Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 4 de 4
Filter
Add more filters










Database
Language
Publication year range
1.
Sensors (Basel) ; 23(6)2023 Mar 09.
Article in English | MEDLINE | ID: mdl-36991682

ABSTRACT

Electroencephalogram (EEG) interpretation plays a critical role in the clinical assessment of neurological conditions, most notably epilepsy. However, EEG recordings are typically analyzed manually by highly specialized and heavily trained personnel. Moreover, the low rate of capturing abnormal events during the procedure makes interpretation time-consuming, resource-hungry, and overall an expensive process. Automatic detection offers the potential to improve the quality of patient care by shortening the time to diagnosis, managing big data and optimizing the allocation of human resources towards precision medicine. Here, we present MindReader, a novel unsupervised machine-learning method comprised of the interplay between an autoencoder network, a hidden Markov model (HMM), and a generative component: after dividing the signal into overlapping frames and performing a fast Fourier transform, MindReader trains an autoencoder neural network for dimensionality reduction and compact representation of different frequency patterns for each frame. Next, we processed the temporal patterns using a HMM, while a third and generative component hypothesized and characterized the different phases that were then fed back to the HMM. MindReader then automatically generates labels that the physician can interpret as pathological and non-pathological phases, thus effectively reducing the search space for trained personnel. We evaluated MindReader's predictive performance on 686 recordings, encompassing more than 980 h from the publicly available Physionet database. Compared to manual annotations, MindReader identified 197 of 198 epileptic events (99.45%), and is, as such, a highly sensitive method, which is a prerequisite for clinical use.


Subject(s)
Electroencephalography , Epilepsy , Humans , Electroencephalography/methods , Epilepsy/diagnosis , Neural Networks, Computer , Fourier Analysis , Unsupervised Machine Learning
2.
Neurology ; 98(19): e1933-e1941, 2022 05 10.
Article in English | MEDLINE | ID: mdl-35277439

ABSTRACT

BACKGROUND AND OBJECTIVES: Information on stroke among severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccines remains scarce. We report stroke incidence as an adverse event following immunization (AEFI) among recipients of 79,399,446 doses of 6 different SARS-CoV-2 vaccines (BNT162b2, ChAdOx1 nCov-19, Gam-COVID-Vac, CoronaVac, Ad5-nCoV, and Ad26.COV2-S) between December 24, 2020, and August 31, 2021, in Mexico. METHODS: This retrospective descriptive study analyzed stroke incidence per million doses among hospitalized adult patients (≥18 years) during an 8-month interval. According to the World Health Organization, AEFIs were defined as clinical events occurring within 30 days after immunization and categorized as either nonserious or serious, depending on severity, treatment, and hospital admission requirements. Acute ischemic stroke (AIS), intracerebral hemorrhage (ICH), subarachnoid hemorrhage (SAH), and cerebral venous thrombosis (CVT) cases were collected through a passive epidemiologic surveillance system in which local health providers report potential AEFI to the Mexican General Board of Epidemiology. Data were captured with standardized case report formats by an ad hoc committee appointed by the Mexican Ministry of Health to evaluate potential neurologic AEFI against SARS-COV-2. RESULTS: We included 56 patients (31 female patients [55.5%]) for an overall incidence of 0.71 cases per 1,000,000 administered doses (95% CI 0.54-0.92). Median age was 65 years (interquartile range [IQR] 55-76 years); median time from vaccination to stroke (of any subtype) was 2 days (IQR 1-5 days). In 27 (48.2%) patients, the event was diagnosed within the first 24 hours after immunization. The most frequent subtype was AIS in 43 patients (75%; 0.54 per 1,000,000 doses, 95% CI 0.40-0.73), followed by ICH in 9 (16.1%; 0.11 per 1,000,000 doses, 95% CI 0.06-0.22) and SAH and CVT, each with 2 cases (3.6%; 0.03 per 1,000,000 doses, 95% CI 0.01-0.09). Overall, the most common risk factors were hypertension in 33 (58.9%) patients and diabetes in 22 (39.3%). Median hospital length of stay was 6 days (IQR 4-13 days). At discharge, functional outcome was good (modified Rankin Scale score 0-2) in 41.1% of patients; in-hospital mortality rate was 21.4%. DISCUSSION: Stroke is an exceedingly rare AEFI against SARS-CoV-2. Preexisting stroke risk factors were identified in most patients. Further research is needed to evaluate causal associations between SARS-COV-2 vaccines and stroke.


Subject(s)
COVID-19 Vaccines , COVID-19 , Ischemic Stroke , Aged , BNT162 Vaccine , COVID-19/epidemiology , COVID-19/prevention & control , COVID-19 Vaccines/adverse effects , ChAdOx1 nCoV-19 , Female , Humans , Ischemic Stroke/epidemiology , Male , Mexico/epidemiology , Middle Aged , Retrospective Studies , SARS-CoV-2 , Vaccination/adverse effects
3.
J Clin Neurophysiol ; 38(3): 231-236, 2021 May 01.
Article in English | MEDLINE | ID: mdl-32141983

ABSTRACT

INTRODUCTION: Intraoperative neurophysiological monitoring (IONM) is widely used to prevent nervous system injury during surgeries in elderly patients. However, there are no studies that describe the characteristics and changes in neurophysiological tests during the IONM of patients aged 60 years and older. The study aims to describe and compare IONM changes during surgeries in adult patients aged 18 to 59 years with those aged 60 years and older. METHODS: We performed a comparative retrospective study of patients aged 18 to 59 years versus those 60 aged years and older who underwent IONM during 2013 to 2018 in Mexico City. Sociodemographic characteristics were recorded and compared. Intraoperative neurophysiological monitoring techniques, their changes, and surgical procedures for both groups were analyzed and compared using descriptive statistics, Mann-Whitney U, Fisher, and χ2 tests. The sensitivity, specificity, and positive and negative predictive values were calculated. RESULTS: In total, 195 patients were analyzed: 104 patients, 68.63 ± 6.54 years old (elderly group) and 91 patients, 42.3 ± 10.5 years old (younger group). No differences were found in the rates of signal change during IONM between the group of elderly patients and the younger group. The sensitivity, specificity, and positive and negative predictive values were 80%, 99%, 80%, and 99%, respectively. CONCLUSIONS: Elderly patients have a similar rate of changes in IONM signals compared with younger patients during heterogeneous surgeries guided by IONM.


Subject(s)
Intraoperative Neurophysiological Monitoring/methods , Neurosurgical Procedures/methods , Adolescent , Adult , Aged , Female , Humans , Male , Mexico , Middle Aged , Retrospective Studies , Young Adult
4.
Front Neurol ; 11: 598974, 2020.
Article in English | MEDLINE | ID: mdl-33324338

ABSTRACT

Epilepsia partialis continua (EPC) has changed in its clinical and pathophysiological definition throughout time. Several etiologies have been described in addition to classic causes of EPC. The following case depicts a young woman who had a peculiar onset of epilepsy with a continuous visual aura becoming a form of chronic recurrent and non-progressive EPC. The patient was initially misdiagnosed as a non-neurological entity (assumed psychiatric in origin), but finally, an immune-mediated epilepsy was diagnosed, and EEG showed focal status epilepticus during evolution. Once the diagnosis was achieved and immune treatment was established, the patient is seizure free. Early identification of an immune basis in patients with epilepsy is important because immunotherapy can reverse the epileptogenic process and reduce the risk of chronic epilepsy. To date, this is the only case reported with EPC manifesting as a continuous visual aura associated with antiglutamic acid decarboxylase 65 (anti-GAD65) and anti-N-methyl-d-aspartate (anti-NMDA) antibodies.

SELECTION OF CITATIONS
SEARCH DETAIL
...