Quiz collegato alla guida · Difficile Livello

Utilizzo di ChatGPT per il quiz di diagnosi differenziale

Verifica ciò che gli studi Kanjee e Goh hanno scoperto sulla diagnosi GPT-4, perché i benchmark delle vignette sopravvalutano l'accuratezza del posto letto e come l'ancoraggio influisce sui suggerimenti.

Domanda 1 di 8

Nel test del 2023 di Kanjee e colleghi di GPT-4 su casi clinicopatologici NEJM, quanto spesso è stata la diagnosi finale in qualsiasi punto del differenziale del modello?

Anteprima di ogni domanda8 domande

Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.

  1. Nel test del 2023 di Kanjee e colleghi di GPT-4 su casi clinicopatologici NEJM, quanto spesso è stata la diagnosi finale in qualsiasi punto del differenziale del modello?
    • About 39 percent
    • About 64 percent
    • About 92 percent
    • About 15 percent
  2. Qual è stato il risultato principale dello studio Goh et al. studio randomizzato?
    • Physicians given GPT-4 scored far higher than those without it
    • GPT-4 alone performed worse than every physician
    • Giving physicians GPT-4 did not significantly improve their diagnostic reasoning scores, although GPT-4 alone scored higher
    • The trial was stopped for patient harm
  3. Perché i parametri di riferimento delle vignette possono sopravvalutare il rendimento di un modello con pazienti reali?
    • Vignettes arrive with the relevant findings already chosen and cleaned up, and published cases may be in training data
    • Vignettes are always written in another language
    • Real patients have fewer symptoms than vignettes
    • Models cannot read case descriptions longer than a paragraph
  4. A clinician asks, "Could this be lupus?" at the start of her prompt. Which failure mode does this invite?
    • Invented laboratory reference ranges
    • Refusing to answer medical questions
    • Losing the conversation history
    • Sycophantic anchoring toward the diagnosis the user suggested
  5. Why is scoring "correct diagnosis anywhere in the list" a flawed measure?
    • It rewards long lists, which can prompt unnecessary testing
    • It ignores the patient's age
    • It only works for pediatric cases
    • It requires the model to cite references
  6. Getting two differently ordered lists from nearly identical prompts shows what about the model's ranking?
    • The model is broken and should not be used
    • The second answer is always the correct one
    • The ranking is not a calibrated probability estimate and shifts with wording
    • The model is searching the live internet
  7. What is the main privacy concern with pasting a patient's chart into a consumer chatbot?
    • The chatbot will refuse clinical questions
    • Entering identifiable information without a business associate agreement can breach HIPAA
    • Consumer chatbots cannot read lab values
    • It automatically bills the patient's insurer
  8. Which prompt request best helps a clinician act on a model's differential?
    • "Give me the single correct diagnosis"
    • "Confirm my diagnosis is right"
    • "Write the discharge summary"
    • "List supporting and contradicting features for each item and the test that best separates the top candidates"