Table 2

Feasibility of application and validation efforts of subtype classifications from data driven studies

Criterion	Graham 19993	Gasparoli 20024	Dujardin 20045	Lewis 20056	Schrag 20067	Post 20088	Reijnders 20099	Van Rooden 201110	Liu 201111
Subtypes reproduced in independent cohort?	n/a	n/a	n/a	Yes^‡	n/a	n/a	Yes	Yes	n/a
Algorithm for classification derived?	No	No	Yes	No^‡	No	No	No	Yes	No
Percentage of cohort correctly classified by algorithm in independent cohort?	n/a	n/a	n/a	n/a	n/a	n/a	n/a	77	n/a
Distinguishing clinical/demographic features^*	No	Yes	Yes	Yes	Yes	Yes	Yes	Yes	No
Distinguishing pathological features^†	n/a	n/a	n/a	Yes^‡	n/a	n/a	n/a	n/a	n/a

↵* Were subtypes distinguishable on the basis of clinical or demographic features not included in the derivation of the clusters? (See text for details).
↵† Were subtypes distinguishable on the basis of pathological findings?
↵‡ By Selikhova et al 13
n/a, not assessed.