Search

In this article, we have carried out a case study to optimize the classification of the maliciousness of cybersecurity events by IP addresses using machine learning techniques. The optimization is studied focusing on time complexity. Firstly, we have used the extreme gradient boosting model, and secondly, we have parallelized the machine learning algorithm to study the effect of using a different number of cores for the problem. We have classified the cybersecurity events’ maliciousness in a biclass and a multiclass scenario. All the experiments have been carried out with a well-known optimal set of features: the geolocation information of the IP address. However, the geolocation features of an IP address can change over time. Also, the relation between the IP address and its label of maliciousness can be modified if we test the address several times. Then, the models’ performance could degrade because the information acquired from training on past samples may not generalize well to new samples. This situation is known as concept drift. For this reason, it is necessary to study if the optimization proposed works in a concept drift scenario. The results show that the concept drift does not degrade the models. Also, boosting algorithms achieving competitive or better performance compared to similar research works for the biclass scenario and an effective categorization for the multiclass case. The best efficient setting is reached using five nodes regarding high-performance computation resources.

Objective: Analyse the clinical profile, associated tumour types, and response to treatment of paraneoplastic neurological syndromes associated with antibodies against Ma proteins. Methods: A retrospective study of patients with antibodies against Ma proteins identified in a neuroimmunology laboratory of reference. Results: Of the 32 patients identified, 20 showed reactivity against Ma2 only (anti-Ma2 antibodies), 11 against Ma1 and Ma2 (anti-Ma antibodies), and 1 with reactivity against Ma1 only (anti-Ma1 antibodies). The most common clinical presentations were limbic encephalopathy, diencephalic dysfunction, or brainstem encephalopathy, frequently appearing as a combination of these features. Three patients had isolated cerebellar dysfunction with anti-Ma antibodies, and 2 exhibited peripheral nervous system syndrome with anti-Ma2 antibodies. Testicular tumours were the most common neoplasms (40%) in the anti-Ma2 cases. In the group associated with anti-Ma1 antibodies, the most common were lung tumours (36%), followed by testicular tumours. All idiopathic cases were reactive to Ma2. The clinical outcome was significantly better in the anti-Ma2 group. The patient with anti-Ma1 presented with limbic encephalitis and brainstem dysfunction associated with lymphoepithelioma of the bladder. Conclusions: Specifically determining the different reactivities of anti-Ma protein antibodies in order to differentiate between Ma1 and Ma2 antibodies is important because anti-Ma2-associated paraneoplastic syndromes have a better outcome. Lastly, this study is the first to confirm that there may be cases that react exclusively to antibodies against Ma1. Resumen: Objetivo: Analizar el perfil clínico, los tipos de tumour asociado y la respuesta al tratamiento de los síndromes neurológicos paraneoplásicos asociados a anticuerpos contra proteínas Ma. Métodos: Estudio retrospectivo de los pacientes con anticuerpos contra proteínas Ma identificados en un laboratorio de referencia en neuroinmunología. Resultados: Se diagnosticó a 32 pacientes, 20 con reactividad frente a Ma2 aislada (anticuerpos anti-Ma2), 11 con reactividad frente a Ma1 y Ma2 (anticuerpos anti-Ma) y uno con reactividad frente a Ma1 aislada (anticuerpos anti-Ma1). La presentación clínica más frecuente fue un cuadro neurológico que de forma aislada o en combinación afectó al sistema límbico, diencéfalo y mesencéfalo. Tres pacientes presentaron un cuadro cerebeloso aislado con anti-Ma y 2 un síndrome periférico con anti-Ma2. Los tumores testiculares fueron los más frecuentes (40%) en los casos anti-Ma2. En el grupo asociado a anti-Ma1, los más frecuentes fueron los tumores de pulmón (36%), seguidos de los testiculares. Todos los casos idiopáticos fueron reactivos frente a Ma2. La evolución clínica fue significativamente mejor en el grupo anti-Ma2. El paciente con anti-Ma1 presentó un cuadro de encefalitis límbica y mesodiencefálica asociado a un cáncer linfoepitelial de vejiga. Conclusiones: La determinación específica de las diferentes reactividades de las proteínas Ma, diferenciando los anticuerpos frente a Ma1 y Ma2, es importante pues los síndromes neurológicos asociados a anticuerpos anti-Ma2 responden mejor al tratamiento. Finalmente, se confirma por primera vez que puede haber casos con anticuerpos que solo reaccionan contra Ma1. Keywords: Paraneoplastic neurological syndromes, Limbic encephalitis, Onconeural antibodies, Anti-Ma, Anti-Ma2, Palabras clave: Síndromes neurológicos paraneoplásicos, Encefalitis límbica, Anticuerpos onconeuronales, Anti-Ma, Anti-Ma2

Resumen: Objetivo: Analizar el perfil clínico, los tipos de tumor asociado y la respuesta al tratamiento de los síndromes neurológicos paraneoplásicos asociados a anticuerpos contra proteínas Ma. Métodos: Estudio retrospectivo de los pacientes con anticuerpos contra proteínas Ma identificados en un laboratorio de referencia en neuroinmunología. Resultados: Se diagnosticó a 32 pacientes, 20 con reactividad frente a Ma2 aislada (anticuerpos anti-Ma2), 11 con reactividad frente a Ma1 y Ma2 (anticuerpos anti-Ma) y uno con reactividad frente a Ma1 aislada (anticuerpos anti-Ma1). La presentación clínica más frecuente fue un cuadro neurológico que de forma aislada o en combinación afectó al sistema límbico, diencéfalo y mesencéfalo. Tres pacientes presentaron un cuadro cerebeloso aislado con anti-Ma y 2 un síndrome periférico con anti-Ma2. Los tumores testiculares fueron los más frecuentes (40%) en los casos anti-Ma2. En el grupo asociado a anti-Ma1, los más frecuentes fueron los tumores de pulmón (36%), seguidos de los testiculares. Todos los casos idiopáticos fueron reactivos frente a Ma2. La evolución clínica fue significativamente mejor en el grupo anti-Ma2. El paciente con anti-Ma1 presentó un cuadro de encefalitis límbica y mesodiencefálica asociado a un cáncer linfoepitelial de vejiga. Conclusiones: La determinación específica de las diferentes reactividades de las proteínas Ma, diferenciando los anticuerpos frente a Ma1 y Ma2, es importante pues los síndromes neurológicos asociados a anticuerpos anti-Ma2 responden mejor al tratamiento. Finalmente, se confirma por primera vez que puede haber casos con anticuerpos que solo reaccionan contra Ma1. Abstract: Objective: Analyse the clinical profile, associated tumour types, and response to treatment of paraneoplastic neurological syndromes associated with antibodies against Ma proteins. Methods: A retrospective study of patients with antibodies against Ma proteins identified in a neuroimmunology laboratory of reference. Results: Of the 32 patients identified, 20 showed reactivity against Ma2 only (anti-Ma2 antibodies), 11 against Ma1 and Ma2 (anti-Ma antibodies), and 1 with reactivity against Ma1 only (anti-Ma1 antibodies). The most common clinical presentations were limbic encephalopathy, diencephalic dysfunction, or brainstem encephalopathy, frequently appearing as a combination of these features. Three patients had isolated cerebellar dysfunction with anti-Ma antibodies, and 2 exhibited peripheral nervous system syndrome with anti-Ma2 antibodies. Testicular tumours were the most common neoplasms (40%) in the anti-Ma2 cases. In the group associated with anti-Ma1 antibodies, the most common were lung tumours (36%), followed by testicular tumours. All idiopathic cases were reactive to Ma2. The clinical outcome was significantly better in the anti-Ma2 group. The patient with anti-Ma1 presented with limbic encephalitis and brainstem dysfunction associated with lymphoepithelioma of the bladder. Conclusions: Specifically determining the different reactivities of anti-Ma protein antibodies in order to differentiate between Ma1 and Ma2 antibodies is important because anti-Ma2-associated paraneoplastic syndromes have a better outcome. Lastly, this study is the first to confirm that there may be cases that react exclusively to antibodies against Ma1. Palabras clave: Síndromes neurológicos paraneoplásicos, Encefalitis límbica, Anticuerpos onconeuronales, Anti-Ma, Anti-Ma2, Keywords: Paraneoplastic neurological syndromes, Limbic encephalitis, Onconeural antibodies, Anti-Ma, Anti-Ma2