Skip to main content

Table 1 Clinical trial versus Real-world datasets for AI evaluation

From: A framework for validating AI in precision medicine: considerations from the European ITFoC consortium

  

Clinical trial datasets

Real-world datasets

Setting

 

Experimental

Real world

Population

Representativeness

Selective sample

Large sample

Type

Homogeneous

Heterogeneous

Size

+/−

++++

Time period for recruitment and follow-up

Limited

Long

Data

Type

Clinical +/− -omics

Clinical +/− -omics

Collected by

Dedicated specialist professionals

Various healthcare professionals

Quality

+++

+/−

Need for data management

+/−

+++

Need for anonymization

+

+