The academic point-of-care anti-CD19 chimeric antigen receptor T-cell product varnimcabtagene autoleucel (ARI-0001 cells) shows efficacy and safety in the treatment of relapsed/refractory B-cell non-Hodgkin lymphoma.

Varnimcabtagene autoleucel (var-cel) is an academic anti-CD19 chimeric antigen receptor (CAR) product used for the treatment of non-Hodgkin lymphoma (NHL) in the CART19-BE-01 trial. Here we report updated outcomes of patients with NHL treated with var-cel. B-cell recovery was compared with patients with acute lymphoblastic leukaemia (ALL). Forty-five patients with NHL were treated. Cytokine release syndrome (any grade) occurred in 84% of patients (4% grade ≥3) and neurotoxicity in 7% (2% grade ≥3). The objective response rate was 73% at Day +100, and the 3-year duration of response was 56%. The 3-year progression-free and overall survival were 40% and 52% respectively. High lactate dehydrogenase was the only covariate with an impact on progression-free survival. The 3-year incidence of B-cell recovery was lower in patients with NHL compared to ALL (25% vs. 60%). In conclusion, in patients with NHL, the toxicity of var-cel was manageable, while B-cell recovery was significantly prolonged compared to ALL. This trial was registered as NCT03144583.

Significance of clinical-immunological patterns and diagnostic yield of biopsies in microscopic polyangiitis and granulomatosis with polyangiitis.

BACKGROUND: Microscopic polyangiitis (MPA) and granulomatosis with polyangiitis (GPA) are the two major antineutrophil cytoplasmic antibody (ANCA)-associated vasculitis (AAV). OBJECTIVES: To characterize a homogenous AAV cohort and to assess the impact of clinicopathological profiles and ANCA serotypes on clinical presentation and prognosis. Clinical differences in GPA patients according to ANCA serotype and the diagnostic yield for vasculitis of biopsies in different territories were also investigated. RESULTS: This retrospective study (2000-2021) included 152 patients with AAV (77 MPA/75 GPA). MPA patients (96.1% myeloperoxidase [MPO]-ANCA and 2.6% proteinase 3 [PR3]-ANCA) presented more often with weight loss, myalgia, renal involvement, interstitial lung disease (ILD), cutaneous purpura, and peripheral nerve involvement. Patients with GPA (44% PR3-ANCA, 33.3% MPO, and 22.7% negative/atypical ANCA) presented more commonly with ear, nose, and throat and eye/orbital manifestations, more relapses, and higher survival than patients with MPA. GPA was the only independent risk factor for relapse. Poor survival predictors were older age at diagnosis and peripheral nerve involvement. ANCA serotypes differentiated clinical features in a lesser degree than clinical phenotypes. A mean of 1.5 biopsies were performed in 93.4% of patients in different territories. Overall, vasculitis was identified in 80.3% (97.3% in MPA and 61.8% in GPA) of patients. CONCLUSIONS: The identification of GPA presentations associated with MPO-ANCA and awareness of risk factors for relapse and mortality are important to guide proper therapeutic strategies in AAV patients. Biopsies of different affected territories should be pursued in difficult-to-diagnose patients based on their significant diagnostic yield.

Academic challenges on advanced therapy medicinal products' development: a regulatory perspective.

Advanced therapy medicinal products (ATMPs) are becoming the new kid on the block for the treatment of a variety of indications with promising results. Despite the academic contribution to the basic and clinical research of ATMPs, undertaking a full product development process is extraordinarily challenging and demanding for academic institutions. Meeting regulatory requirements is probably the most challenging aspect of academic development, considering the limited experience and resources compared with pharmaceutical companies. This review aims to outline the key aspects to be considered when developing novel ATMPs from an academic perspective, based on the results of our own experience and interaction with the Spanish Agency of Medicines and Medical Devices (AEMPS) and European Medicine Agency (EMA) related to a number of academic ATMP initiatives carried out at our center during the last 5 years. Emphasis is placed on understanding the regulatory requirements during the early phases of the drug development process, particularly for the preparation of a Clinical Trial Application. Academic centers usually lack expertise in product-related documentation (such as the Investigational Medicinal Product Dossier), and therefore, early interaction with regulators is crucial to understand their requirements and receive guidance to comply with them. Insights are shared on managing quality, nonclinical, clinical, and risk and benefit documentation, based on our own experience and challenges. This review aims to empower academic and clinical settings by providing crucial regulatory knowledge to smooth the regulatory journey of ATMPs.

Thrombotic microangiopathy in patients with malignant hypertension.

BACKGROUND: Thrombotic microangiopathy (TMA) is a complication of malignant hypertension (mHTN) attributed to high blood pressure (BP). However, no studies have investigated in patients with mHTN of different aetiologies whether the presence of TMA is associated with specific causes of mHTN. METHODS: We investigated the presence of TMA (microangiopathic haemolytic anaemia and thrombocytopenia) in a large and well-characterized cohort of 199 patients with mHTN of different aetiologies [primary HTN 44%, glomerular diseases 16.6%, primary atypical haemolytic uraemic syndrome (aHUS) 13.1%, renovascular HTN 9.5%, drug-related HTN 7%, systemic diseases 5.5%, endocrine diseases 4.5%]. Outcomes of the study were kidney recovery and kidney failure. RESULTS: Patients with TMA [40 cases (20.1%)] were younger, were more likely female and had lower BP levels and worse kidney function at presentation. Their underlying diseases were primary aHUS (60%), drug-related mHTN (15%), glomerular diseases [all of them immunoglobulin A nephropathy (IgAN); 10%], systemic diseases (10%) and primary HTN (5%). The presence of TMA was 92.3% in primary aHUS, 42.9% in drug-related HTN, 36.4% in systemic diseases, 12.1% in glomerular diseases and 2.3% in primary HTN. No patient with renovascular HTN or mHTN caused by endocrine diseases developed TMA, despite BP levels as high as patients with TMA. A higher proportion of TMA patients developed kidney failure as compared with patients without TMA (56.4% versus 38.9%, respectively). CONCLUSIONS: The presence of TMA in patients with mHTN should guide the diagnosis towards primary aHUS, drug-related mHTN, some systemic diseases and IgAN, while it is exceptional in other causes of mHTN.

Oral hydration as a safe prophylactic measure to prevent post-contrast acute kidney injury in oncologic patients with chronic kidney disease (IIIb) referred for contrast-enhanced computed tomography: subanalysis of the oncological group of the NICIR study.

BACKGROUND: T he objective of this study is to evaluate oral hydration compared to intravenous (i.v.) hydration in the prevention of post-contrast acute kidney injury (PC-AKI) in the oncologic subgroup of patients with stage IIIb chronic kidney disease (CKD) included in the NICIR study referred for elective contrast-enhanced computed tomography (CE-CT). MATERIAL AND METHODS: We performed a retrospective subanalysis of the oncological subgroup (174/228 patients, 74%) from a continuous prospective database of patients included in the recently published non-inferiority NICIR study. Patients received prophylaxis against PC-AKI with either oral hydration (500 mL of water 2 h before and 2000 mL during the 24 h after CE-CT) or i.v. hydration (sodium bicarbonate (166 mmol/L) 3 mL/kg/h starting 1 h before and 1 mL/kg/h during the first hour after CE-CT). The primary outcome was to compare the proportion of PC-AKI in the first 48 to 72 h after CE-CT in the two hydration groups. Secondary outcomes were to compare persistent PC-AKI, the need for haemodialysis, and the occurrence of adverse events related to prophylaxis in each group. RESULTS: Of 174 patients included in the subanalysis, 82 received oral hydration and 92 received i.v. hydration. There were no significant differences in clinical characteristics or risk factors between the two study arms. Overall the PC-AKI rate was 4.6% (8/174 patients), being 3.7% in the oral hydration arm (3/82 patients) and 5.4% (5/92 patients) in the i.v. hydration arm. The persistent PC-AKI rate was 1.2% (1/82 patients) in the oral hydration arm and 3.3% (3/92 patients) in the i.v. hydration arm. No patient required dialysis during the first month after CE-CT or had adverse effects related to the hydration regime. CONCLUSION: In oncological patients with stage IIIb CKD referred for elective CE-CT, the rate of PC-AKI in those receiving oral hydration did not significantly differ from that of patients receiving i.v. hydration.

Reinforcement Learning-Based Autonomous Driving at Intersections in CARLA Simulator.

Intersections are considered one of the most complex scenarios in a self-driving framework due to the uncertainty in the behaviors of surrounding vehicles and the different types of scenarios that can be found. To deal with this problem, we provide a Deep Reinforcement Learning approach for intersection handling, which is combined with Curriculum Learning to improve the training process. The state space is defined by two vectors, containing adversaries and ego vehicle information. We define a features extractor module and an actor-critic approach combined with Curriculum Learning techniques, adding complexity to the environment by increasing the number of vehicles. In order to address a complete autonomous driving system, a hybrid architecture is proposed. The operative level generates the driving commands, the strategy level defines the trajectory and the tactical level executes the high-level decisions. This high-level decision system is the main goal of this research. To address realistic experiments, we set up three scenarios: intersections with traffic lights, intersections with traffic signs and uncontrolled intersections. The results of this paper show that a Proximal Policy Optimization algorithm can infer ego vehicle-desired behavior for different intersection scenarios based only on the behavior of adversarial vehicles.

Driver Take-Over Behaviour Study Based on Gaze Focalization and Vehicle Data in CARLA Simulator.

Autonomous vehicles are the near future of the automobile industry. However, until they reach Level 5, humans and cars will share this intermediate future. Therefore, studying the transition between autonomous and manual modes is a fascinating topic. Automated vehicles may still need to occasionally hand the control to drivers due to technology limitations and legal requirements. This paper presents a study of driver behaviour in the transition between autonomous and manual modes using a CARLA simulator. To our knowledge, this is the first take-over study with transitions conducted on this simulator. For this purpose, we obtain driver gaze focalization and fuse it with the road's semantic segmentation to track to where and when the user is paying attention, besides the actuators' reaction-time measurements provided in the literature. To track gaze focalization in a non-intrusive and inexpensive way, we use a method based on a camera developed in previous works. We devised it with the OpenFace 2.0 toolkit and a NARMAX calibration method. It transforms the face parameters extracted by the toolkit into the point where the user is looking on the simulator scene. The study was carried out by different users using our simulator, which is composed of three screens, a steering wheel and pedals. We distributed this proposal in two different computer systems due to the computational cost of the simulator based on the CARLA simulator. The robot operating system (ROS) framework is in charge of the communication of both systems to provide portability and flexibility to the proposal. Results of the transition analysis are provided using state-of-the-art metrics and a novel driver situation-awareness metric for 20 users in two different scenarios.

Complement as the enabler of carfilzomib-induced thrombotic microangiopathy.

Carfilzomib has been associated with the development of thrombotic microangiopathy (TMA) in relapsed/refractory multiple myeloma patients, a severe disease with no currently available aetiological treatment. We evaluated the potential role of terminal complement pathway in four patients with carfilzomib-induced TMA. Membrane attack complex (C5b-9) deposition on endothelial cells in culture exposed to plasma from patients during the acute phase of the disease suggests complement overactivation as a mechanism of potential endothelial damage in three out of four patients. If confirmed in larger cohorts, C5b-9 evaluation will allow early identification of patients who could benefit from complement blockade and treatment monitoring.

Gaze Focalization System for Driving Applications Using OpenFace 2.0 Toolkit with NARMAX Algorithm in Accidental Scenarios.

Monitoring driver attention using the gaze estimation is a typical approach used on road scenes. This indicator is of great importance for safe driving, specially on Level 3 and Level 4 automation systems, where the take over request control strategy could be based on the driver's gaze estimation. Nowadays, gaze estimation techniques used in the state-of-the-art are intrusive and costly, and these two aspects are limiting the usage of these techniques on real vehicles. To test this kind of application, there are some databases focused on critical situations in simulation, but they do not show real accidents because of the complexity and the danger to record them. Within this context, this paper presents a low-cost and non-intrusive camera-based gaze mapping system integrating the open-source state-of-the-art OpenFace 2.0 Toolkit to visualize the driver focalization on a database composed of recorded real traffic scenes through a heat map using NARMAX (Nonlinear AutoRegressive Moving Average model with eXogenous inputs) to establish the correspondence between the OpenFace 2.0 parameters and the screen region the user is looking at. This proposal is an improvement of our previous work, which was based on a linear approximation using a projection matrix. The proposal has been validated using the recent and challenging public database DADA2000, which has 2000 video sequences with annotated driving scenarios based on real accidents. We compare our proposal with our previous one and with an expensive desktop-mounted eye-tracker, obtaining on par results. We proved that this method can be used to record driver attention databases.

Recovery and applications of ammoniacal nitrogen from nitrogen-loaded residual streams: A review.

Total ammoniacal nitrogen (TAN) is considered to be a pollutant, but is also a versatile resource. This review presents an overview of the TAN recovery potentials from nitrogen (N)-loaded residual streams by discussing the sources, recovery technologies and potential applications. The first section of the review addresses the fate of TAN after its production. The second section describes the identification and categorisation of N-loaded (≥0.5 g L-1 of reduced N) residual streams based on total suspended solids (TSS), chemical oxygen demand (COD), total Kjeldahl nitrogen (TKN), TAN, and TAN/TKN ratio. Category 1 represents streams with a low TAN/TKN ratio (<0.5) that need conversion of organic-N to TAN prior to TAN recovery, for example by anaerobic digestion (AD). Category 2 represents streams with a high TAN/TKN ratio (≥0.5) and high TSS (>1 g L-1) that require a decrease of the TSS prior to TAN recovery, whereas category 3 represents streams with a high TAN/TKN ratio (≥0.5) and low TSS (≤1 g L-1) that are suitable for direct TAN recovery. The third section focuses on the key processes and limitations of AD, which is identified as a suitable technology to increase the TAN/TKN ratio by converting organic-N to TAN. In the fourth section, TAN recovery technologies are evaluated in terms of the feed composition tolerance, the required inputs (energy, chemicals, etc.) and obtained outputs of TAN (chemical form, concentration, etc.). Finally, in the fifth section, the use of recovered TAN for three major potential applications (fertilizer, fuel, and resource for chemical and biochemical processes) is discussed. This review presents an overview of possible TAN recovery strategies based on the available technologies, but the choice of the recovery strategy shall ultimately depend on the product characteristics required by the application. The major challenges identified in this review are the lack of information on enhancing the conversion of organic-N into TAN by AD, the difficulties in comparing the performance and required input of the recovery technologies, and the deficiency of information on the required concentration and quality of the final TAN products for reuse.

Case report of COVID-19 in a kidney transplant recipient: Does immunosuppression alter the clinical presentation?

COVID-19 is novel infectious disease with an evolving understanding of its epidemiology and clinical manifestations. Immunocompromised patients often present atypical presentations of viral diseases. Herein we report a case of a COVID-19 infection in a solid organ transplant recipient, in which the first clinical symptoms were of gastrointestinal viral disease and fever, which further progressed to respiratory symptoms in 48 hours. In these high risk populations, protocols for screening for SARS-Cov2 may be needed to be re-evaluated.

The renal range of the κ/λ sFLC ratio: best strategy to evaluate multiple myeloma in patients with chronic kidney disease.

BACKGROUND: Monoclonal serum free light chains (sFLC) are a well-known cause of renal impairment (RI) in patients with multiple myeloma (MM). As an indicator of monoclonality, sFLC ratio has acquired a key role in the diagnosis and monitorization of the disease. However, its interpretation is altered in patients with chronic kidney disease (CKD). This study aims to evaluate the modification of the sFLC ratio reference range in patients with CKD, and propose an optimal range for patients with CKD. METHODS: Serum FLC κ/λ ratio and estimated glomerular filtration rate (eGFR) were retrospectively analyzed in 113 control patients (without hematologic disease), 63 patients with MM in complete remission and 347 patients with active MM. The three groups included patients with CKD (eGFR < 90). RESULTS: In the group of patients without active MM (n = 176), the sFLC ratio increased at different stages of CKD without pathological significance, with an increase in the number of false positives specially when eGFR is ≤55 ml/min. An optimal range was established for patients with eGFR ≤55 ml/min/1.73 m2: 0.82-3,6 with maximum sensitivity + specificity for that group with an improvement in the Area under the curve (AUC), 0.91 (0.84-0.97) compared with the current ranges proposed by Katzmann and Hutchinson. CONCLUSIONS: This study confirms the influence of eGFR on the interpretation of the sFLC ratio, showing a decreasing specificity in progressive CKD stages when using the reference sFLC range (Katzmann), especially in patients with eFGR ≤55. According to our results, we suggest a modified optimal range (0.82-3,6) for eGFR ≤55 ml/min/1.73 m2. It is necessary to validate this modified range in larger and prospective studies.

Drive-By-Wire Development Process Based on ROS for an Autonomous Electric Vehicle.

This paper presents the development process of a robust and ROS-based Drive-By-Wire system designed for an autonomous electric vehicle from scratch over an open source chassis. A revision of the vehicle characteristics and the different modules of our navigation architecture is carried out to put in context our Drive-by-Wire system. The system is composed of a Steer-By-Wire module and a Throttle-By-Wire module that allow driving the vehicle by using some commands of lineal speed and curvature, which are sent through a local network from the control unit of the vehicle. Additionally, a Manual/Automatic switching system has been implemented, which allows the driver to activate the autonomous driving and safely taking control of the vehicle at any time. Finally, some validation tests were performed for our Drive-By-Wire system, as a part of our whole autonomous navigation architecture, showing the good working of our proposal. The results prove that the Drive-By-Wire system has the behaviour and necessary requirements to automate an electric vehicle. In addition, after 812 h of testing, it was proven that it is a robust Drive-By-Wire system, with high reliability. The developed system is the basis for the validation and implementation of new autonomous navigation techniques developed within the group in a real vehicle.

A Waypoint Tracking Controller for Autonomous Road Vehicles Using ROS Framework.

Automated Driving Systems (ADSs) require robust and scalable control systems in order to achieve a safe, efficient and comfortable driving experience. Most global planners for autonomous vehicles provide as output a sequence of waypoints to be followed. This paper proposes a modular and scalable waypoint tracking controller for Robot Operating System (ROS)-based autonomous guided vehicles. The proposed controller performs a smooth interpolation of the waypoints and uses optimal control techniques to ensure robust trajectory tracking even at high speeds in urban environments (up to 50 km/h). The delays in the localization system and actuators are compensated in the control loop to stabilize the system. Forward velocity is adapted to path characteristics using a velocity profiler. The controller has been implemented as an ROS package providing scalability and exportability to the system in order to be used with a wide variety of simulators and real vehicles. We show the results of this controller using the novel and hyper realistic CARLA Simulator and carrying out a comparison with other standard and state-of-art trajectory tracking controllers.

High-permeability alternatives to current dialyzers performing both high-flux hemodialysis and postdilution online hemodiafiltration.

Most high-flux dialyzers can be used in both hemodialysis (HD) and online hemodiafiltration (OL-HDF). However, some of these dialyzers have higher permeability and should not be prescribed for OL-HDF to avoid high albumin losses. The aim of this study was to compare the safety and efficacy of a currently used dialyzer in HD and OL-HDF with those of several other high permeability dialyzers which should only be used in HD. A prospective, single-center study was carried out in 21 patients. Each patient underwent 5 dialysis sessions with routine dialysis parameters: 2 sessions with Helixone (HD and postdilution OL-HDF) and 1 session each with steam sterilized polyphenylene, polymethylmethacrylate (PMMA), and medium cut-off (MCO) dialyzers in HD treatment. The removal ratios (RR) of urea, creatinine, ß2 -microglobulin, myoglobin, prolactin, α1 -microglobulin, α1 -acid glycoprotein, and albumin were compared intraindividually. A proportional part of the dialysate was collected to quantify the loss of various solutes, including albumin. Urea and creatinine RRs with the Helixone-HDF and MCO dialyzers were higher than with the other 3 dialyzers in HD. The ß2 -microglobulin, myoglobin and prolactin RRs with Helixone-HDF treatment were significantly higher than those obtained with all 4 dialyzers in HD treatment. The ß2 -microglobulin value obtained with the MCO dialyzer was also higher than that obtained with the other 3 dialyzers in HD treatment. The myoglobin RR with MCO was higher than those obtained with Helixone and PMMA in HD treatment. The prolactin RR with Helixone-HD was significantly lower than those obtained in the other 4 study sessions. The α1 -microglobulin and α1 - acid glycoprotein RRs with Helixone-HDF were significantly higher than those obtained with Helixone and PMMA in HD treatment. The albumin loss varied from 0.54 g with Helixone-HD to 3.3 g with polyphenylene. The global removal score values ((UreaRR + ß2 -microglobulinRR + myoglobinRR + prolactinRR + α1 -microglobulinRR + α1 -acid glycoproteinRR - albuminRR )/6) were 43.7% with Helixone-HD, 47.7% with PMMA, 54% with polyphenylene, 54.8% with MCO and 59.6% with Helixone-HDF, with significant differences. In conclusion, this study confirms the superiority of OL-HDF over HD with the high-flux dialyzers that allow both treatments. Although new dialyzers with high permeability can only be used in HD, they are in an intermediate position and some are very close to OL-HDF.

Medium Cut-Off Dialyzer versus Eight Hemodiafiltration Dialyzers: Comparison Using a Global Removal Score.

BACKGROUND: A novel class of membranes, medium cut-off (MCO) membranes, has recently been designed to achieve interesting removal capacities for middle and large middle molecules in hemodialysis (HD) treatments. The few studies published to date have reported contradictory results regarding middle-sized molecules when comparing MCO dialyzers versus dialyzers used in online hemodiafiltration (OL-HDF). METHODS: A prospective, single-center study was carried out in 22 patients. Each patient underwent 9 dialysis sessions with routine dialysis parameters, one with an MCO dialyzer in HD and the other 8 with different dialyzers in OL-HDF. The removal ratio (RR) of urea, creatinine, ß2-microglobulin, myoglobin, prolactin, α1-microglobulin, α1-acid glycoprotein, and albumin was intraindividually compared. Albumin loss in dialysate was measured. We propose a global removal score ([ureaRR + ß2-microglobulinRR + myoglobinRR + prolactinRR + α1-microglobulinRR + α1-acid glycoproteinRR]/6 - albuminRR) as a new tool for measuring dialyzer effectiveness. RESULTS: No significant differences in the RRs of small and middle molecular range molecules were observed between the MCO vs. OL-HDF dialyzers (range 60-80%). Lower RRs were found for α1-microglobulin and α1-acid glycoprotein without significant differences. The albumin RR was < 11% and dialysate albumin loss was < 3.5 g in all situations without significant differences. The global removal score was 54.9 ± 4.8% with the MCO dialyzer without significant differences. CONCLUSIONS: Removal of a wide range of molecular weights, calculated with the proposed global removal score, was almost equal with the MCO dialyzer in HD treatment compared with 8 high-flux dialyzers in high-volume OL-HDF without relevant changes in albumin loss. The global removal score could be a new tool to evaluate the effectiveness of dialyzers and/or different treatment modalities.

Real-Time Semantic Segmentation for Fisheye Urban Driving Images Based on ERFNet.

The interest in fisheye cameras has recently risen in the autonomous vehicles field, as they are able to reduce the complexity of perception systems while improving the management of dangerous driving situations. However, the strong distortion inherent to these cameras makes the usage of conventional computer vision algorithms difficult and has prevented the development of these devices. This paper presents a methodology that provides real-time semantic segmentation on fisheye cameras leveraging only synthetic images. Furthermore, we propose some Convolutional Neural Networks(CNN) architectures based on Efficient Residual Factorized Network(ERFNet) that demonstrate notable skills handling distortion and a new training strategy that improves the segmentation on the image borders. Our proposals are compared to similar state-of-the-art works showing an outstanding performance and tested in an unknown real world scenario using a fisheye camera integrated in an open-source autonomous electric car, showing a high domain adaptation capability.

Computer-Aided Diagnosis of Multiple Sclerosis Using a Support Vector Machine and Optical Coherence Tomography Features.

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 AUCCLASSIFIER. 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 AUCCLASSIFIER = 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.