TY - JOUR
T1 - Detection of subclinical keratoconus using an automated decision tree classification
AU - Smadja, David
AU - Touboul, David
AU - Cohen, Ayala
AU - Doveh, Etti
AU - Santhiago, Marcony R.
AU - Mello, Glauco R.
AU - Krueger, Ronald R.
AU - Colin, Joseph
PY - 2013/8
Y1 - 2013/8
N2 - Purpose: To develop a method for automatizing the detection of subclinical keratoconus based on a tree classification. Design: Retrospective case-control study. Methods: setting: University Hospital of Bordeaux. participants: A total of 372 eyes of 197 patients were enrolled: 177 normal eyes of 95 subjects, 47 eyes of 47 patients with forme fruste keratoconus, and 148 eyes of 102 patients with keratoconus. observation procedure: All eyes were imaged with a dual Scheimpflug analyzer. Fifty-five parameters derived from anterior and posterior corneal measurements were analyzed for each eye and a machine learning algorithm, the classification and regression tree, was used to classify the eyes into the 3 above-mentioned conditions. main outcome measures: The performance of the machine learning algorithm for classifying eye conditions was evaluated, and the curvature, elevation, pachymetric, and wavefront parameters were analyzed in each group and compared. Results: The discriminating rules generated with the automated decision tree classifier allowed for discrimination between normal and keratoconus with 100% sensitivity and 99.5% specificity, and between normal and forme fruste keratoconus with 93.6% sensitivity and 97.2% specificity. The algorithm selected as the most discriminant variables parameters related to posterior surface asymmetry and thickness spatial distribution. Conclusion: The machine learning classifier showed very good performance for discriminating between normal corneas and forme fruste keratoconus and provided a tool that is closer to an automated medical reasoning. This might help in the surgical decision before refractive surgery by providing a good sensitivity in detecting ectasia-susceptible corneas.
AB - Purpose: To develop a method for automatizing the detection of subclinical keratoconus based on a tree classification. Design: Retrospective case-control study. Methods: setting: University Hospital of Bordeaux. participants: A total of 372 eyes of 197 patients were enrolled: 177 normal eyes of 95 subjects, 47 eyes of 47 patients with forme fruste keratoconus, and 148 eyes of 102 patients with keratoconus. observation procedure: All eyes were imaged with a dual Scheimpflug analyzer. Fifty-five parameters derived from anterior and posterior corneal measurements were analyzed for each eye and a machine learning algorithm, the classification and regression tree, was used to classify the eyes into the 3 above-mentioned conditions. main outcome measures: The performance of the machine learning algorithm for classifying eye conditions was evaluated, and the curvature, elevation, pachymetric, and wavefront parameters were analyzed in each group and compared. Results: The discriminating rules generated with the automated decision tree classifier allowed for discrimination between normal and keratoconus with 100% sensitivity and 99.5% specificity, and between normal and forme fruste keratoconus with 93.6% sensitivity and 97.2% specificity. The algorithm selected as the most discriminant variables parameters related to posterior surface asymmetry and thickness spatial distribution. Conclusion: The machine learning classifier showed very good performance for discriminating between normal corneas and forme fruste keratoconus and provided a tool that is closer to an automated medical reasoning. This might help in the surgical decision before refractive surgery by providing a good sensitivity in detecting ectasia-susceptible corneas.
UR - http://www.scopus.com/inward/record.url?scp=84880569913&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84880569913&partnerID=8YFLogxK
U2 - 10.1016/j.ajo.2013.03.034
DO - 10.1016/j.ajo.2013.03.034
M3 - Article
C2 - 23746611
AN - SCOPUS:84880569913
VL - 156
SP - 237-246.e1
JO - American Journal of Ophthalmology
JF - American Journal of Ophthalmology
SN - 0002-9394
IS - 2
ER -