Patricia Butterfield & Naomi Chaytor October 18th, 2017

Slides:



Advertisements
Similar presentations
DiseaseNo disease 60 people with disease 40 people without disease Total population = 100.
Advertisements

Clinical Effectiveness: Interpreting test results Nick Price 17 th October 2006.
Validity and Reliability of Analytical Tests. Analytical Tests include both: Screening Tests Diagnostic Tests.
Power and sample size.
Chapter 4 Pattern Recognition Concepts: Introduction & ROC Analysis.
Comparison of the HIV LIA vs WB on HIV-Negative Samples CDC-HIV Diagnostics Meeting “New Diagnostic Technologies” Dec 5-7, 2007 Dr. John Kim National Laboratory.
TESTING A TEST Ian McDowell Department of Epidemiology & Community Medicine November, 2004.
Diagnostic Tests Patrick S. Romano, MD, MPH Professor of Medicine and Pediatrics Patrick S. Romano, MD, MPH Professor of Medicine and Pediatrics.
What Happens to the Performance of a Diagnostic Test when the Disease Prevalence and the Cut-Point Change? Pathological scores Healthy scores Healthy population.
Azita Kheiltash Social Medicine Specialist Tehran University of Medical Sciences Diagnostic Tests Evaluation.
CRITICAL APPRAISAL Dr. Cristina Ana Stoian Resident Journal Club
Statistical Fridays J C Horrow, MD, MSSTAT
(Medical) Diagnostic Testing. The situation Patient presents with symptoms, and is suspected of having some disease. Patient either has the disease or.
What is Screening? Basic Public Health Concepts Sheila West, Ph.D. El Maghraby Professor of Ophthalmology Wilmer Eye Institute Johns Hopkins University.
Interpreting Diagnostic Tests
Statistics in Screening/Diagnosis
BASIC STATISTICS: AN OXYMORON? (With a little EPI thrown in…) URVASHI VAID MD, MS AUG 2012.
Lecture 4: Assessing Diagnostic and Screening Tests
Basic statistics 11/09/13.
Diagnostic Testing Ethan Cowan, MD, MS Department of Emergency Medicine Jacobi Medical Center Department of Epidemiology and Population Health Albert Einstein.
Applied Epidemiology PU Unit 9 Overview  Epidemiologic specializations  Research design  Global Burden of Disease Study  Disability-adjusted.
Statistics for nMRCGP Jo Kirkcaldy. Curriculum Condensed Knowledge Incidence and prevalence Specificity and sensitivity Positive and negative predictive.
Sensitivity Sensitivity answers the following question: If a person has a disease, how often will the test be positive (true positive rate)? i.e.: if the.
BIOE 301 Lecture Thirteen. Review of Lecture 12 The burden of cancer Contrasts between developed/developing world How does cancer develop? Cell transformation.
Sensitivity & Specificity Sam Thomson 8/12/10. Sensitivity Proportion of people with the condition who have a positive test result Proportion of people.
Statistical test for Non continuous variables. Dr L.M.M. Nunn.
Likelihood 2005/5/22. Likelihood  probability I am likelihood I am probability.
Evidence-Based Medicine Diagnosis Component 2 / Unit 5 1 Health IT Workforce Curriculum Version 1.0 /Fall 2010.
Evaluating Results of Learning Blaž Zupan
Screening of diseases Dr Zhian S Ramzi Screening 1 Dr. Zhian S Ramzi.
Positive Predictive Value and Negative Predictive Value
1 Wrap up SCREENING TESTS. 2 Screening test The basic tool of a screening program easy to use, rapid and inexpensive. 1.2.
Predictive values prevalence CK and acute myocardial infarction –sensitivity 70% –specificity 80% –prevalence - 40% –prevalence - 20% –PPV and NPV.
Diagnostic Tests Studies 87/3/2 “How to read a paper” workshop Kamran Yazdani, MD MPH.
Diagnostic Test Characteristics: What does this result mean
Screening.  “...the identification of unrecognized disease or defect by the application of tests, examinations or other procedures...”  “...sort out.
/ 101 Saudi Diploma in Family Medicine Center of Post Graduate Studies in Family Medicine EBM Diagnostic Tests Dr. Zekeriya Aktürk
Laboratory Medicine: Basic QC Concepts M. Desmond Burke, MD.
Diagnosis Examination(MMSE) in detecting dementia among elderly patients living in the community. Excel.
Timothy Wiemken, PhD MPH Assistant Professor Division of Infectious Diseases Diagnostic Tests.
Biostatistics Board Review Parul Chaudhri, DO Family Medicine Faculty Development Fellow, UPMC St Margaret March 5, 2016.
Critical Appraisal Course for Emergency Medicine Trainees Module 5 Evaluation of a Diagnostic Test.
دکتر حمیدرضا صابری
TUTORIAL: SCREENING. PERFORMANCE OBJECTIVES Compute and interpret Sensitivity Specificity Predictive value positive Predictive value negative False positive.
Accuracy, sensitivity and specificity analysis
Screening for Disease: Part One
GP ST2 Group, 28/9/11 Tom Gamble
Performance of a diagnostic test Tunisia, 31 Oct 2014
Probability and Statistics
Evidence-Based Medicine
Question 1 A new ‘Super test’ claims to have a superb capability to diagnose disease X. Its sensitivity is 99% and specificity is 90%. Which of the following.
Class session 7 Screening, validity, reliability
Evaluating Results of Learning
بسم الله الرحمن الرحيم Clinical Epidemiology
What is Screening? Basic Public Health Concepts Sheila West, Ph.D.
کاربرد آمار در آزمایشگاه
Machine Learning Week 10.
How do we judge efficacy of a screening test?
Evaluation of the Guidelines for Management of Pancreatic Branch-Duct Intraductal Papillary Mucinous Neoplasm  Raymond S. Tang, Benjamin Weinberg, David.
Diagnosis II Dr. Brent E. Faught, Ph.D. Assistant Professor
Accuracy, sensitivity and specificity analysis
Hint: Numerator Denominator. Vascular Technology Lecture 34: Test Validation (Statistical Profile and Correlation) HHHoldorf.
What is Screening? Basic Public Health Concepts Sheila West, Ph.D.
Is a Positive Developmental-Behavioral Screening Score Sufficient to Justify Referral? A Review of Evidence and Theory  R. Christopher Sheldrick, PhD,
Millie D. Long, Bruce E. Sands 
Figure 1. Table for calculating the accuracy of a diagnostic test.
Evaluating Models Part 1
A Systematic Review and Meta-analysis of D-dimer as a Rule-out Test for Suspected Acute Aortic Dissection  Stephen E. Asha, MBBS, MMed (Clin Epi), James.
Diagnostic performance of dentist clinical impression.
Clinical Effectiveness: sensitivity, specificity and PPV
Presentation transcript:

Patricia Butterfield & Naomi Chaytor October 18th, 2017 Assessing Validity and Reliability in Diagnostic and Screening Tests: Session 2 Patricia Butterfield & Naomi Chaytor October 18th, 2017

Objective-hour 2: Using case study examples and clinical vignettes, calculate and interpret sensitivity, specificity, positive predictive value, and negative predictive value.

Create a table from the data on facial weakness from table 5 in the paper Calculate sensitivity and specificity

ANSWER 1

Sensitivity: 8x100/46 = 17% Specificity: 18x100/19 = 95% ANSWER 1: Focal Lesion No Lesion Abnormal Exam 8 (True Pos) 1 (False Pos) 9 Normal Exam 38 (False Neg) 18 (True Neg) 56 46 19 65 Sensitivity: 8x100/46 = 17% Specificity: 18x100/19 = 95%

Calculate PPV and NPV: PPV = true positives x 100 true positives + false positives NPV = true negatives x 100 true negatives + false negatives Interpret these values – Clinical implications?

ANSWER 2

ANSWER 2: Focal Lesion No Lesion Abnormal Exam 8 (True Pos) 1 (False Pos) 9 Normal Exam 38 (False Neg) 18 (True Neg) 56 46 19 65 PPV = 8 (TP) x 100/9 (TP + FP) = 89% NPV = 18 (TN) x 100/56 (TN + FN) = 32% If you have a focal exam, you have an 89% likelihood of having a focal lesion If you have a normal exam, you have a 32% chance of not having a lesion (you are still more likely to have a lesion!)

What is the prevalence/Base Rate of focal lesions in the paper? Does this matter? What would happen if the prevalence of disease changed? 71% prevalence of focal lesion in paper sample

Half the groups (1% prevalence): Focal Lesion No Lesion Abnormal Exam 5 149 154 Normal Exam 25 2821 2846 30 2970 3000 Half the groups (33% prevalence): Focal Lesion No Lesion Abnormal Exam 5 3 8 Normal Exam 25 57 82 30 60 90

ANSWER 3 & 4

ANSWER 3: 1% prevalence of focal lesions: PPV = 5 (TP) x 100/154 (TP + FP) = 3% NPV = 2821 (TN) x 100/2846 (TN + FN) = 99% If you have a focal exam, you have a 3% chance of having a focal lesion (higher than 1%, but not much) If you have a normal exam, you have a 99% chance of not having a lesion (same as before test)

ANSWER 4: 33% prevalence of focal lesion: PPV = 5 (TP) x 100/8 (TP + FP) = 63% NPV = 57 (TN) x 100/82 (TN + FN) = 70% If you have a focal exam, you have a 63% chance of having a focal lesion (twice as good as base rate) If you have a normal exam, you have a 70% chance of not having a lesion (about the same as base rate)

The end.