistics, SatScan, zipcode Multiple detection algorithms – how many are flagging? Multiple detections corroborate problem Real-time vs. batch?

Real-time Detection Data is unsettled when it arrives Pressure for real-time may exacerbate existing problems Is it sustainable? Who will monitor it? How valuable is it? If not everyday – can we do it in a crisis?

Weaknesses of Detection Algorithms Cusum, EWMA – most widely used Control chart has many assumptions Normally distributed Stationary assumption Are assumptions being met? Method must match data Getting false alarms that exceed rate that would be expected may signal disconnect between data and algorithm

Challenges (to name a few) Syndrome categorization More? Fewer? Subsetting? Statistical significance does not equal public health significance “False” alarms

Issues for Users False positives Disconnect between developers and users Difficulty evaluating what is a real alarm Data quality issues What user needs are being supported? What are other uses for data? Overall evaluation of syndromic surveillance utility

Possible Approaches to Improving Detection Explanation to user of why alarming Pop-up? Text-strings from physicians Phased alerting system Yelling, Anomalies, Alert Improving alert qualification (RODS in Ohio)

Possible Approaches to Improving Detection (continued) Better pre-processing of data Better post-processing of data De-duplication of data, etc. Failure analysis of false alarms What are major contributors?

Needs Refined data Improved algorithms Human expert required to make determination Domain knowledge Local knowledge Statistical analysis is only a tool Good relationships among users Federal, state, local, facility levels

Summary Systems: Alarm too often Users: May become discouraged Statistical challenges Detection methods up to it? Data problems? Solutions: Better data, better processing, more money