MindReader: Unsupervised Classification of Electroencephalographic Data.

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.

The role of short-term video electroencephalogram monitoring for epilepsy and psychogenic seizures: Experience from a Latin American referral center.

Short-term VEEG represents an affordable option in limited resources environments. There are few reports on its use. Its diagnostic yield is variable (7-57%) and can be related to the differences in recording time. The present study analyzes possible predictive factors to support the indication of a short-term VEEG. We analyzed short-term VEEG studies (<24 h) throughout a period of 5 years (2013-2017). The patients were clustered according to the date of last epileptic seizure and the frequency of epileptic events per month and subcategorized depending on the frequency found. Chi square univariate analysis was performed looking for predictive variables to obtain an epileptic short-term EEG. A multivariate logistic regression analysis was performed with statistically significant variables. A total of 1092 VEEG were analyzed from 832 patients. 34.5% were reported as epileptic VEEG. In the multivariate analysis, 3 predictors of epileptic short-term VEEG were identified: The use of 2 or more antiepileptic drugs (AEDs) (OR 1.67, CI 1.23-2.25, p = 0.001), the presence of an epileptic event in the last month (OR 1.53, CI 1.07-2.17, p = 0.018) and daily seizures (OR 1.84, CI 1.21-2.78, p = 0.004). Six-month seizure free subjects predict a non-epileptic VEEG (OR 0.58, CI 0.30-0.89, p = 0.013).

Blood pressure at hospital admission and outcome after primary intracerebral hemorrhage.

INTRODUCTION: The importance of the admission blood pressure (BP) for intracerebral hemorrhage (ICH) outcome is not completely clear. Our objective was to analyze the clinical impact of BP at hospital arrival in patients with primary ICH. MATERIAL AND METHODS: We studied 316 patients (50% women, mean age: 64 years, 75% with hypertension history) with acute primary ICH. The first BP reading at admission was evaluated for its association with neuroimaging findings and outcome. A Cox proportional hazards model and Kaplan-Meier analyses were constructed to evaluate factors associated with in-hospital mortality. RESULTS: Intraventricular irruption occurred in 52% of cases. A high frequency of third ventricle extension was observed in patients with BP readings in the upper quartiles of the distribution (systolic, diastolic, or mean arterial pressure). Blood pressure readings did not correlate with hematoma volumes. In-hospital case fatality rate was 46% (63% among those with ventricular irruption). Systolic BP (SBP) > 190 mm Hg was independently associated with in-hospital mortality in supratentorial (n = 285) ICH (hazard ratio: 1.19, 95% confidence interval: 1.02-1.38, for the highest vs. the lowest quartile) even after adjustment for known strong predictors (age, ICH volume, Glasgow coma scale and ventricular extension). Blood pressure was not significantly associated with ventricular extension or outcome in patients with infratentorial ICH. CONCLUSIONS: A high BP on admission is associated with an increased risk of intraventricular extension and early mortality in patients with supratentorial ICH. However, a significant proportion of patients with high BP readings without ventricular irruption still have an increased risk of death.

Evaluation of blood pressure measurements in first ambulatory neurological consultations: a missed part of the physical examination?

OBJECTIVE: To obtain a blood pressure reading is mandatory during either the general or specialized physical examination. This study describes factors associated with the accomplishment of blood pressure measurement in the first neurological consultation. METHODS: We studied first ambulatory neurology consultations in a Mexican referral hospital. Demographic characteristics, diagnostic category of referral, final diagnosis and data on physical examination were collected to establish a logistic regression analysis in order to identify factors associated with the accomplishment of blood pressure measurement. RESULTS: Over 8 months 778 outpatients were studied. The most frequent diagnoses for first consultation were headache (26%), epilepsy (14%) and stroke (13%). Only in 39% (n=301) of the outpatients blood pressure was registered, among them, 30% had normal blood pressure, 43% had 121-139/81-89 mmHg, 20% had 140-159/90-99 mmHg and 7% had ≥ 160/100 mmHg. The independent factors that favored the practice of BP determination in multivariable analysis were >65 years of age (odds ratio: 2.26; 95% confidence interval: 1.52-3.36) and headache complaint (odds ratio: 1.81, 95% confidence interval: 1.30-2.53). Notably, only 43% of patients with stroke had blood pressure registration, even when these stroke patients had blood pressure readings, they had higher blood pressure than with other diagnoses (p<0.05). CONCLUSION: Blood pressure registration was frequently omitted from the first neurological consultation, particularly in outpatients who might need it the most.

Evaluation of blood pressure measurements in first ambulatory neurological consultations: A missed part of the physical examination? / Evaluación de la medición de la presión arterial en primeras consultas neurológicas ambulatorias: ¿una parte olvidada del examen físico?

Objective: To obtain a blood pressure reading is mandatory during either the general or specialized physical examination. This study describes factors associated with the accomplishment of blood pressure measurement in the first neurological consultation. Methods: We studied first ambulatory neurology consultations in a Mexican referral hospital. Demographic characteristics, diagnostic category of referral, final diagnosis and data on physical examination were collected to establish a logistic regression analysis in order to identify factors associated with the accomplishment of blood pressure measurement. Results: Over 8 months 778 outpatients were studied. The most frequent diagnoses for first consultation were headache (26%), epilepsy (14%) and stroke (13%). Only in 39% (n = 301) of the outpatients blood pressure was registered, among them, 30% had normal blood pressure, 43% had 121-139/81-89mmHg, 20% had 140-159/90-99mmHg and 7% had ≥ 160/100mmHg. The independent factors that favored the practice of BP determination in multivariable analysis were >65 years of age (odds ratio: 2.26; 95% confidence interval: 1.52-3.36) and headache complaint (odds ratio: 1.81, 95% confidence interval: 1.30-2.53). Notably, only 43% of patients with stroke had blood pressure registration, even when these stroke patients had blood pressure readings, they had higher blood pressure than with other diagnoses (p< 0.05). Conclusion: Blood pressure registration was frequently omitted from the first neurological consultation, particularly in outpatients who might need it the most.

Objetivo: La medición de la presión arterial es mandatoria durante el examen físico general o especializado. Este estudio describe factores asociados al cumplimiento de la medición de la presión arterial en la primera consulta neurológica. Métodos: Realizamos un estudio sobre consultas neurológicas ambulatorias en un hospital de referencia mexicano. Se recolectaron características demográficas, categoría diagnóstica de referencia, diagnóstico final y datos sobre el examen físico para construir un análisis de regresión logística con el objetivo de identificar factores asociados con el cumplimiento de la medición de la presión arterial. Resultados: Durante 8 meses estudiamos a 778 pacientes. Los diagnósticos de envío más frecuentes fueron cefalea (26%), epilepsia (14%) y enfermedad cerebrovascular (13%). Solo en el 39% (n = 301) de los pacientes se midió la presión arterial y, de entre ellos, el 30% presentaron presión arterial normal, el 43% 121-139/81-89mmHg, el 20% 140-159/90-99mmHg y el 7% ≥ 160/100 mmHg. En un análisis multivariable, la edad > 65 años (razón de momios: 2.26, intervalo de confianza del 95%: 1.52-3.36) y cefalea como motivo de consulta (razón de momios: 1.81, intervalo de confianza del 95%: 1.30-2.53) fueron los factores independientes asociados al registro de la presión arterial. De manera notable, solo al 43% de los pacientes con enfermedad cerebrovascular se les había registrado la presión sanguínea; estos pacientes la tenían más elevada que los pacientes con otros diagnósticos (p <0.05). Conclusión: En este estudio con frecuencia se omitió el registro de la presión arterial en la primera consulta neurológica, especialmente en pacientes que podrían necesitarlo más.

Modificaciones morfológicas en pacientes tratados con el Truax Corrector II: Sancti Spíritus: 2009-2010

Fundamento: El tratamiento del retrognatismo mandibular en edades tempranas se realiza con gran variedad de aparatos ortopédicos funcionales. El Truax Corrector II es uno de los aparatos con eficacia demostrada internacionalmente y poco estudiado en Cuba. Objetivo: Describir las modificaciones morfológicas en pacientes con retrognatismo mandibular tratados con el Truax Corrector II. Metodología: Se realizó un estudio transversal entre diciembre de 2009 a 2010 en la Clínica Estomatológica Provincial de Sancti Spíritus. La muestra quedó conformada por 12 niños de 7 a 10 años con retrognatismo mandibular y período de crecimiento activo. Se evolucionaron las variables: resalte y sobrepase incisivos, ancho transversal de ambos maxilares y relaciones de molares derecha e izquierda. Se utilizó el test de comparación de medias para muestras pareadas, el de Rangos con signos de Wilcoxon y el algoritmo de Monte Carlos. Resultados: En el 100 por ciento de los pacientes ocurrió disminución de 3,75 mm como promedio del resalte incisivo, un aumento de los diámetros transversales maxilares (0,8 mm el superior y 1,4 el inferior) y una disminución de 0,66 mm como promedio del sobrepase incisivo. Las relaciones molares derechas e izquierda evolucionaron a neutroclusión en un 83,3 por ciento de los pacientes en estudio. Conclusiones: La totalidad de los pacientes tratados con el Truax Corrector II mostró una evolución satisfactoria, con mejoría de las variables morfológicas estudiadas (AU)

Background: The treatment of mandibular retrognathia in early ages is performed with a variety of functional orthopedic devices. The Truax Corrector II is one of the devices with internationally proven efficacy and little studied in Cuba. Objective: Describing the morphological changes in patients with mandibular retrognathia treated with the Truax Corrector II. Methodology: A cross-sectional study was made from December 2009 to 2010 in the Provincial Dental Clinic of Sancti Spiritus. The sample consisted of 12 children from 7 to 10 years with mandibular retrognathia and in a period of active growth. The variables studied included: overjet and overbite of incisors, transverse width of both jaws and right and left molar ratios. The tests used included the comparison of means for paired samples, that of Wilcoxons signed ranks and Monte Carlo algorithm. Results: In 100 porcent of the patients occurred an average decrease of 3,75 mm in incisor overjet, an increase of jaw transverse diameters (0.8 mm the upper and 1,4 mm the lower) and an average drop of 0,66 mm in incisor overbite. The right and left molar ratios evolved to neutroclusion in 83,3 porcent of patients studied. Conclusions: All patients treated with the Truax Corrector II showed a satisfactory outcome, with improvement of the morphological variables studied