View abstract

Cet abstract a été assigné à sessions
TitreA new nomogram for laser corneal refractive surgery based on Artificial intelligence
ButTo predict delta between programmed laser treatment and really delivered treatment.
To compare the predicted delta with the wavelight nomogram
To study relative importance of each preoperative parameter.
MéthodesWe reviewed 2728 myopic eyes operated with Wavelight Refractive Suite. Preoperative and one-month postoperative refractions and programmed treatment defined the observed delta. Delta is then predicted from clinical, laser and topographical preoperative parameters using machine learning regression algorithm.
RésultatsMachine learning nomogram reduced the error and improve outcomes. Outcomes are also improved after using machine learning and Wavelight nomogram.
Programmed spherical equivalent is the more influential parameter to predict sphere and programmed astigmatism is the more influential parameter to predict cylinder.
ConclusionMachine learning could allow to increase laser treatment accuracy and our understanding of causes of residual errors.
Conflit d'intérêtNon
Auteur 1
NomCRAHAY
InitialesF-X
InstitutCHR Citadelle
VilleLiège
Auteur 2
NomDebellemaniere
InitialesG
InstitutFondation Ophtalmologique Adolphe de Rothschild
VilleParis
Auteur 3
NomRampat
InitialesR
InstitutFondation Ophtalmologique Adolphe de Rothschild
VilleParis
Auteur 4
NomMoran
InitialesS
InstitutFondation Ophtalmologique Adolphe de Rothschild
VilleParis
Auteur 5
NomGatinel
InitialesD
InstitutFondation Ophtalmologique Adolphe de Rothschild
VilleParis
top ^