Integration and fusion of standard automated perimetry and optical coherence tomography data for improved automated glaucoma diagnostics
2011

Improving Glaucoma Diagnosis with Data Fusion

Sample size: 260 publication 10 minutes Evidence: high

Author Information

Author(s): Bizios Dimitrios, Heijl Anders, Bengtsson Boel

Primary Institution: Skåne University Hospital, Lund University

Hypothesis

Can the integration of Standard Automated Perimetry (SAP) and Optical Coherence Tomography (OCT) data improve the accuracy of glaucoma diagnosis using Artificial Neural Networks (ANNs)?

Conclusion

Integrating parameters from both SAP and OCT significantly enhances the performance of ANNs in diagnosing glaucoma.

Supporting Evidence

  • The diagnostic accuracy from a combination of fused SAP and OCT data was 95.39%.
  • Fused OCT and combined fused OCT and SAP data provided similar AROC values of 0.978.
  • ANNs based on the OCT parameters did not perform significantly worse than those based on fused data.

Takeaway

This study shows that combining two types of eye tests can help doctors better identify glaucoma, a disease that affects vision.

Methodology

Data from 125 healthy individuals and 135 glaucoma patients were analyzed using ANNs with both fused and non-fused parameters from SAP and OCT.

Potential Biases

Potential bias from selection criteria and the reference standard used for diagnosing glaucoma.

Limitations

The study's reference standard for glaucoma diagnosis was based on optic nerve head morphology, which may not correlate perfectly with functional tests.

Participant Demographics

{"healthy":{"sample_size":125,"age":"64.65 ± 8.11","gender":"66 females, 59 males"},"glaucoma":{"sample_size":135,"age":"73.36 ± 7.81","gender":"79 females, 56 males"}}

Statistical Information

P-Value

p < 0.0001

Statistical Significance

p < 0.001

Digital Object Identifier (DOI)

10.1186/1471-2415-11-20

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication