Latent Supervision: A Method for Improved Performance and Calibration of Machine Learning Classification Models in Ophthalmology

Purpose: Standard supervised learning assumes deterministic labels (e.g., positive or negative, present or absent), neglecting the diagnostic uncertainty inherent in clinical practice. We propose latent supervision, a novel algorithm which applies latent class analysis to incorporate multiple diagno...

Volledige beschrijving

Bibliografische gegevens

Hoofdauteurs:	Hady Yazbeck, MD, Jad Assaf, MD, Tom M. Lietman, MD, Jeremy D. Keenan, MD, John Jackson, MD, Jayashree Kalpathy-Cramer, PhD, J. Peter Campbell, MD, Xubo Song, PhD, Travis K. Redd, MD
Formaat:	Artigo
Taal:	Inglês
Gepubliceerd in:	Elsevier 2026-05-01
Reeks:	Ophthalmology Science
Onderwerpen:	Latent class analysis Artificial intelligence Trachoma Infectious keratitis
Online toegang:	http://www.sciencedirect.com/science/article/pii/S2666914526000898
Tags:	Voeg label toe Geen labels, Wees de eerste die dit record labelt!