The purpose of this paper is to evaluate the feasibility of diagnosing multiple sclerosis (MS) using optical coherence tomography (OCT) data and a support vector machine (SVM) as an automatic classifier. Forty-eight MS patients without symptoms of optic neuritis and forty-eight healthy control subjects were selected. Swept-source optical coherence tomography (SS-OCT) was performed using a DRI (deep-range imaging) Triton OCT device (Topcon Corp., Tokyo, Japan). Mean values (right and left eye) for macular thickness (retinal and choroidal layers) and peripapillary area (retinal nerve fibre layer, retinal, ganglion cell layer—GCL, and choroidal layers) were compared between both groups. Based on the analysis of the area under the receiver operator characteristic curve (AUC), the 3 variables with the greatest discriminant capacity were selected to form the feature vector. A SVM was used as an automatic classifier, obtaining the confusion matrix using leave-one-out cross-validation. Classification performance was assessed with Matthew’s correlation coefficient (MCC) and the AUC_CLASSIFIER. The most discriminant variables were found to be the total GCL++ thickness (between inner limiting membrane to inner nuclear layer boundaries), evaluated in the peripapillary area and macular retina thickness in the nasal quadrant of the outer and inner rings. Using the SVM classifier, we obtained the following values: MCC = 0.81, sensitivity = 0.89, specificity = 0.92, accuracy = 0.91, and AUC_CLASSIFIER = 0.97. Our findings suggest that it is possible to classify control subjects and MS patients without previous optic neuritis by applying machine-learning techniques to study the structural neurodegeneration in the retina.

The response of many biomedical systems can be modelled using a linear combination of damped exponential functions. The approximation parameters, based on equally spaced samples, can be obtained using Prony’s method and its variants (e.g. the matrix pencil method). This paper provides a tutorial on the main polynomial Prony and matrix pencil methods and their implementation in MATLAB and analyses how they perform with synthetic and multifocal visual-evoked potential (mfVEP) signals. This paper briefly describes the theoretical basis of four polynomial Prony approximation methods: classic, least squares (LS), total least squares (TLS) and matrix pencil method (MPM). In each of these cases, implementation uses general MATLAB functions. The features of the various options are tested by approximating a set of synthetic mathematical functions and evaluating filtering performance in the Prony domain when applied to mfVEP signals to improve diagnosis of patients with multiple sclerosis (MS). The code implemented does not achieve 100%-correct signal approximation and, of the methods tested, LS and MPM perform best. When filtering mfVEP records in the Prony domain, the value of the area under the receiver-operating-characteristic (ROC) curve is 0.7055 compared with 0.6538 obtained with the usual filtering method used for this type of signal (discrete Fourier transform low-pass filter with a cut-off frequency of 35 Hz). This paper reviews Prony’s method in relation to signal filtering and approximation, provides the MATLAB code needed to implement the classic, LS, TLS and MPM methods, and tests their performance in biomedical signal filtering and function approximation. It emphasizes the importance of improving the computational methods used to implement the various methods described above.

Background: The aim of this study is to explore an objective approach that aids the diagnosis of bipolar disorder (BD), based on optical coherence tomography (OCT) data which are analyzed using artificial intelligence. Methods: Structural analyses of nine layers of the retina were analyzed in 17 type I BD patients and 42 controls, according to the areas defined by the Early Treatment Diabetic Retinopathy Study (ETDRS) chart. The most discriminating variables made up the feature vector of several automatic classifiers: Gaussian Naive Bayes, K-nearest neighbors and support vector machines. Results: BD patients presented retinal thinning affecting most layers, compared to controls. The retinal thickness of the parafoveolar area showed a high capacity to discriminate BD subjects from healthy individuals, specifically for the ganglion cell (area under the curve (AUC) = 0.82) and internal plexiform (AUC = 0.83) layers. The best classifier showed an accuracy of 0.95 for classifying BD versus controls, using as variables of the feature vector the IPL (inner nasal region) and the INL (outer nasal and inner inferior regions) thickness. Conclusions: Our patients with BD present structural alterations in the retina, and artificial intelligence seem to be a useful tool in BD diagnosis, but larger studies are needed to confirm our findings.

This study aims to identify objective biomarkers of fibromyalgia (FM) by applying artificial intelligence algorithms to structural data on the neuroretina obtained using swept-source optical coherence tomography (SS-OCT). The study cohort comprised 29 FM patients and 32 control subjects. The thicknesses of complete retina, 3 retinal layers [ganglion cell layer (GCL+), GCL++ (between the inner limiting membrane and the inner nuclear layer boundaries) and retinal nerve fiber layer (RNFL)] and choroid in 9 areas around the macula were obtained using SS-OCT. Discriminant capacity was evaluated using the area under the curve (AUC) and the Relief algorithm. A diagnostic aid system with an automatic classifier was implemented. No significant difference (p ≥ .660) was found anywhere in the choroid. In the RNFL, a significant difference was found in the inner inferior region (p = .010). In the GCL+, GCL++ layers and complete retina, a significant difference was found in the 4 regions defining the inner ring: temporal, superior, nasal and inferior. Applying an ensemble RUSBoosted tree classifier to the features with greatest discriminant capacity achieved accuracy = .82 and AUC = .82. This study identifies a potential novel objective and non-invasive biomarker of FM based on retina analysis using SS-OCT.

As multiple sclerosis (MS) usually affects the visual pathway, visual electrophysiological tests can be used to diagnose it. The objective of this paper is to research methods for processing multifocal electroretinogram (mfERG) recordings to improve the capacity to diagnose MS. MfERG recordings from 15 early-stage MS patients without a history of optic neuritis and from 6 control subjects were examined. A normative database was built from the control subject signals. The mfERG recordings were filtered using empirical mode decomposition (EMD). The correlation with the signals in a normative database was used as the classification feature. Using EMD-based filtering and performance correlation, the mean area under the curve (AUC) value was 0.90. The greatest discriminant capacity was obtained in ring 4 and in the inferior nasal quadrant (AUC values of 0.96 and 0.94, respectively). Our results suggest that the combination of filtering mfERG recordings using EMD and calculating the correlation with a normative database would make mfERG waveform analysis applicable to assessment of multiple sclerosis in early-stage patients.

Multiple sclerosis (MS) and Alzheimer’s disease (AD) cause retinal thinning that is detectable in vivo using optical coherence tomography (OCT). To date, no papers have compared the two diseases in terms of the structural differences they produce in the retina. The purpose of this study is to analyse and compare the neuroretinal structure in MS patients, AD patients and healthy subjects using OCT. Spectral domain OCT was performed on 21 AD patients, 33 MS patients and 19 control subjects using the Posterior Pole protocol. The area under the receiver operating characteristic (AUROC) curve was used to analyse the differences between the cohorts in nine regions of the retinal nerve fibre layer (RNFL), ganglion cell layer (GCL), inner plexiform layer (IPL) and outer nuclear layer (ONL). The main differences between MS and AD are found in the ONL, in practically all the regions analysed (AUROC_FOVEAL = 0.80, AUROC_PARAFOVEAL = 0.85, AUROC_PERIFOVEAL = 0.80, AUROC__PMB = 0.77, AUROC_PARAMACULAR = 0.85, AUROC_{INFERO_NASAL} = 0.75, AUROC_{INFERO_TEMPORAL} = 0.83), and in the paramacular zone (AUROC_PARAMACULAR = 0.75) and infero-temporal quadrant (AUROC_{INFERO_TEMPORAL} = 0.80) of the GCL. In conclusion, our findings suggest that OCT data analysis could facilitate the differential diagnosis of MS and AD.