Skip to main content

Table 3 Assessment of test items using the preliminary conceptual framework for establishing content validity of AI-generated test items (integrated case clusters, SAQs and OSPEs)

From: Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study

Types of errors

Sage Poe©

Chart GPT©

Claude-Instant©

Pre-clerkship

At graduation

Pre-clerkship

At graduation

Pre-clerkship

At graduation

Integrated case cluster

Technical accuracy

Complete

Complete

Complete

Complete

Deficient

Complete a

Comprehensiveness

Deficient

Deficient

Deficient

Deficient

Deficient

Deficient a

Education level

Complete

Deficient

Deficient

Deficient

Complete

Complete a

Free of construction defects

Deficient

Deficient

Deficient

Deficient

Deficient

Complete a

Short answer questions

Technical accuracy

Complete

Complete

Complete

Complete

Complete

Complete

Comprehensiveness

Complete

Complete

Complete

Complete

Complete

Complete

Education level

Complete

Deficient

Complete

Deficient

Complete

Complete

Free of construction defects

Deficient

Deficient

Deficient

Deficient

Deficient

Complete

OSPEs

Technical accuracy

Not Available

Complete

Complete

Complete

Complete

Comprehensiveness

Complete

Complete

Complete

Complete

Education level

Complete

Complete

Complete

Complete

Free of construction defects

Complete

Complete

Complete

Complete

  1. a- Only a small portion of the requested test items were provided by the concerned AI tool