OCT-based optic neuropathy diagnosis using explainable and privacy-preserving machine learning.

AI / informaticsScientific reports· May 2026

OCT-based optic neuropathy diagnosis using explainable and privacy-preserving machine learning.

Md Mahmudul Hasan, Jack Phu, Henrietta Wang … Arcot Sowmya

Read paper

Neuro-ophthalmologyAI / informaticsDiagnosisQ1IF 5.0

Machine learning diagnosed optic neuropathy from optical coherence tomography scans more accurately than clinicians did.

OCT-based optic neuropathy diagnosis using explainable and privacy-preserving machine learning.

Md Mahmudul Hasan … Arcot Sowmya

Scientific reports · May 2026

Background

Glaucoma shares similarities with neurodegenerative conditions like dementia, Parkinson's disease, and ischaemic optic neuropathy, which affect ocular health.

26.3%

Results

26.3%

machine caught more optic-nerve damage cases than eye doctors did

More results

However, current studies exclude neurodegenerative cases in neuropathy diagnosis and rely on 'black box' models.

A team of three clinicians, with 12, 11, and 6 years of experience, evaluated their performance on the same dataset for a human versus machine comparison, with the machine achieving an area under the curve of 0.90 for classifying neuropathy.

“

Conclusion

In conclusion, both non-explainable and explainable methods show promise in enhancing diagnostic support for clinical decision-making, with the privacy-preserving approach safeguarding data privacy.

OCT-based optic neuropathy diagnosis using explainable and privacy-preserving machine learning.

OCT-based optic neuropathy diagnosis using explainable and privacy-preserving machine learning.

Related papers