A machine-learning model based on morphogeometric parameters for RETICS disease classification and GUI development

This work pursues two objectives: defining a new concept of risk probability associated with su_ering early-stage keratoconus, classifying disease severity according to the RETICS (Thematic Network for Co-Operative Research in Health) scale. It recruited 169 individuals, 62 healthy and 107 keratocon...

Descripción completa

Detalles Bibliográficos
Autores: Bolarín Guillén, José Miguel, Cavas Martínez, Francisco, Velázquez Blázquez, José Sebastián, Alió Sanz, Jorge Luciano
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2020
País:España
Institución:Universidad Politécnica de Cartagena(UPCT)
Repositorio:Repositorio Digital UPCT
OAI Identifier:oai:repositorio.upct.es:10317/9329
Acceso en línea:http://hdl.handle.net/10317/9329
https://www.mdpi.com/2076-3417/10/5/1874
Access Level:acceso abierto
Palabra clave:Scheimpflug
3D cornea model
Early keratoconus
Corrected Distance Visual Acuity (CDVA)
Expresión Gráfica en Ingeniería
3201.09 Oftalmología
1203.09 Diseño Con Ayuda del Ordenador
Descripción
Sumario:This work pursues two objectives: defining a new concept of risk probability associated with su_ering early-stage keratoconus, classifying disease severity according to the RETICS (Thematic Network for Co-Operative Research in Health) scale. It recruited 169 individuals, 62 healthy and 107 keratoconus diseased, grouped according to the RETICS classification: 44 grade I; 18 grade II; 15 grade III; 15 grade IV; 15 grade V. Di_erent demographic, optical, pachymetric and eometrical parameters were measured. The collected data were used for training two machine-learning models: a multivariate logistic regression model for early keratoconus detection and an ordinal logistic regression model for RETICS grade assessments. The early keratoconus detection model showed very good sensitivity, specificity and area under ROC curve, with around 95% for training and 85% for validation. The variables that made the most significant contributions were gender, coma-like, central thickness, high-order aberrations and temporal thickness. The RETICS grade assessment also showed high-performance figures, albeit lower, with a global accuracy of 0.698 and a 95% confidence interval of 0.623–0.766. The most significant variables were CDVA, central thickness and temporal thickness. The developed web application allows the fast, objective and quantitative assessment of keratoconus in early diagnosis and RETICS grading terms.