View abstract

Cet abstract a été assigné à session AOB Free Papers 1

Type de présentation	Oral presentation
Titre	Training the “Cone Location and Magnitude Index Expanded” on Keratoconus Suspect Eyes using Machine Learning

But	To use artificial intelligence in retraining the Cone Location and Magnitude Index Expanded to detect keratoconus suspect corneas.
Méthodes	349 eyes of 349 patients from the American University of Beirut Medical Center were included in the study, with 133 eyes with normal control corneas (NL), 147 eyes with definite keratoconus (KC), and 75 eyes with keratoconus suspect corneas (KCS). KCS corneas were normal fellow eyes of patients with highly asymmetric keratoconus. Different parameters from anterior, posterior corneal map and pachymetry were used.
Résultats	Using logistic regression, the machine learning model trained on three categories of eyes achieved a sensitivity of 67%, specificity of 87%, positive predictive value (PPV) of 58%, and F1 score of 0.62 in detecting KCS. A new artificial intelligence algorithm (CatBoost) scored 71% of sensitivity, 91% of specificity, a PPV of 68% and F1 score of 0.70, while using the same parameters incorporated in the original index.
Conclusion	Artificial intelligence improves the performance of the Cone Location and Magnitude Index Expanded in detecting early suspicion of keratoconus.
Conflit d'intérêt	Non
Détails conflits d'intérêt	None

Auteurs 1

Nom	WEHBI
Initiales	Z
Institut	American University of Beirut
Ville	Beirut, Lebanon

Auteurs 2

Nom	Hammoud
Initiales	B
Institut	American University of Beirut
Ville	Beirut, Lebanon

Auteurs 3

Nom	Assaf
Initiales	J.F
Institut	Casey Eye Institute
Ville	Portland, Oregon

Auteurs 4

Nom	Awwad
Initiales	S.T
Institut	American University of Beirut
Ville	Beirut, Lebanon