Document Detail

Automated decision tree classification of corneal shape.
MedLine Citation:
PMID:  16357645     Owner:  NLM     Status:  MEDLINE    
PURPOSE: The volume and complexity of data produced during videokeratography examinations present a challenge of interpretation. As a consequence, results are often analyzed qualitatively by subjective pattern recognition or reduced to comparisons of summary indices. We describe the application of decision tree induction, an automated machine learning classification method, to discriminate between normal and keratoconic corneal shapes in an objective and quantitative way. We then compared this method with other known classification methods.
METHODS: The corneal surface was modeled with a seventh-order Zernike polynomial for 132 normal eyes of 92 subjects and 112 eyes of 71 subjects diagnosed with keratoconus. A decision tree classifier was induced using the C4.5 algorithm, and its classification performance was compared with the modified Rabinowitz-McDonnell index, Schwiegerling's Z3 index (Z3), Keratoconus Prediction Index (KPI), KISA%, and Cone Location and Magnitude Index using recommended classification thresholds for each method. We also evaluated the area under the receiver operator characteristic (ROC) curve for each classification method.
RESULTS: Our decision tree classifier performed equal to or better than the other classifiers tested: accuracy was 92% and the area under the ROC curve was 0.97. Our decision tree classifier reduced the information needed to distinguish between normal and keratoconus eyes using four of 36 Zernike polynomial coefficients. The four surface features selected as classification attributes by the decision tree method were inferior elevation, greater sagittal depth, oblique toricity, and trefoil.
CONCLUSION: Automated decision tree classification of corneal shape through Zernike polynomials is an accurate quantitative method of classification that is interpretable and can be generated from any instrument platform capable of raw elevation data output. This method of pattern classification is extendable to other classification problems.
Michael D Twa; Srinivasan Parthasarathy; Cynthia Roberts; Ashraf M Mahmoud; Thomas W Raasch; Mark A Bullimore
Related Documents :
17958935 - Feasibility of a telemedicine framework for collaborative pacemaker follow-up.
17254295 - Nerbio: using selected word conjunctions, term normalization, and global patterns to im...
12054835 - Two notions of conspicuity and the classification of phyllotaxis.
10566315 - Aggregation and reclassification--assessment of galen methods in the domain of thoracic...
19847795 - Meta-analysis of genome-wide association studies: no efficiency gain in using individua...
15275495 - Use of pcr in the field.
Publication Detail:
Type:  Comparative Study; Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  Optometry and vision science : official publication of the American Academy of Optometry     Volume:  82     ISSN:  1040-5488     ISO Abbreviation:  Optom Vis Sci     Publication Date:  2005 Dec 
Date Detail:
Created Date:  2005-12-16     Completed Date:  2006-01-24     Revised Date:  2014-09-08    
Medline Journal Info:
Nlm Unique ID:  8904931     Medline TA:  Optom Vis Sci     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1038-46     Citation Subset:  IM    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Cornea / pathology*
Corneal Topography
Decision Trees*
Keratoconus / classification*,  pathology
Reproducibility of Results
Retrospective Studies
Grant Support

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  The agreement and repeatability of tear meniscus height measurement methods.
Next Document:  Orbscan global pachymetry: analysis of repeated measures.