Detection of Subclinical Keratoconus Using an Automated Decision Tree Classification

Smadja, David; Touboul, David; Cohen, Ayala; Doveh, Etti; Santhiago, Marcony R.; Mello, Glauco Reggiani; Krueger, Ronald R.; Colin, Joseph

doi:10.1016/j.ajo.2013.03.034

Cited by 210 publications

(175 citation statements)

References 23 publications

Supporting

Mentioning

173

Contrasting

Unclassified

Order By: Relevance

“…In addition, TMS-5 topographic maps showed a keratoconic appearance. Subjects were included in the forme fruste keratoconus group when they had no topographic or clinical signs of keratoconus in one eye, but presented a diagnosis of keratoconus in the contralateral eye 3–5 20. Additionally, all patients enrolled in the forme fruste keratoconus group had to pass through the two TMS-5 keratoconus screening programmes with 0% Keratoconus Index and Keratoconus Severity Index (no topographic signs).…”

Section: Methodsmentioning

confidence: 99%

Comparison of three-dimensional optical coherence tomography and combining a rotating Scheimpflug camera with a Placido topography system for forme fruste keratoconus diagnosis

et al. 2013

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Comparison of three-dimensional optical coherence tomography and combining a rotating Scheimpflug camera with a Placido topography system for forme fruste keratoconus diagnosis

et al. 2013

View full text Add to dashboard Cite

show abstract

“…The one developed for discriminating between normals and mild (subclinical) keratoconus had 93.6% sensitivity and 97.2% specificity. 24 However, this is fundamental to validate such approaches in a new set of cases. In another study, a combination of corneal topography (I-S value) and minimum pachymetry from OCT was statistically the most significant in separating the ectatic from normal eyes.…”

Section: Enhanced Screening For Ectasia Susceptibilitymentioning

confidence: 99%

“…While this may be a challenging and complex task for the clinician to combine the data from different sources, artificial intelligence techniques, such as neural network (NN), decision tree (DT), support vector machine (SVM), and regression analysis have been used to facilitate clinical decisions. 8,18,24,27,30 In a retrospective case control study, 177 normal eyes were compared to 148 eyes with clinical keratoconus and to 47 eyes with normal topography from 47 patients with clinical keratoconus in the fellow eye using the Galilei. A total of 55 parameters were analyzed so that a machine learning algorithm was created using a DT approach.…”

Section: Enhanced Screening For Ectasia Susceptibilitymentioning

confidence: 99%

Enhanced Screening for Ectasia Risk prior to Laser Vision Correction

Belin¹,

Ambrósio²

2017

International Journal of Keratoconus and Ectatic Corneal Diseases

View full text Add to dashboard Cite

Aim: To prospectively review current understanding and future trends of screening for keratectasia risk prior refractive laser vision correction (LVC).Background: Progressive keratectasia is an uncommon but severe complication of LVC. Preoperative ectatic corneal disease is the most important risk factor. Screening for subclinical ectasia relies on proper interpretation of advanced diagnostic technologies, including front surface corneal topography, three-dimensional tomography, and biomechanical assessments.Summary: Studies involving eyes with normal and stable corneas, compared to eyes with frank ectatic diseases and to eyes with normal topography from patients with very asymmetric ectasia, allow for developing advanced methods and testing its sensitivity. However, the ideal study populations for testing the sensitivity and specificity of ectasia risk assessments are respectively the preoperative of cases that developed ectasia and the ones with stable outcomes after LVC. Young age and low thickness are surrogates of corneal biomechanics, which may be replaced as risk factors by direct measurements. Keratectasia may also occur due to the surgical impact on corneal structure or due to significant trauma postoperatively. Percentage tissue altered higher than 40% is a more sensitive para meter than a fixed value for minimal residual stromal bed of 250 µm. However, the biomechanical impact from surgery is related to the region and number of lamellae that are severed, so that flap thickness and geometry should play a more relevant role, which is in agreement with finite element simulations. Arti ficial intelligence methods allow for combining parameters, which significantly enhance the accuracy for detecting ectasia risk. Conclusion:An enhanced screening approach for preventing keratectasia should consider both preoperative patient-related data and procedure-related parameters to individually characterize ectasia susceptibility or predisposition.Clinical Significance: Keratectasia is an uncommon, however, severe complication of LVC. Although prevention is the best strategy, an individualized enhanced ectasia screening approach for ectasia risk assessment prior to LVC procedures should integrate patient-related (individual ectasia susceptibility) and procedure-related parameters (biomechanical impact).

show abstract

“…2 The literature on the Galilei analyzer is limited. [2][3][4] The Visante Omni system (Carl Zeiss Meditec AG) was introduced in 2009 and combines Atlas 9000…”

mentioning

confidence: 99%

Intraobserver repeatability and interobserver reproducibility of corneal measurements in normal eyes using an optical coherence tomography–Placido disk device

Shah

Han

Htoon

2015

Journal of Cataract and Refractive Surgery

View full text Add to dashboard Cite

show abstract

Detection of Subclinical Keratoconus Using an Automated Decision Tree Classification

Cited by 210 publications

References 23 publications

Comparison of three-dimensional optical coherence tomography and combining a rotating Scheimpflug camera with a Placido topography system for forme fruste keratoconus diagnosis

Comparison of three-dimensional optical coherence tomography and combining a rotating Scheimpflug camera with a Placido topography system for forme fruste keratoconus diagnosis

Enhanced Screening for Ectasia Risk prior to Laser Vision Correction

Intraobserver repeatability and interobserver reproducibility of corneal measurements in normal eyes using an optical coherence tomography–Placido disk device

Contact Info

Product

Resources

About