Reliability analysis of successive Corneal Visualization Scheimpflug Technology measurements in different keratoconus stages

BACKGROUND

This study assesses the reliability of successive corneal biomechanical response measurements by the Corneal Visualization Scheimpflug Technology (CST, Corvis ST^® , Oculus Optikgeräte, Wetzlar, Germany) in different keratoconus (KC) stages.

METHODS

A total of 173 eyes (15 controls: 15 eyes, and 112 KC patients: stages 1|1-2|2|2-3|3|3-4|4, n = 26|16|36|18|31|26|5 according to Topographical KC Classification, TKC) were repeatedly examined five times with the CST, each after repositioning the patient's head and re-adjusting the device. Tomographical analysis (Pentacam HR^® ; Oculus, Wetzlar, Germany) was performed once before and once after CST measurements. Outcome measures included (1) A1 velocity, (2) deformation amplitude (DA) ratio 2 mm, (3) integrated radius, (4) stiffness parameter A1 and (5) Ambrósio relational thickness to the horizontal profile (ARTh). The Corvis Biomechanical Index (CBI) is reported to be extracted out of these parameters. Mean values of the five measurements and Cronbach's α were calculated as a measure for reliability.

RESULTS

Ambrósio relational thickness to the horizontal profile and SPA1 were significantly higher in controls (534|123) compared to TKC1 (384|88), TKC2 (232|66), TKC3 (152|55) and TKC4 (71|27; p < 0.0001). The other parameters were similar in controls and TKC1 (A1 velocity: 0.148|0.151 m/s; integrated radius: 8.2|8.6 mm^-1 ), but significantly higher in TKC stages 2 to 4 (DA ratio 2 mm: 5.5|6.3|8.0; A1 velocity: 0.173|0.174|0.186 m/second; integrated radius: 10.9|12.8|19.0 mm^-1 ; p < 0.0001). All parameters proved to be highly reliable (Cronbach's α ≥ 0.834) and the corneal tomography remained unaffected.

CONCLUSIONS

The individual parameters included in the CBI (consisting of ARTh, SPA1, DA ratio 2 mm, A1 velocity and integrated radius) are highly reliable but differ KC stage-dependently.

[Keratoconus detection and classification from parameters of the Corvis®ST : A study based on algorithms of machine learning]

BACKGROUND AND OBJECTIVE

In the last decades increasingly more systems of artificial intelligence have been established in medicine, which identify diseases or pathologies or discriminate them from complimentary diseases. Up to now the Corvis®ST (Corneal Visualization Scheimpflug Technology, Corvis®ST, Oculus, Wetzlar, Germany) yielded a binary index for classifying keratoconus but did not enable staging. The purpose of this study was to develop a prediction model, which mimics the topographic keratoconus classification index (TKC) of the Pentacam high resolution (HR, Oculus) with measurement parameters extracted from the Corvis®ST.

PATIENTS AND METHODS

In this study 60 measurements from normal subjects (TKC 0) and 379 eyes with keratoconus (TKC 1-4) were recruited. After measurement with the Pentacam HR (target parameter TKC) a measurement with the Corvis®ST device was performed. From this device 6 dynamic response parameters were extracted, which were included in the Corvis biomechanical index (CBI) provided by the Corvis®ST (ARTh, SP-A1, DA ratio 1 mm, DA ratio 2 mm, A1 velocity, max. deformation amplitude). In addition to the TKC as the target, the binarized TKC (1: TKC 1-4, 0: TKC 0) was modelled. The performance of the model was validated with accuracy as an indicator for correct classification made by the algorithm. Misclassifications in the modelling were penalized by the number of stages of deviation between the modelled and measured TKC values.

RESULTS

A total of 24 different models of supervised machine learning from 6 different families were tested. For modelling of the TKC stages 0-4, the algorithm based on a support vector machine (SVM) with linear kernel showed the best performance with an accuracy of 65.1% correct classifications. For modelling of binarized TKC, a decision tree with a coarse resolution showed a superior performance with an accuracy of 95.2% correct classifications followed by the SVM with linear or quadratic kernel and a nearest neighborhood classifier with cubic kernel (94.5% each).

CONCLUSION

This study aimed to show the principle of supervised machine learning applied to a set-up for the modelled classification of keratoconus staging. Preprocessed measurement data extracted from the Corvis®ST device were used to mimic the TKC provided by the Pentacam device with a series of different algorithms of machine learning.