Direct Uncertainty Prediction for Medical Second Opinions Maithra - - PowerPoint PPT Presentation

direct uncertainty prediction for medical second opinions
SMART_READER_LITE
LIVE PREVIEW

Direct Uncertainty Prediction for Medical Second Opinions Maithra - - PowerPoint PPT Presentation

Direct Uncertainty Prediction for Medical Second Opinions Maithra Raghu , Katy Blumer, Rory Sayres, Ziad Obermeyer, Sendhil Mullainathan, Jon Kleinberg Poster #246 Poster #246: Direct Uncertainty Prediction for Medical Second Opinions Human


slide-1
SLIDE 1

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Direct Uncertainty Prediction for Medical Second Opinions

Maithra Raghu, Katy Blumer, Rory Sayres, Ziad Obermeyer, Sendhil Mullainathan, Jon Kleinberg

Poster #246

slide-2
SLIDE 2

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Human Expert Disagreements

slide-3
SLIDE 3

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Human Expert Disagreements

slide-4
SLIDE 4

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Doctor Disagreements

slide-5
SLIDE 5

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Doctor Disagreements

Diagnostic Concordance Amongst Pathologists Interpreting Breast Biopsy Specimens, UW School of Medicine, JAMA, 2015

slide-6
SLIDE 6

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Doctor Disagreements

Diagnostic Concordance Amongst Pathologists Interpreting Breast Biopsy Specimens, UW School of Medicine, JAMA, 2015

  • Agreement between individual

pathologist grade and a panel consensus score on ~240 breast biopsies, 6900 individual case diagnoses

  • 25% disagreement between

pathologists and consensus

slide-7
SLIDE 7

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Doctor Disagreements

Grade 3: Moderate Diabetic Retinopathy Grade 2: Mild Diabetic Retinopathy

Ophthalmology: Diagnosis from Fundus Photographs

slide-8
SLIDE 8

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

The Source of Disagreements

Grade 3: Moderate Diabetic Retinopathy Grade 2: Mild Diabetic Retinopathy

Random Mistakes? Ophthalmology: Diagnosis from Fundus Photographs

slide-9
SLIDE 9

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

The Source of Disagreements

Diagnosis Type Diagnosis Type Fraction of votes Patient 1 Patient 2

slide-10
SLIDE 10

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

ML for Doctor Disagreement Prediction

Given input (image) x, predict the amount of disagreement. Flag patients for medical second opinions.

slide-11
SLIDE 11

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

ML for Doctor Disagreement Prediction

Given input (image) x, predict the amount of disagreement. Flag patients for medical second opinions. Training data: xi, with multiple labels y(i)

1,...,y(i) k (different

doctors) I.e. (xi, pi), pi grade distribution, target U(pi) (e.g. U() = entropy)

slide-12
SLIDE 12

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

ML for Doctor Disagreement Prediction

Given input (image) x, predict the amount of disagreement. Flag patients for medical second opinions. Training data: xi, with multiple labels y(i)

1,...,y(i) k (different

doctors) I.e. (xi, pi), pi grade distribution, target U(pi) (e.g. U() = entropy) 1) Uncertainty Via Classification (UVC): (i) train classifier on empirical distribution of labels (xi, pi) (ii) postprocess with U() 2) Direct Uncertainty Prediction (DUP): directly predict scalar uncertainty score (xi, U(pi))

slide-13
SLIDE 13

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Direct Uncertainty Prediction

slide-14
SLIDE 14

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Direct Uncertainty Prediction

Hidden information:

61 (age) F (gender) medical history

slide-15
SLIDE 15

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Direct Uncertainty Prediction

Theorem: DUP gives an unbiased estimate of true uncertainty

slide-16
SLIDE 16

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Empirical Results: Synthetic Examples

Mixture of Gaussians SVHN and CIFAR-10: Image Blurring Application

slide-17
SLIDE 17

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Large Scale Medical Application

Diabetic Retinopathy (DR) 5 class scale: 1 None 2 Mild 3 Moderate 4 Severe 5 Proliferative

Referable

slide-18
SLIDE 18

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Large Scale Medical Application

slide-19
SLIDE 19

Poster #246: Direct Uncertainty Prediction for Medical Second Opinions

Large Scale Medical Application

Small Gold Standard Evaluation Set Individual Grades by Specialists

3 2 2 3

Single, Consensus, Adjudicated Grade

Poster #246