Revisión sistemática de la aplicación de algoritmos de «machine learning» en la esclerosis múltiple / A systematic review of the application of machine-learning algorithms in multiple sclerosis

Introducción: La aplicación de la inteligencia artificial y en particular de algoritmos de aprendizaje automático o «machine learning» (ML) constituye un desafío y al mismo tiempo una gran oportunidad en diversas disciplinas científicas, técnicas y clínicas. Las aplicaciones específicas en el estudio de la esclerosis múltiple (EM) no han sido una excepción mostrando un creciente interés en los últimos años. Objetivo: Realizar una revisión sistemática de la aplicación de algoritmos de ML en la EM. Material y métodos: Empleando el motor de búsqueda de libre acceso PubMed que accede a la base de datos MEDLINE, se seleccionaron aquellos estudios que incluyeran simultáneamente los dos siguientes conceptos de búsqueda: «machine learning» y «multiple sclerosis». Se rechazaron aquellos estudios que fueran revisiones, estuvieran en otro idioma que no fuera el castellano o el inglés, y aquellos trabajos que tuvieran un carácter técnico y no fueran aplicados para la EM. Se seleccionaron como válidos 76 artículos y fueron rechazados 38. Conclusiones: Tras la revisión de los estudios seleccionados, se pudo observar que la aplicación del ML en la EM se concentró en cuatro categorías: 1) clasificación de subtipos de pacientes dentro de la enfermedad; 2) diagnóstico del paciente frente a controles sanos u otras enfermedades; 3) predicción de la evolución o de la respuesta a intervenciones terapéuticas y por último 4) otros enfoques. Los resultados hallados hasta la fecha muestran que los diferentes algoritmos de ML pueden ser un gran apoyo para el profesional sanitario tanto en la clínica como en la investigación de la EM.(AU)

Introduction: The applications of artificial intelligence, and in particular automatic learning or “machine learning” (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years. Objective: We present a systematic review of the application of ML algorithms in MS. Materials and methods: We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords “machine learning” and “multiple sclerosis.” We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected. Conclusions: After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.(AU)

Redes neurales atencionales en enfermedades neurodegenerativas: evidencias anatómico-funcionales empleando el Attention Network Test / Attentional networks in neurodegenerative diseases: anatomical and functional evidence from the Attention Network Test

Introducción: Comprender las alteraciones en la anatomía y función del cerebro en los procesos cognitivos para las enfermedades neurodegenerativas es aún un desafío para la neurociencia actual. Desde la neurociencia experimental algunos test computarizados han sido desarrollados para mejorar nuestro conocimiento de las redes neurales involucradas en la cognición. El Attention Network Test (ANT) permite medir la activad de las 3 redes atencionales (alerta, orientación y función ejecutiva).ObjetivosEl principal objetivo de esta revisión fue describir todas las alteraciones anatómicas y funcionales encontradas en diversas enfermedades neurológicas usando el ANT.Material y métodosUn protocolo de revisión fue aplicado seleccionando estudios desde 2010 en la base de datos PubMed, que involucraban al ATN en diferentes enfermedades neurológicas. Se obtuvieron 32 artículos para esclerosis múltiple, epilepsia o Parkinson entre otras enfermedades.ConclusionesSe confirman algunas de las estructuras anatómicas propuestas para el modelo de 3 grandes redes atencionales. Las estructuras más relevantes para la red de alerta son la corteza prefrontal, las regiones parietales, el tálamo y el cerebelo. El tálamo es también relevante para la red de orientación, junto a regiones parietales posteriores. Respecto a la red ejecutiva no depende exclusivamente de la corteza prefrontal y corteza cingulada anterior, sino también de estructuras subcorticales como los ganglios basales y el cerebelo y sus proyecciones hacia toda la corteza. (AU)

Introduction: Understanding alterations to brain anatomy and cognitive function associated with neurodegenerative diseases remains a challenge for neuroscience today. In experimental neuroscience, several computerised tests have been developed to contribute to our understanding of neural networks involved in cognition. The Attention Network Test (ANT) enables us to measure the activity of 3 attentional networks (alertness, orienting, and executive function).ObjectivesThe main aim of this review is to describe all the anatomical and functional alterations found in diverse neurological diseases using the ANT.Material and methodsWe collected studies published since 2010 in the PubMed database that employed the ANT in different neurological diseases. Thirty-two articles were obtained, addressing multiple sclerosis, epilepsy, and Parkinson's disease, among other disorders.ConclusionsSome of the anatomical structures proposed in the 3 attentional networks model were confirmed. The most relevant structures in the alertness network are the prefrontal cortex, parietal region, thalamus, and cerebellum. The thalamus is also relevant in the orienting network, together with posterior parietal regions. The executive network does not depend exclusively on the prefrontal cortex and anterior cingulate cortex, but also involves such subcortical structures as the basal ganglia and cerebellum and their projections towards the entire cortex. (AU)

Attentional networks in neurodegenerative diseases: anatomical and functional evidence from the Attention Network Test.

INTRODUCTION: Understanding alterations to brain anatomy and cognitive function associated with neurodegenerative diseases remains a challenge for neuroscience today. In experimental neuroscience, several computerised tests have been developed to contribute to our understanding of neural networks involved in cognition. The Attention Network Test (ANT) enables us to measure the activity of 3 attentional networks (alertness, orienting, and executive function). OBJECTIVES: The main aim of this review is to describe all the anatomical and functional alterations found in diverse neurological diseases using the ANT. MATERIAL AND METHODS: We collected studies published since 2010 in the PubMed database that employed the ANT in different neurological diseases. Thirty-two articles were obtained, addressing multiple sclerosis, epilepsy, and Parkinson's disease, among other disorders. CONCLUSIONS: Some of the anatomical structures proposed in the 3 attentional networks model were confirmed. The most relevant structures in the alertness network are the prefrontal cortex, parietal region, thalamus, and cerebellum. The thalamus is also relevant in the orienting network, together with posterior parietal regions. The executive network does not depend exclusively on the prefrontal cortex and anterior cingulate cortex, but also involves such subcortical structures as the basal ganglia and cerebellum and their projections towards the entire cortex.

A systematic review of the application of machine-learning algorithms in multiple sclerosis.

INTRODUCTION: The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years. OBJECTIVE: We present a systematic review of the application of ML algorithms in MS. MATERIALS AND METHODS: We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected. CONCLUSIONS: After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

A systematic review of the application of machine-learning algorithms in multiple sclerosis. / Revisión sistemática de la aplicación de algoritmos de «machine learning¼ en la esclerosis múltiple.

INTRODUCTION: The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years. OBJECTIVE: We present a systematic review of the application of ML algorithms in MS. MATERIALS AND METHODS: We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected. CONCLUSIONS: After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

Altered phase and nonphase EEG activity expose impaired maintenance of a spatial-object attentional focus in multiple sclerosis patients.

Some of the anatomical and functional basis of cognitive impairment in multiple sclerosis (MS) currently remains unknown. In particular, there is scarce knowledge about modulations in induced EEG (nonphase activity) for diverse frequency bands related to attentional deficits in this pathology. The present study analyzes phase and nonphase alpha and gamma modulations in 26 remitting-relapsing multiple sclerosis patients during their participation in the attention network test compared with twenty-six healthy controls (HCs) matched in sociodemographic variables. Behavioral results showed that the MS group exhibited general slowing, suggesting impairment in alerting and orienting networks, as has been previously described in other studies. Time-frequency analysis of EEG revealed that the gamma band was related to the spatial translation of the attentional focus, and the alpha band seemed to be related to the expectancy mechanisms and cognitive processing of the target. Moreover, phase and nonphase modulations differed in their psychophysiological roles and were affected differently in the MS and HC groups. In summary, nonphase modulations can unveil hidden cognitive mechanisms for phase analysis and complete our knowledge of the neural basis of cognitive impairment in multiple sclerosis pathology.

Attentional networks in neurodegenerative diseases: anatomical and functional evidence from the Attention Network Test. / Redes neurales atencionales en enfermedades neurodegenerativas: evidencias anatómico-funcionales empleando el Attention Network Test.

INTRODUCTION: Understanding alterations to brain anatomy and cognitive function associated with neurodegenerative diseases remains a challenge for neuroscience today. In experimental neuroscience, several computerised tests have been developed to contribute to our understanding of neural networks involved in cognition. The Attention Network Test (ANT) enables us to measure the activity of 3 attentional networks (alertness, orienting, and executive function). OBJECTIVES: The main aim of this review is to describe all the anatomical and functional alterations found in diverse neurological diseases using the ANT. MATERIAL AND METHODS: We collected studies published since 2010 in the PubMed database that employed the ANT in different neurological diseases. Thirty-two articles were obtained, addressing multiple sclerosis, epilepsy, and Parkinson's disease, among other disorders. CONCLUSIONS: Some of the anatomical structures proposed in the 3 attentional networks model were confirmed. The most relevant structures in the alertness network are the prefrontal cortex, parietal region, thalamus, and cerebellum. The thalamus is also relevant in the orienting network, together with posterior parietal regions. The executive network does not depend exclusively on the prefrontal cortex and anterior cingulate cortex, but also involves such subcortical structures as the basal ganglia and cerebellum and their projections towards the entire cortex.

[The Attention Network Test in the study of cognitive impairment of ADHD patients]. / El Attention Network Test en el estudio de los déficits cognitivos de pacientes con trastorno por déficit de atención.

INTRODUCTION: The Attention Network Test (ANT) has been applied to the study of potential attentional impairments in diverse neuropathologies in the last years. This test allows analyzing of different networks involved in attentional processing (alerting, orientation and executive system). DEVELOPMENT: A specific application of ANT in ADHD patients shows that it is possible to find diverse impairments in the three attentional networks and even some studies revealed no alterations. Potential causes of this heterogeneity in the results could be based in methodological variations between studies, other pathological conditions in the participants and the network effects calculation that has been probed that could be wrongly interpreted. CONCLUSIONS: Despite the lack of conclusive results, this test shows multiple applications that would allow disentangling diverse cognitive impairments in ADHD patients. ANT could analyze diverse cognitive mechanisms that could be compromised in these patients (tonic and phasic alerting, temporal and spatial expectancy, degree of interference of the distractor stimuli, attentional blinking o inhibition of return). This test could help to perform a better characterization of ADHD patients further than the classical forms considered nowadays (unattended and combined).

TITLE: El Attention Network Test en el estudio de los déficits cognitivos de pacientes con trastorno por déficit de atención.Introducción. El Attention Network Test (ANT) se ha aplicado en el estudio de las posibles alteraciones atencionales en diversas neuropatologías en los últimos años. Este test permite el análisis de diversas redes implicadas en el proceso atencional (alerta, orientación y sistema ejecutivo). Desarrollo. La aplicación particular del ANT en pacientes con trastorno por déficit de atención muestra que es posible encontrar diversas alteraciones de las tres redes atencionales según los estudios e incluso, en algunos casos, la ausencia de alteraciones en ellas. Las posibles causas de esta heterogeneidad pueden deberse a variaciones metodológicas en la aplicación del test, otras condiciones patológicas no consideradas de los pacientes y el análisis de redes sugerido por los creadores del modelo y que se ha demostrado en diversos estudios que puede llevar a interpretaciones erróneas. Conclusiones. A pesar de los resultados todavía poco concluyentes con la aplicación del ANT en el trastorno por déficit de atención, este test muestra múltiples aplicaciones que permitirán desentrañar los diversos déficits cognitivos que están presentes en los pacientes con trastorno por déficit de atención. Entre ellos, el test puede analizar diversos mecanismos que pueden estar afectados en estos pacientes (la alerta tónica y fásica, la expectativa temporal o espacial, el grado de interferencia de los estímulos distractores, el parpadeo atencional o la inhibición de retorno). El ANT puede ayudar a una mejor caracterización de los pacientes con trastorno por déficit de atención más allá de las formas clásicas consideradas hasta ahora (inatento o combinado).