BME 314 Lecture 10 Mia Markey 2010

BME 314 Lecture 10 Mia Markey 2010 - Informatics...

Info iconThis preview shows pages 1–14. Sign up to view the full content.

View Full Document Right Arrow Icon
UT Biomedical Informatics Lab Informatics 1
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
UT Biomedical Informatics Lab Biomedical Informatics biomedical informatics = bioinformatics + medical  informatics bio informatics : study of the optimal storage and use  of  biological data  in biomedical research medical  informatics : study of the optimal storage  and use of  medical data  for clinical decision making  and related tasks. Now more commonly called  “clinical informatics”. 2
Background image of page 2
UT Biomedical Informatics Lab Confusion Matrix 303 17 973 965 + + - - Truth Prediction 3
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
UT Biomedical Informatics Lab Accuracy Number correctly classified samples divided  by the total number of samples Accuracy =  (965 + 303) / (965 + 17 + 973 + 303) = 56% 303 17 973 965 + + - - Truth Prediction 4
Background image of page 4
UT Biomedical Informatics Lab Two Kinds of Mistakes Accuracy just counts up the number of times the  right answer was obtained But, there are two  kinds of mistakes… Could classify as positive when actually negative Or, could classify as negative when actually positive So, we need two measures to separate these  errors 303 17 973 965 + + - - Truth Prediction 5
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
UT Biomedical Informatics Lab Accuracy Depends on Prevalence Another disadvantage of accuracy is that it depends upon the prevalence of the population, i.e., the frequency with which the two classes occur 6
Background image of page 6
UT Biomedical Informatics Lab Prevalence Number positive (disease) samples divided  by the total number of samples 303 17 973 965 + + - - Truth Prediction Prevalence =  (965 + 17) / (965 + 17 + 973 + 303) = 43% 7
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
UT Biomedical Informatics Lab Prevalence & Accuracy Accuracy =  (0 + 99) / (99 + 0 + 1 + 0) = 99% Prevalence =  1 / (99 + 0 + 1 + 0) = 1% 99 1 0 0 + + - - Truth Prediction 8
Background image of page 8
UT Biomedical Informatics Lab Sensitivity, Specificity Introduce two measures called  sensitivity  and  specificity  that separate the two kinds of errors and  do not depend on prevalence 9
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
UT Biomedical Informatics Lab Sensitivity or True Positive Fraction Number samples classified as positive that  were actually positive divided by the number  of samples that were actually positive Sensitivity = 965 / (965 + 17) = 98% 303 17 973 965 + + - - Truth Prediction 10
Background image of page 10
UT Biomedical Informatics Lab Specificity or True Negative Fraction Number samples classified as negative that  were actually negative divided by the number  of samples that were actually negative Specificity = 303 / (303 + 973) = 24% 303 17 973 965 + + - - Truth Prediction 11
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
UT Biomedical Informatics Lab Prevalence & Accuracy, Sensitivity & Specificity Accuracy =  (0 + 99) / (99 + 0 + 1 + 0) = 99% Prevalence =  1 / (99 + 0 + 1 + 0) = 1% 99 1 0 0 + + - - Truth Prediction Sensitivity =  (0) / (0 + 1) = 0% Specificity =  (99) / (0 + 99) = 100% 12
Background image of page 12
UT Biomedical Informatics Lab Dependence of Accuracy on Prevalence Accuracy = 
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 14
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 59

BME 314 Lecture 10 Mia Markey 2010 - Informatics...

This preview shows document pages 1 - 14. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online