Lab 2: medical screening under extreme cost asymmetry

72 min
Block 22 — Guided laboratories
Objective
build, evaluate and operate a two-stage medical screening classifier on a cohort whose prevalence is 1.5 percent, whose missing values are informative rather than accidental, and whose enrollment sites do not supply data of equal quality; derive the operating threshold from the clinical consequence of a miss rather than from any statistical optimum; confront the measured fact that a model with an AUC of 0.9327 produces a positive predictive value of 0.0417 at the required sensitivity; measure the subgroup performance gap and evaluate three honest responses to it; compute the end-to-end characteristics of the screen-then-confirm cascade including the confirmatory test's own imperfection; and produce the clinical summary in the vocabulary a clinical committee uses — likelihood ratios, pre-test and post-test probabilities, and volumes per ten thousand people screened.
Estimated duration
180 minutes
Prerequisites
chapters 018, 019, 026, 028, 034, 036, 050, 052, 054, 055, 056, 058, 062, 063, 064, 075, 076, 079, 080 and 082, and lab 1 (085.0-lab01-churn-classification.md)
Associated quizzes
086.1-quiz-screening-versus-diagnosis.md to 086.9-quiz-clinical-reporting.md

Preview — the rest of the lesson is for enrolled readers.

Already enrolled with a code?

Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.

Sign inNo account yet? Create one
This lesson is part of the “Hands-on Labs” module

The first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.

Are you a student on this course?

The code is tied to your account: sign in or create an account and it will be applied automatically when you come back.

No account yet? Create one