quiz bu lëkkale ak tegtal · Diggante Niveau

Dañuy jàngat jumtukaayi IA ci wàllu pajum ni quiz clinician

Test yiy àtte done yiñ gëmloo jaaykat yi, lu tax valeur prédictif bu baax ak etalonnage am solo ci gox bi, ak li FDA 510(k) clearance di wane.

Laaj 1 de 8

Benn jaaykat dafa xamle AUC bu 0.85 ci xeetu yàqu-yàqu bi. Lan la guide bi wax nimero bii mënul wax hopitaal bi?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Benn jaaykat dafa xamle AUC bu 0.85 ci xeetu yàqu-yàqu bi. Lan la guide bi wax nimero bii mënul wax hopitaal bi?
    • How well the model ranks cases in the vendor's own dataset
    • Whether the model was built with machine learning
    • How the tool will behave with the hospital's own patients, workflow and alert threshold
    • Whether the model can be installed in an EHR
  2. Lan lañu gis ci 2021 ci wàllu sepsis buñ siiwal ci JAMA Internal Medicine?
    • Much weaker discrimination than the developer reported, with many missed cases and frequent alerts
    • Performance identical to the developer's figures
    • Better performance at the external site than at the development site
    • That the FDA had revoked the model's clearance
  3. Amna luñu xool bu baax ci 10 ci teemeer boo jél ci malaad yi. Lan moo waral mu mëna defar ay njuumte yu bari ci benn jumtukaay bu 2 pursaa kese ñoo am feebar bi?
    • Calibration always improves at lower prevalence
    • AUC automatically falls when prevalence falls
    • Sensitivity rises sharply at lower prevalence
    • Positive predictive value depends on prevalence, so a larger share of alerts are false when the condition is rarer
  4. Buñu sukkandikoo ci tegtal bi, ban yoon la aparey medikaal yu bari yu IA di jëfandikoo ngir yegg ci marse Etats Unis?
    • Premarket approval backed by randomized trials
    • The 510(k) pathway, based on substantial equivalence to an existing device
    • No FDA review of any kind
    • Emergency use authorization
  5. Luy jëfandikoo ab modelu IA klinik bu noppi wala lëndëm?
    • Muting the sound on alert notifications
    • A vendor updating the model without telling the customer
    • Letting the model score live patients without showing results to clinicians, so local performance can be measured
    • Running the model only during overnight shifts
  6. A dermatology group learns that darker skin tones were rare in a classifier's training images. Which evaluation area does this concern?
    • Post-deployment monitoring
    • Bias, meaning performance across patient subgroups
    • Regulatory status
    • Alert threshold selection
  7. A model assigns 30 percent risk to a group of patients, but only 10 percent of them go on to have the outcome. What problem does this show?
    • A low AUC, necessarily
    • Substantial equivalence failure
    • High positive predictive value
    • Poor calibration
  8. After go-live, a hospital switches to a new lab assay and the values feeding the model shift. What does the guide call this, and how should it be handled?
    • Input drift, which ongoing monitoring should detect
    • Algorithm aversion, which training should fix
    • Substantial equivalence, which the FDA handles
    • Prevalence shift, which needs no action