A framework using autoencoders quantifies patient-level similarity to development data and measures predictive model performance across similarity subgroups to distinguish case-mix effects from model deficiencies in external validation.
Advances in neural information processing systems 2018, 31
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Rethinking external validation for the target population: Capturing patient-level similarity with a generative model
A framework using autoencoders quantifies patient-level similarity to development data and measures predictive model performance across similarity subgroups to distinguish case-mix effects from model deficiencies in external validation.