Objective To compare axonal loss in ganglion cells detected with swept-source optical coherence tomography (SS-OCT) in eyes of patients with multiple sclerosis (MS) versus healthy controls using different machine learning techniques. To analyze the capability of machine learning techniques to improve the detection of retinal nerve fiber layer (RNFL) and the complex Ganglion Cell Layer–Inner plexiform layer (GCL+) damage in patients with multiple sclerosis and to use the SS-OCT as a biomarker to early predict this disease. Methods Patients with relapsing-remitting MS (n = 80) and age-matched healthy controls (n = 180) were enrolled. Different protocols from the DRI SS-OCT Triton system were used to obtain the RNFL and GCL+ thicknesses in both eyes. Macular and peripapilar areas were analyzed to detect the zones with higher thickness decrease. The performance of different machine learning techniques (decision trees, multilayer perceptron and support vector machine) for identifying RNFL and GCL+ thickness loss in patients with MS were evaluated. Receiver-operating characteristic (ROC) curves were used to display the ability of the different tests to discriminate between MS and healthy eyes in our population. Results Machine learning techniques provided an excellent tool to predict MS disease using SS-OCT data. In particular, the decision trees obtained the best prediction (97.24%) using RNFL data in macular area and the area under the ROC curve was 0.995, while the wide protocol which covers an extended area between macula and papilla gave an accuracy of 95.3% with a ROC of 0.998. Moreover, it was obtained that the most significant area of the RNFL to predict MS is the macula just surrounding the fovea. On the other hand, in our study, GCL+ did not contribute to predict MS and the different machine learning techniques performed worse in this layer than in RNFL. Conclusions Measurements of RNFL thickness obtained with SS-OCT have an excellent ability to differentiate between healthy controls and patients with MS. Thus, the use of machine learning techniques based on these measures can be a reliable tool to help in MS diagnosis.

No abstract

Machine learning approaches in diagnosis and prognosis of multiple sclerosis (MS) were analysed using retinal nerve fiber layer (RNFL) thickness, measured by optical coherence tomography (OCT). A cross-sectional study (72 MS patients and 30 healthy controls) was used for diagnosis. These 72 MS patients were involved in a 10-year longitudinal follow-up study for prognostic purposes. Structural measurements of RNFL thickness were performed using different Spectralis OCT protocols: fast macular thickness protocol to measure macular RNFL, and fast RNFL thickness protocol and fast RNFL-N thickness protocol to measure peripapillary RNFL. Binary classifiers such as multiple linear regression (MLR), support vector machines (SVM), decision tree (DT), k-nearest neighbours (k-NN), Naïve Bayes (NB), ensemble classifier (EC) and long short-term memory (LSTM) recurrent neural network were tested. For MS diagnosis, the best acquisition protocol was fast macular thickness protocol using k-NN (accuracy: 95.8%; sensitivity: 94.4%; specificity: 97.2%; precision: 97.1%; AUC: 0.958). For MS prognosis, our model with a 3-year follow up to predict disability progression 8 years later was the best predictive model. DT performed best for fast macular thickness protocol (accuracy: 91.3%; sensitivity: 90.0%; specificity: 92.5%; precision: 92.3%; AUC: 0.913) and SVM for fast RNFL-N thickness protocol (accuracy: 91.3%; sensitivity: 87.5%; specificity: 95.0%; precision: 94.6%; AUC: 0.913). This work concludes that measurements of RNFL thickness obtained with Spectralis OCT have a good ability to diagnose MS and to predict disability progression in MS patients. This machine learning approach would help clinicians to have valuable information.

Ocular surface inflammatory disorder (OSID) is a spectrum of disorders that have features of several etiologies whilst displaying similar phenotypic signs of ocular inflammation. They are complicated disorders with underlying mechanisms related to several autoimmune disorders, such as rheumatoid arthritis (RA), Sjögren’s syndrome, and systemic lupus erythematosus (SLE). Current literature shows the involvement of both innate and adaptive arms of the immune system in ocular surface inflammation. The ocular surface contains distinct components of the immune system in the conjunctiva and the cornea. The normal conjunctiva epithelium and sub-epithelial stroma contains resident immune cells, such as T cells, B cells (adaptive), dendritic cells, and macrophages (innate). The relative sterile environment of the cornea is achieved by the tolerogenic properties of dendritic cells in the conjunctiva, the presence of regulatory lymphocytes, and the existence of soluble immunosuppressive factors, such as the transforming growth factor (TGF)-β and macrophage migration inhibitory factors. With the presence of both innate and adaptive immune system components, it is intriguing to investigate the most important leukocyte population in the ocular surface, which is involved in immune surveillance. Our meta-analysis investigates into this with a focus on both infectious (contact lens wear, corneal graft rejection, Cytomegalovirus, keratitis, scleritis, ocular surgery) and non-infectious (dry eye disease, glaucoma, graft-vs-host disease, Sjögren’s syndrome) situations. We have found the predominance of dendritic cells in ocular surface diseases, along with the Th-related cytokines. Our goal is to improve the knowledge of immune cells in OSID and to open new dimensions in the field. The purpose of this study is not to limit ourselves in the ocular system, but to investigate the importance of dendritic cells in the disorders of other mucosal organs (e.g., lungs, gut, uterus). Holistically, we want to investigate if this is a common trend in the initiation of any disease related to the mucosal organs and find a unified therapeutic approach. In addition, we want to show the power of computational approaches to foster a collaboration between computational and biological science.

Glaucoma causes blindness due to the progressive death of retinal ganglion cells. The immune response chronically and subclinically mediates a homeostatic role. In current clinical practice, it is impossible to analyse neuroinflammation non-invasively. However, analysis of vitreous images using optical coherence tomography detects the immune response as hyperreflective opacities. This study monitors vitreous parainflammation in two animal models of glaucoma, comparing both healthy controls and sexes over six months. Computational analysis characterizes in vivo the hyperreflective opacities, identified histologically as hyalocyte-like Iba-1+ (microglial marker) cells. Glaucomatous eyes showed greater intensity and number of vitreous opacities as well as dynamic fluctuations in the percentage of activated cells (50–250 microns2) vs. non-activated cells (10–50 microns2), isolated cells (10 microns2) and complexes (>250 microns2). Smaller opacities (isolated cells) showed the highest mean intensity (intracellular machinery), were the most rounded at earlier stages (recruitment) and showed the greatest change in orientation (motility). Study of vitreous parainflammation could be a biomarker of glaucoma onset and progression.