Keratoconus, Machine Learning
Conditions
Keywords
keratoconus, machine learning
Brief summary
Keratoconus (KC) is a bilateral ocular disease characterized by progressive thinning and steepening of the cornea, usually in its inferotemporal region. The disease often occurs asymmetrically as one eye is more severely affected by the condition. The changes underlying KC lead to the generation of irregular astigmatism resulting in diminished visual acuity of the patients and can even lead to axial corneal scarring in advanced stages. The disease usually occurs in the second or third decade of life, but can develop at any age. KC is a complex condition involving environmental factors such as age, eye rubbing, contact lens use, atopy, sun exposure, hormones, toxins, as well as a genetic component. However, how these factors contribute to the disease is still unknown and intraindividual differences might exist. KC can be categorized into different forms based on the stage of the disease. In clinical KC, there are both topographic and slit lamp findings of the disease. The importance of corneal epithelial imaging in the diagnosis of keratoconus has been further demonstrated in several clinical studies. As new anterior segment optical coherence tomography (AS-OCT) devices provide more detailed measurements for instance of the corneal epithelium. This layer could therefore be an interesting marker for the prediction of KC progression and contribute to earlier diagnosis as well as better outcome of the disease. The aim of this retrospective study is therefore to determine whether different topographical and volumetric data, for instance epithelial thickness maps (ETM), can be reliably used to predict the progression of KC using a machine learning algorithm.
Interventions
DIAGNOSTIC_TESTMS-39
The MS-39 (Costruzione Strumenti Oftalmici, Firenze, Italy) is a device for anterior segment analysis of the eye, which combines Placido disc corneal topography and high-resolution SD-OCT. The device provides information on pachymetry, elevation, curvature, and dioptric power of both corneal surfaces. To obtain corneal topography, 22 Placido disc rings are emanated from a laser emitted diode (LED) light source at 635 nanometres (nm). The central 10 millimetres of the anterior corneal surface are covered. Epithelial thickness maps are calculated for different sectors (central, paracentral inferior/superior/nasal/temporal).
Sponsors
Vienna Institute for Research in Ocular Surgery
Study design
Observational model
OTHER
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Healthy volunteers
No
Inclusion criteria
* Patients with KC progression as defined dependent on Kmax/year: o 1. Kmax \< 48 Dioptres (D): \>0.5 D per year o 2. Kmax 48.01-53 D: \>0.6 D per year o 3. Kmax 53.01-58 D: \>0.8 D per year o 4. Kmax \> 58 D: \>1.5 D per year - Non progressive group: Patients with stable KC (KC progression dependent on Kmax \< than the values described above/year)
Exclusion criteria
* Relevant other ophthalmic diseases that are likely to influence the measurement outcome like corneal scars or epithelial dystrophies * Too few measurements/too short follow-up to define progression of KC
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Sensitivity of the machine learning algorithm on the final test data set | through study completion, one year | Sensitivity of the machine learning algorithm on the final test data set to differentiate between progressive/non-progressive eyes based on Kmax-change per year |
| Specificity of the machine learning algorithm on the final test data set | through study completion, one year | Specificity of the machine learning algorithm on the final test data set to differentiate between progressive/non-progressive eyes based on Kmax-change per year |
Countries
Austria
Outcome results
None listed