Robert Gordon Biostatistics and Medical Safety Johnson & Johnson

Slides:



Advertisements
Similar presentations
Advancing Assessment Literacy Data Analysis I: Summarizing, Representing, and Sharing Data.
Advertisements

The Forest for the Trees Visualizing Adverse Events Andreas Brueckner Bayer Healthcare.
Industry/FDA/Academia Safety Graphics Working Group Introduction and Overview FDA/QSPI Biostatistics, Statistical Programming, and Data Management Summit.
Population Population
Copyright © 2014 by The University of Kansas Collecting and Analyzing Data.
Copyright © 2010, 2007, 2004 Pearson Education, Inc. All Rights Reserved. Lecture Slides Elementary Statistics Eleventh Edition and the Triola.
Qi Jiang and Liping Huang on Behalf of the Adverse Event Sub Team
Chapter 2: Looking at Data - Relationships /true-fact-the-lack-of-pirates-is-causing-global-warming/
McGraw-Hill/Irwin McGraw-Hill/Irwin Copyright © 2009 by The McGraw-Hill Companies, Inc. All rights reserved.
Module 4: Data presentation & interpretation. Module 4: Learning objectives  Understand different ways to best summarize data  Choose the right table/graph.
Graphical Data Displays and Interpretation 2009 October 9.
Graphical Data Displays and Interpretation Wednesday, October 9.
Scientific Communication and Technological Failure presentation for ILTM, July 9, 1998 Dan Little.
Types of Data Displays Based on the 2008 AZ State Mathematics Standard.
Module 3: Data presentation & interpretation. Module 3: Learning Objectives  Understand different ways to best summarize data  Choose the right table/graph.
CORRELATIO NAL RESEARCH METHOD. The researcher wanted to determine if there is a significant relationship between the nursing personnel characteristics.
How to Assess Student Learning in Arts Partnerships Part II: Survey Research Revised April 2, 2012 Mary Campbell-Zopf, Ohio Arts Council
JumpStart the Regulatory Review: Applying the Right Tools at the Right Time to the Right Audience Lilliam Rosario, Ph.D. Director Office of Computational.
PSYCHOLOGY 820 Chapters Introduction Variables, Measurement, Scales Frequency Distributions and Visual Displays of Data.
NSW Curriculum and Learning Innovation Centre Tinker with Tinker Plots Elaine Watkins, Senior Curriculum Officer, Numeracy.
Tabular Display of Data Prepared by: Gary Klass
Tutor: Prof. A. Taleb-Bendiab Contact: Telephone: +44 (0) CMPDLLM002 Research Methods Lecture 9: Quantitative.
Chap 1-1 Copyright ©2013 Pearson Education, Inc. publishing as Prentice Hall Business Statistics: A First Course 6 th Edition Chapter 1 Introduction.
+ The Practice of Statistics, 4 th edition - For AP* STARNES, YATES, MOORE Chapter 1: Exploring Data Introduction Data Analysis: Making Sense of Data.
Welcome to Common Core High School Mathematics Leadership
Chapter 12 Visual Aids. Learning Objective 1 Describe the purposes of visual aids in written and oral communication.
Lecture 1.2 Field work (lab work). Analysis of data.
Computational Diagnostics: A Novel Approach to Viewing Medical Data 5th International Conference on Coordinated & Multiple Views in Exploratory Visualization.
Overview of CCSS Statistics and Probability Math Alliance September 2011.
MATH 3400 Computer Applications of Statistics Lecture 6 Data Visualization and Presentation.
Exploring Data Section 1.1 Analyzing Categorical Data.
EXPERIMENTAL DATA PROCESSING Ilya I. Ogol. There are three kinds of lies: lies, damned lies, and statistics.
Researcher’s Name School City, State.  Explain the background concepts that your audience needs to understand your research.  Describe why you chose.
PowerPoint Template – delete this slide Fill in the appropriate slides Remove any bold or italicized words after you’ve added your changes Delete slides.
14-1 © 2014 by McGraw-Hill Education. This is proprietary material solely for authorized instructor use. Not authorized for sale or distribution in any.
Graphical Approaches for Safety Signal Detection Efforts of the FDA-Industry-Academia Working Group Mat Soukup, Ph.D. Acting Team Lead Biometrics 7, CDER.
Click to add Presentation Title Arial 32, 5 line max title space line 3, title space line 4, title space line 5 Presenter Title Organization Insert your.
Investigating Patterns Cornell Notes & Additional Activities.
Copyright © Allyn & Bacon 2008 Intelligent Consumer Chapter 14 This multimedia product and its contents are protected under copyright law. The following.
Multi-dimensional Dynamic Visualization of Clinical Data Jianmei Wang Roche Products Limited October
CONFIDENTIAL Data Visualization Katelina Boykova 15 October 2015.
Qualitative and Quantitative Research Methods
White Papers to Fill the Gaps of Standardization of Tables, Figures, and Listings (Creating Standard Targets) Analyses and Displays for Vital Signs, ECG,
Copyright © 2010, 2007, 2004 Pearson Education, Inc. All Rights Reserved. Section 4-2 Displaying Distributions with Graphs.
Surveillance and Population-based Prevention Department for Prevention of Noncommunicable Diseases Displaying data and interpreting results.
Data Visualization: The new era of revolution in the pharmaceutical industry Mark Matthews GCE Solutions PhUSE 2015.
Bayesian approach to equivalence study of medical device 1 1.
Bell Ringer You will need a new bell ringer sheet – write your answers in the Monday box. 3. Airport administrators take a sample of airline baggage and.
+ Warm Up Which of these variables are categorical? Which are quantitative?
Communicating with Graphs Notes 1.3. Objectives Identify three types of graphs and explain the ways they are used. Analyze data using the various types.
Robert Gordon FDA/QSPI Biostatistics, Statistical Programming and Data Management Summit Washington D.C. March 2012.
Data: Categorical vs. Quantitative Mr. Diaz Math 3.
A Training Course for the Analysis and Reporting of Data from Education Management Information Systems (EMIS)
Copyright © 2009 Pearson Education, Inc. 3.2 Picturing Distributions of Data LEARNING GOAL Be able to create and interpret basic bar graphs, dotplots,
Biostatistics Dr. Amjad El-Shanti MD, PMH,Dr PH University of Palestine 2016.
PowerPoint Template – delete this slide Fill in the appropriate slides Remove any bold or italicized words after you’ve added your changes Delete slides.
03/20161 EPI 5344: Survival Analysis in Epidemiology Estimating S(t) from Cox models March 29, 2016 Dr. N. Birkett, School of Epidemiology, Public Health.
DIA Annual Meeting 2014 Statistical Science and Quantitative Thinking Track AJ Sankoh, Rima Izem.
Safety of the Subject Cena Jones-Bitterman, MPP, CIP, CCRP
Visualizations of Safety Data
An Integrated Analysis of Liver Safety Data from Orlistat Clinical Trials Obes Facts 2012;5:485–494 - DOI: / Fig. 1. Occurrence of two.
Safety of the Subject Cena Jones-Bitterman, MPP, CIP, CCRP
1 Topic Title First slide 2 line 3 line 4 line
Presenter Name Title Organization.
Visualizing Subject Level Data in Clinical Trial Data
Volume 151, Issue 6, Pages (December 2016)
1 Session Title 2 line 3 line 4 line
ASA Safety Monitoring Working Group
Safety analysis of clinical trials in NDA submissions JSM 2018, Jul
1 Topic Title First slide 2 line 3 line 4 line
Presentation transcript:

Robert Gordon Biostatistics and Medical Safety Johnson & Johnson Organized and Effective Interpretation of Clinical Laboratory Data: Graphs Make a Difference Robert Gordon Biostatistics and Medical Safety Johnson & Johnson

Disclaimer The views and opinions expressed in the following PowerPoint slides are those of the individual presenter. These PowerPoint slides are the intellectual property of the individual presenter and are protected under the copyright laws of the United States of America and other countries. Used by permission. All rights reserved.

Overview Conflicts of Interest / Disclaimer Industry Drivers J&J has financed the trip and accommodations Industry Drivers Labs and Liver Methodology, Categories and Questions Some Examples Q & A Pitfalls and Suggestions

Industry Drivers

Industry Documents Hepatology 48(5):1680-9, 2008

CIOMS: Council for International Organizations of Medical Sciences ‘…the risk to individual trial subjects is a critical consideration during product development, at a time when the effectiveness of a product is generally uncertain.’ – CIOMS VII

Why Graphics for Lab Data Aid in identification of the unexpected Numerical quantities focus on expected values, graphical summaries on unexpected values. (John Tukey) Identify patterns within the clinical data Temporal, dose groups, demographics Combination of multiple lab parameters Shift tables → matrix plots Identification of syndromes, concurrent abnormalities Much more effective interpretation of tabular data Very large datasets

From This!

To This! Amit, hieberger, Lane ‘Graphical approaches to the analysis of safety data from clinical trials’ 2007 Amit, hieberger, Lane ‘Graphical approaches to the analysis of safety data from clinical trials’ 2007

Labs and Liver Methodology, Categories and Questions

Methodology Identify the clinical questions that we are trying to answer regarding labs and liver results Align appropriate graphs with their ‘most’ appropriate category – multiple crossovers Critique and enhance graphs to best answer the questions Provide background, uses, enhancements, and yes – CODE!

Labs and Liver Categories Baseline & Trending Association between Lab Variables Liver Function Tests General

Baseline and Trending Are abnormal lab values a result of a borderline baseline lab value? What are the changes and percent changes from baseline over time? What are the toxicity grade trends over time? (what specifically would you be looking for in a trend?) What is the patient’s profile over time?

Association between Lab Variables Are there multiple lab values that are elevated or abnormal, either concurrently or not? How can we easily identify patients with simultaneous elevations in multiple lab tests over time? How can we display values for multiple lab parameters for subjects of interest?

Liver Function Tests How do we perform a comprehensive assessment of hepato-toxicity? How can we efficiently identify possible cases of drug induced liver injury? What are the maximum LFT values (or any max lab values) over time during the course of the study?

General Are there graphics which can aid in determining emerging safety signals? Is there a temporal relationship between treatment and lab abnormalities? What is the lab profile of the entire study, either by lab units or upper/lower limits of normal? What is the hazard for developing a low lab count over time while on treatment? Are there effective means of transitioning from whole population level to individual level?

Some Examples

ACTIVE TREATMENT GROUP From This! Subject ID Peak ALT ULN Peak Bili ULN Treatment Subject 10013 5.65 0.74 Active Subject 10014 3.56 0.80 Subject 10015 2.73 1.13 Subject 10016 5.66 4.57 Subject 10017 2.47 0.88 Subject 10018 7.73 1.32 Control Subject 10019 33.06 1.46 Subject 10020 11.60 3.23 Subject 10021 6.04 0.69 Subject 10022 13.60 0.83 Subject 10023 1.85 0.58 Subject 10024 0.21 0.42 Subject 10025 53.06 1.29 Subject 10026 8.36 1.63 Subject 10027 25.67 1.93 Subject 10028 31.23 1.27 ACTIVE TREATMENT GROUP   Peak Bilirubin < 2 Peak Bilirubin ≥ 2 Total Peak ALT < 3 1109 (73%) 29 (2%) 1138 (75%) Peak ALT ≥ 3 347 (23%) 30 (2%) 377 (25%) 1456 (96%) 59 (4 %) 1517 (100%) CONTROL GROUP 579 (80%) 6 (<1%) 585 (81%) 128 (18%) 5 (<1%) 133 (19%) 707 (98%) 11 (2%) 718 (100%^)

To This!

Let’s Remove Coloring

Simple and Powerful SubjectID LabTest StudyDay xULN Subject 123456US ALT (SGPT) 0.8 8 0.6 14 6 18 3.3 29 3 33 5.2 36 2.5 40 1.9 44 1.8 48 2.8 52 1.2 54 1 56 59 64 1.5 70 1.4 AST (SGOT) 0.9 3.5 Study Day Treatment ALT (xULN) AST (xULN) Bilirubin (xULN)   0.8 1 8 X 0.6 0.9 14 6 3.5 2 18 3.3 2.8 29 3 1.4 0.7 33 5.2 2.5 1.1 36 1.8 40 1.9 1.6 44 48 52 1.2 54 1.3 56 59 64 1.5 70 0.4   STUDY DAY 8 14 18 29 33 36 40 44 48 52 54 56 59 64 70 Treatment X ALT (xULN) 0.8 0.6 6 3.3 3 5.2 2.5 1.9 1.8 2.8 1.2 1 1.5 1.4 AST (xULN) 0.9 3.5 1.6 1.3 Bilirubin (xULN) 2 0.7 1.1 0.4

Trending over Time [Courtesy - Andreas Brueckner – Bayer]

Matrix Plots [SAS Institute - http://support.sas.com/sassamples/graphgallery/Health_and_Life_Sciences_Industry.html ]

Subjects of Interest [Courtesy – J&J]

Age Profile by Treatment Group [Courtesy – Qi Jiang– Amgen]

Interpretation – ‘Graphics Reveal Data’ (Tufte) ANSCOMBE’s QUARTET Graph 1 Graph 2 Graph 3 Graph 4 X Y 10 8.04 9.14 7.46 8 6.58 6.95 8.14 6.77 5.76 13 7.58 8.74 12.74 7.71 9 8.81 8.77 7.11 8.84 11 8.33 9.26 7.81 8.47 14 9.96 8.1 7.04 6 7.24 6.13 6.08 5.25 4 4.26 3.1 5.39 19 12.5 12 10.84 9.13 8.15 5.56 7 4.82 7.26 6.42 7.91 5 5.68 4.47 5.73 6.89 Mean of Y's 7.5 Mean of X's 9 Regression line Y = 0.5X + 3

Tufte Quotes ‘The Visual Display of Quantitative Information’ Modern data graphics can do much more than simply substitute for small statistical tables. At their best, graphics are instruments for reasoning about quantitative information. Often the most effective way to describe, explore, and summarize a set of numbers – even a large set – is to look at pictures of those numbers. Furthermore, of all methods for analyzing and communicating statistical information, well-designed data graphics are usually the simplest and at the same time the most powerful. The minimum we should hope for with any display technology is that it should do no harm. There is no such thing as information overload, just bad design. If something is cluttered and/or confusing, fix your design Excellence in statistical graphics consists of complex ideas communicated with clarity, precision, and efficiency.

FDA/Industry/Academia Working Group Members Regulatory: George Rochester, Matt Soukup, Bruce Weaver, Janelle Charles, Chuck Cooper, Suzanne Demko, Robert Fiorentino, Richard Forshee, Eric Frimpong, Ted Guo, Pravin Jadjav, Stephine Keeton, Leslie Kenna, Joyce Korvick, Catherine Njue, Antonio Paredes, Je Summers, Mark Walderhaug, Yaning Wang, Markus Yap, Hao Zhu Industry: Ken Koury, Brenda Crowe, Rich Anziano, Navdeep Boparai, Andreas Brueckner, Susan Duke, Sylvia Engelen, Mac Gordon, Larry Gould, Matthew Gribbin, Liping Huang, Qi Jiang, Andreas Krause Academia: Mary Banach , Frank Harrell

Thank You! Q & A

Pitfalls and Suggestions

Our Hepatotoxicity Graph

Let’s Remove Coloring

Reference Lines

Major and Minor Tickmarks

Logarithmic Scale ?

Our Hepatotoxicity Graph

Know Your Data

Proper Labeling http://richworks.in/2010/04/50-most-stunning-examples-of-data-visualization-and-infographics/