1
|
Montolío A, Cegoñino J, Garcia-Martin E, Pérez Del Palomar A. The macular retinal ganglion cell layer as a biomarker for diagnosis and prognosis in multiple sclerosis: A deep learning approach. Acta Ophthalmol 2024; 102:e272-e284. [PMID: 37300357 DOI: 10.1111/aos.15722] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Revised: 05/12/2023] [Accepted: 05/28/2023] [Indexed: 06/12/2023]
Abstract
PURPOSE The macular ganglion cell layer (mGCL) is a strong potential biomarker of axonal degeneration in multiple sclerosis (MS). For this reason, this study aims to develop a computer-aided method to facilitate diagnosis and prognosis in MS. METHODS This paper combines a cross-sectional study of 72 MS patients and 30 healthy control subjects for diagnosis and a 10-year longitudinal study of the same MS patients for the prediction of disability progression, during which the mGCL was measured using optical coherence tomography (OCT). Deep neural networks were used as an automatic classifier. RESULTS For MS diagnosis, greatest accuracy (90.3%) was achieved using 17 features as inputs. The neural network architecture comprised the input layer, two hidden layers and the output layer with softmax activation. For the prediction of disability progression 8 years later, accuracy of 81.9% was achieved with a neural network comprising two hidden layers and 400 epochs. CONCLUSION We present evidence that by applying deep learning techniques to clinical and mGCL thickness data it is possible to identify MS and predict the course of the disease. This approach potentially constitutes a non-invasive, low-cost, easy-to-implement and effective method.
Collapse
Affiliation(s)
- Alberto Montolío
- Biomaterials Group, Aragon Institute of Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain
- Mechanical Engineering Department, University of Zaragoza, Zaragoza, Spain
| | - José Cegoñino
- Biomaterials Group, Aragon Institute of Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain
- Mechanical Engineering Department, University of Zaragoza, Zaragoza, Spain
| | - Elena Garcia-Martin
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain
- GIMSO Research and Innovation Group, Aragon Institute for Health Research (IIS Aragon), Zaragoza, Spain
| | - Amaya Pérez Del Palomar
- Biomaterials Group, Aragon Institute of Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain
- Mechanical Engineering Department, University of Zaragoza, Zaragoza, Spain
| |
Collapse
|
2
|
Wei S, Du Y, Luo M, Song R. Development of a predictive model for predicting disability after optic neuritis: a secondary analysis of the Optic Neuritis Treatment Trial. Front Neurol 2024; 14:1326261. [PMID: 38268999 PMCID: PMC10807422 DOI: 10.3389/fneur.2023.1326261] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2023] [Accepted: 12/12/2023] [Indexed: 01/26/2024] Open
Abstract
Objective The present study aimed to develop a prediction model for predicting developing debilities after optic neuritis. Methods The data for this research was obtained from the Optic Neuritis Treatment Trial (ONTT). The predictive model was built based on a Cox proportional hazards regression model. Model performance was assessed using Harrell's C-index for discrimination, calibration plots for calibration, and stratification of patients into low-risk and high-risk groups for utility evaluation. Results A total of 416 patients participated. Among them, 101 patients (24.3%) experienced disability, which was defined as achieving or surpassing a score of 3 on the expanded disability status scale. The median follow-up duration was 15.5 years (interquartile range, 7.0 to 16.8). Two predictors in the final predictive model included the classification of multiple sclerosis at baseline and the condition of the optic disk in the affected eye at baseline. Upon incorporating these two factors into the model, the model's C-index stood at 0.71 (95% CI, 0.66-0.76, with an optimism of 0.005) with a favorable alignment with the calibration curve. By utilizing this model, the ONTT cohort can be categorized into two risk categories, each having distinct rates of disability development within a 15-year timeframe (high-risk group, 41% [95% CI, 31-49%] and low-risk group, 13% [95% CI, 8.4-17%]; log-rank p-value of <0.001). Conclusion This predictive model has the potential to assist physicians in identifying individuals at a heightened risk of experiencing disability following optic neuritis, enabling timely intervention and treatment.
Collapse
|
3
|
Viladés E, Cordón B, Pérez-Velilla J, Orduna E, Satue M, Polo V, Sebastian B, Larrosa JM, Pablo L, García-Martin E. Evaluation of multiple sclerosis severity using a new OCT tool. PLoS One 2023; 18:e0288581. [PMID: 37440532 DOI: 10.1371/journal.pone.0288581] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2021] [Accepted: 06/30/2023] [Indexed: 07/15/2023] Open
Abstract
PURPOSE To assess the ability of a new posterior pole protocol to detect areas with significant differences in retinal nerve fiber layer (RNFL) and ganglion cell layer (GCL) thickness in patients with multiple sclerosis versus healthy control subjects; in addition, to assess the correlation between RNFL and GCL thickness, disease duration, and the Expanded Disability Status Scale (EDSS). METHODS We analyzed 66 eyes of healthy control subjects and 100 eyes of remitting-relapsing multiple sclerosis (RR-MS) patients. Double analysis based on first clinical symptom onset (CSO) and conversion to clinically definite MS (CDMS) was performed. The RR-MS group was divided into subgroups by CSO and CDMS year: CSO-1 (≤ 5 years) and CSO-2 (≥ 6 years), and CDMS-1 (≤ 5 years) and CDMS-2 (≥ 6 years). RESULTS Significant differences in RNFL and GCL thickness were found between the RR-MS group and the healthy controls and between the CSO and CDMS subgroups and in both layers. Moderate to strong correlations were found between RNFL and GCL thickness and CSO and CDMS. Furthermore, we observed a strong correlation with EDSS 1 year after the OCT examination. CONCLUSIONS The posterior pole protocol is a useful tool for assessing MS and can reveal differences even in early stages of the disease. RNFL thickness shows a strong correlation with disability status, while GCL thickness correlates better with disease duration.
Collapse
Affiliation(s)
- Elisa Viladés
- Miguel Servet Ophthalmology Research and Innovation Group (GIMSO), Aragon Institute for Health Research (IIS Aragón), University of Zaragoza, Zaragoza, Spain
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain
| | - Beatriz Cordón
- Miguel Servet Ophthalmology Research and Innovation Group (GIMSO), Aragon Institute for Health Research (IIS Aragón), University of Zaragoza, Zaragoza, Spain
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain
| | - Javier Pérez-Velilla
- Miguel Servet Ophthalmology Research and Innovation Group (GIMSO), Aragon Institute for Health Research (IIS Aragón), University of Zaragoza, Zaragoza, Spain
| | - Elvira Orduna
- Miguel Servet Ophthalmology Research and Innovation Group (GIMSO), Aragon Institute for Health Research (IIS Aragón), University of Zaragoza, Zaragoza, Spain
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain
| | - Maria Satue
- Miguel Servet Ophthalmology Research and Innovation Group (GIMSO), Aragon Institute for Health Research (IIS Aragón), University of Zaragoza, Zaragoza, Spain
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain
| | - Vicente Polo
- Miguel Servet Ophthalmology Research and Innovation Group (GIMSO), Aragon Institute for Health Research (IIS Aragón), University of Zaragoza, Zaragoza, Spain
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain
| | - Berta Sebastian
- Miguel Servet Ophthalmology Research and Innovation Group (GIMSO), Aragon Institute for Health Research (IIS Aragón), University of Zaragoza, Zaragoza, Spain
- Neurology Department, Miguel Servet University Hospital, Zaragoza, Spain
| | - Jose Manuel Larrosa
- Miguel Servet Ophthalmology Research and Innovation Group (GIMSO), Aragon Institute for Health Research (IIS Aragón), University of Zaragoza, Zaragoza, Spain
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain
| | - Luis Pablo
- Miguel Servet Ophthalmology Research and Innovation Group (GIMSO), Aragon Institute for Health Research (IIS Aragón), University of Zaragoza, Zaragoza, Spain
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain
| | - Elena García-Martin
- Miguel Servet Ophthalmology Research and Innovation Group (GIMSO), Aragon Institute for Health Research (IIS Aragón), University of Zaragoza, Zaragoza, Spain
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain
| |
Collapse
|
4
|
Weatherley G, Araujo RP, Dando SJ, Jenner AL. Could Mathematics be the Key to Unlocking the Mysteries of Multiple Sclerosis? Bull Math Biol 2023; 85:75. [PMID: 37382681 PMCID: PMC10310626 DOI: 10.1007/s11538-023-01181-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2023] [Accepted: 06/19/2023] [Indexed: 06/30/2023]
Abstract
Multiple sclerosis (MS) is an autoimmune, neurodegenerative disease that is driven by immune system-mediated demyelination of nerve axons. While diseases such as cancer, HIV, malaria and even COVID have realised notable benefits from the attention of the mathematical community, MS has received significantly less attention despite the increasing disease incidence rates, lack of curative treatment, and long-term impact on patient well-being. In this review, we highlight existing, MS-specific mathematical research and discuss the outstanding challenges and open problems that remain for mathematicians. We focus on how both non-spatial and spatial deterministic models have been used to successfully further our understanding of T cell responses and treatment in MS. We also review how agent-based models and other stochastic modelling techniques have begun to shed light on the highly stochastic and oscillatory nature of this disease. Reviewing the current mathematical work in MS, alongside the biology specific to MS immunology, it is clear that mathematical research dedicated to understanding immunotherapies in cancer or the immune responses to viral infections could be readily translatable to MS and might hold the key to unlocking some of its mysteries.
Collapse
Affiliation(s)
- Georgia Weatherley
- School of Mathematical Sciences, Queensland University of Technology, Brisbane, Australia
| | - Robyn P Araujo
- School of Mathematical Sciences, Queensland University of Technology, Brisbane, Australia
| | - Samantha J Dando
- School of Biomedical Sciences, Centre for Immunology and Infection Control, Faculty of Health, Queensland University of Technology, Brisbane, Australia
| | - Adrianne L Jenner
- School of Mathematical Sciences, Queensland University of Technology, Brisbane, Australia.
| |
Collapse
|
5
|
Comparison of Machine Learning Methods Using Spectralis OCT for Diagnosis and Disability Progression Prognosis in Multiple Sclerosis. Ann Biomed Eng 2022; 50:507-528. [PMID: 35220529 PMCID: PMC9001622 DOI: 10.1007/s10439-022-02930-3] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2021] [Accepted: 02/10/2022] [Indexed: 12/28/2022]
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.
Collapse
|
6
|
Guerrieri S, Comi G, Leocani L. Optical Coherence Tomography and Visual Evoked Potentials as Prognostic and Monitoring Tools in Progressive Multiple Sclerosis. Front Neurosci 2021; 15:692599. [PMID: 34421520 PMCID: PMC8374170 DOI: 10.3389/fnins.2021.692599] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2021] [Accepted: 06/07/2021] [Indexed: 11/13/2022] Open
Abstract
Understanding the mechanisms underlying progression and developing new treatments for progressive multiple sclerosis (PMS) are among the major challenges in the field of central nervous system (CNS) demyelinating diseases. Over the last 10 years, also because of some technological advances, the visual pathways have emerged as a useful platform to study the processes of demyelination/remyelination and their relationship with axonal degeneration/protection. The wider availability and technological advances in optical coherence tomography (OCT) have allowed to add information on structural neuroretinal changes, in addition to functional information provided by visual evoked potentials (VEPs). The present review will address the role of the visual pathway as a platform to assess functional and structural damage in MS, focusing in particular on the role of VEPs and OCT, alone or in combination, in the prognosis and monitoring of PMS.
Collapse
Affiliation(s)
- Simone Guerrieri
- Experimental Neurophysiology Unit, San Raffaele Hospital, Institute of Experimental Neurology (INSPE), Milan, Italy.,Vita-Salute San Raffaele University, Milan, Italy
| | - Giancarlo Comi
- Vita-Salute San Raffaele University, Milan, Italy.,Casa di Cura del Policlinico, Milan, Italy
| | - Letizia Leocani
- Experimental Neurophysiology Unit, San Raffaele Hospital, Institute of Experimental Neurology (INSPE), Milan, Italy.,Vita-Salute San Raffaele University, Milan, Italy
| |
Collapse
|
7
|
Montolío A, Martín-Gallego A, Cegoñino J, Orduna E, Vilades E, Garcia-Martin E, Palomar APD. Machine learning in diagnosis and disability prediction of multiple sclerosis using optical coherence tomography. Comput Biol Med 2021; 133:104416. [PMID: 33946022 DOI: 10.1016/j.compbiomed.2021.104416] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2020] [Revised: 03/25/2021] [Accepted: 04/16/2021] [Indexed: 01/02/2023]
Abstract
BACKGROUND Multiple sclerosis (MS) is a neurodegenerative disease that affects the central nervous system, especially the brain, spinal cord, and optic nerve. Diagnosis of this disease is a very complex process and generally requires a lot of time. In addition, treatments are applied without any information on the disability course in each MS patient. For these two reasons, the objective of this study was to improve the MS diagnosis and predict the long-term course of disability in MS patients based on clinical data and retinal nerve fiber layer (RNFL) thickness, measured by optical coherence tomography (OCT). MATERIAL AND METHODS A total of 104 healthy controls and 108 MS patients, 82 of whom had a 10-year follow-up, were enrolled. Classification algorithms 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 to develop two predictive models: MS diagnosis model and MS disability course prediction model. RESULTS For MS diagnosis, the best result was obtained using EC (accuracy: 87.7%; sensitivity: 87.0%; specificity: 88.5%; precision: 88.7%; AUC: 0.8775). In line with this good performance, the accuracy was 85.4% using k-NN and 84.4% using SVM. And, for long-term prediction of MS disability course, LSTM recurrent neural network was the most appropriate classifier (accuracy: 81.7%; sensitivity: 81.1%; specificity: 82.2%; precision: 78.9%; AUC: 0.8165). The use of MLR, SVM and k-NN also showed a good performance (AUC ≥ 0.8). CONCLUSIONS This study demonstrated that machine learning techniques, using clinical and OCT data, can help establish an early diagnosis and predict the course of MS. This advance could help clinicians select more specific treatments for each MS patient. Therefore, our findings underscore the potential of RNFL thickness as a reliable MS biomarker.
Collapse
Affiliation(s)
- Alberto Montolío
- Group of Biomaterials, Aragon Institute of Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain; Department of Mechanical Engineering, University of Zaragoza, Zaragoza, Spain
| | - Alejandro Martín-Gallego
- Group of Biomaterials, Aragon Institute of Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain; Department of Mechanical Engineering, University of Zaragoza, Zaragoza, Spain
| | - José Cegoñino
- Group of Biomaterials, Aragon Institute of Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain; Department of Mechanical Engineering, University of Zaragoza, Zaragoza, Spain
| | - Elvira Orduna
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain; GIMSO Research and Innovative Group, Aragon Institute for Health Research (IIS Aragon), Zaragoza, Spain
| | - Elisa Vilades
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain; GIMSO Research and Innovative Group, Aragon Institute for Health Research (IIS Aragon), Zaragoza, Spain
| | - Elena Garcia-Martin
- Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain; GIMSO Research and Innovative Group, Aragon Institute for Health Research (IIS Aragon), Zaragoza, Spain
| | - Amaya Pérez Del Palomar
- Group of Biomaterials, Aragon Institute of Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain; Department of Mechanical Engineering, University of Zaragoza, Zaragoza, Spain.
| |
Collapse
|
8
|
Özbilen KT, Gündüz T, Çukurova Kartal SN, Gedik AC, Eraksoy M, Kürtüncü M. Bruch's membrane opening-minimum rim width: An alternative OCT biomarker study for multiple sclerosis. Eur J Ophthalmol 2021; 31:2141-2149. [PMID: 33601900 DOI: 10.1177/1120672121996638] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
PURPOSE Bruch's membrane opening-minimum rim width (BMO-MRW) and RNFL measured using anatomic positioning system (APS-RNFL) are novel OCT methods and remained unexplored in MS patients.To investigate the novel parameters of spectral-domain OCT as an alternative biomarker in patients with multiple sclerosis (MS). METHODS Retrospective cohort study; participants consisted of relapsing-remitting MS (RRMS) patients and healthy controls (HC). Eyes were classified according to the presence of MS and previous optic neuritis (ON). Measurements of standard peripapillary RNFL (S-RNFL), BMO-MRW, and APS-RNFL were performed. RESULT A total of 244 eyes of 122 participants (MS-patients: 63, HC: 59) were included in the study. Fifty-one eyes had a history of previous ON. In almost all measured parameters, neuroretinal rim thicknesses were observed the thinnest in eyes with ON history between all subgroups. S-RNFL and APS-RNFL techniques showed the difference in neuroretinal rim thickness in all three subjects (ON+, ON-, and HC). However, BMO-MRW, on the other hand, could not distinguish between ON(-) patients and HC. The relationship between OCT parameters and EDSS were observed only in eyes with an ON history in all three techniques. A meaningful model with 78% accuracy was obtained by using only the OCT parameters as risk factors. In the ROC analysis, no parameters were found to have acceptable high sensitivity and specificity. BMO-MRW was statistically weaker in every aspect than other RNFL techniques. CONCLUSION The novel APS-RNFL technique appears to be a bit more reliable alternative to S-RNFL technique to support therapeutic decision-making in MS. BMO-MRW has not been found as a successful alternative to S-RNFL.
Collapse
Affiliation(s)
- Kemal Turgay Özbilen
- Department of Ophthalmology, Istanbul Faculty of Medicine, Istanbul University, Istanbul, Turkey
| | - Tuncay Gündüz
- Department of Neurology, Istanbul Faculty of Medicine, Istanbul University, Istanbul, Turkey
| | | | - Ali Ceyhun Gedik
- Lüleburgaz State Hospital, Ophthalmology Clinic, Kırklareli, Turkey
| | - Mefküre Eraksoy
- Department of Neurology, Istanbul Faculty of Medicine, Istanbul University, Istanbul, Turkey
| | - Murat Kürtüncü
- Department of Neurology, Istanbul Faculty of Medicine, Istanbul University, Istanbul, Turkey
| |
Collapse
|
9
|
Detection of Neurological and Ophthalmological Pathologies with Optical Coherence Tomography Using Retinal Thickness Measurements: A Bibliometric Study. APPLIED SCIENCES-BASEL 2020. [DOI: 10.3390/app10165477] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
We carry out a bibliometric analysis on neurological and ophthalmological pathologies based on retinal nerve fiber layer (RNFL) thickness measured with optical coherence tomography (OCT). Documents were selected from Scopus database. We have applied the most commonly used bibliometric indicators, both for production and dispersion, as Price’s law of scientific literature growth, Lotka’s law, the transient index, and the Bradford model. Finally, the participation index of the different countries and affiliations was calculated. Two-hundred-and-forty-one documents from the period 2000–2019 were retrieved. Scientific production was better adjusted to linear growth (r = 0.88) than exponential (r = 0.87). The duplication time of the documents obtained was 5.6 years. The transience index was 89.62%, which indicates that most of the scientific production is due to very few authors. The signature rate per document was 5.2. Nine journals made up the Bradford core. USA and University of California present the highest production. The most frequently discussed topics on RNFL thinning are glaucoma and neurodegenerative diseases (NDD). The growth of the scientific literature on RNFL thickness was linear, with a very high rate of transience, which indicates low productivity and the presence of numerous authors who sporadically publish on this topic. No evidence of a saturation point was observed. In the last 10 years, there has been an increase in documents relating the decline of RNFL to NDD.
Collapse
|