Retinal electroretinogram features can detect depression state and treatment response in adults: A machine learning approach.

BACKGROUND: Major depressive disorder (MDD) is a major public health problem. The retina is a relevant site to indirectly study brain functioning. Alterations in retinal processing were demonstrated in MDD with the pattern electroretinogram (PERG). Here, the relevance of signal processing and machine learning tools applied on PERG was studied. METHODS: PERG - whose stimulation is reversible checkerboards - was performed according to the International Society for Clinical Electrophysiology of Vision (ISCEV) standards in 24 MDD patients and 29 controls at the inclusion. PERG was recorded every 4 weeks for 3 months in patients. Amplitude and implicit time of P50 and N95 were evaluated. Then, time/frequency features were extracted from the PERG time series based on wavelet analysis. A statistical model has been learned in this feature space and a metric aiming at quantifying the state of the MDD patient has been derived, based on minimum covariance determinant (MCD) mahalanobis distance. RESULTS: MDD patients showed significant increase in P50 and N95 implicit time (p = 0,006 and p = 0,0004, respectively, Mann-Whitney U test) at the inclusion. The proposed metric extracted from the raw PERG provided discrimination between patients and controls at the inclusion (p = 0,0001). At the end of the follow-up at week 12, the difference between the metrics extracted on controls and patients was not significant (p = 0,07), reflecting the efficacy of the treatment. CONCLUSIONS: Signal processing and machine learning tools applied on PERG could help clinical decision in the diagnosis and the follow-up of MDD in measuring treatment response.

Exploration of the retinal nerve fiber layer thickness by measurement of the linear dichroism.

An electro-optic device mounted on a slit lamp to assess the degree of polarization of a light beam that has double passed through the retina about the optic-nerve head in the living human eye is described. The asymmetric structure of the retinal nerve's fiber layer possesses a linear-form dichroism and will partially polarize an unpolarized light beam that is scattered at the fundus of the eye and has double passed the ocular media (cornea, lens, retina). This partial polarization is a function of the retinal nerve's fiber layer thickness, and its measurement may be used for exploring glaucoma and other retinal neuropathies. Experimental conditions allow us to neglect corneal dichroism. The first clinical measurements show a different degree of polarization between normal and glaucomatous eyes and a good correlation with the results obtained by optical coherence tomography.