Machine Learning Based on Computed Tomography Pulmonary Angiography in Evaluating Pulmonary Artery Pressure in Patients with Pulmonary Hypertension.

BACKGROUND: Right heart catheterization is the gold standard for evaluating hemodynamic parameters of pulmonary circulation, especially pulmonary artery pressure (PAP) for diagnosis of pulmonary hypertension (PH). However, the invasive and costly nature of RHC limits its widespread application in daily practice. PURPOSE: To develop a fully automatic framework for PAP assessment via machine learning based on computed tomography pulmonary angiography (CTPA). MATERIALS AND METHODS: A machine learning model was developed to automatically extract morphological features of pulmonary artery and the heart on CTPA cases collected between June 2017 and July 2021 based on a single center experience. Patients with PH received CTPA and RHC examinations within 1 week. The eight substructures of pulmonary artery and heart were automatically segmented through our proposed segmentation framework. Eighty percent of patients were used for the training data set and twenty percent for the independent testing data set. PAP parameters, including mPAP, sPAP, dPAP, and TPR, were defined as ground-truth. A regression model was built to predict PAP parameters and a classification model to separate patients through mPAP and sPAP with cut-off values of 40 mm Hg and 55 mm Hg in PH patients, respectively. The performances of the regression model and the classification model were evaluated by analyzing the intraclass correlation coefficient (ICC) and the area under the receiver operating characteristic curve (AUC). RESULTS: Study participants included 55 patients with PH (men 13; age 47.75 ± 14.87 years). The average dice score for segmentation increased from 87.3% ± 2.9 to 88.2% ± 2.9 through proposed segmentation framework. After features extraction, some of the AI automatic extractions (AAd, RVd, LAd, and RPAd) achieved good consistency with the manual measurements. The differences between them were not statistically significant (t = 1.222, p = 0.227; t = -0.347, p = 0.730; t = 0.484, p = 0.630; t = -0.320, p = 0.750, respectively). The Spearman test was used to find key features which are highly correlated with PAP parameters. Correlations between pulmonary artery pressure and CTPA features show a high correlation between mPAP and LAd, LVd, LAa (r = 0.333, p = 0.012; r = -0.400, p = 0.002; r = -0.208, p = 0.123; r = -0.470, p = 0.000; respectively). The ICC between the output of the regression model and the ground-truth from RHC of mPAP, sPAP, and dPAP were 0.934, 0.903, and 0.981, respectively. The AUC of the receiver operating characteristic curve of the classification model of mPAP and sPAP were 0.911 and 0.833. CONCLUSIONS: The proposed machine learning framework on CTPA enables accurate segmentation of pulmonary artery and heart and automatic assessment of the PAP parameters and has the ability to accurately distinguish different PH patients with mPAP and sPAP. Results of this study may provide additional risk stratification indicators in the future with non-invasive CTPA data.

Comparative analysis of hydraulic refrigeration and mechanical vapour compression water cooling technologies in designing a technical system for oysters conservation.

The phenomenon of summer mortality in Pacific oysters cultures also occurs in Brazilian crops, with predominance in the adult phase, generating significant losses for local producers. In the search for a technological solution to mitigate its effects, the mechanical vapour compression and hydraulic refrigeration concepts are evaluated as two proposed cooling technologies. The comparative analysis carried out with numeric simulations indicated that the hydraulic cooling system presents disadvantages regarding both the size of the compression column and the energy efficiency, compared to the mechanical vapour compression cycle. By computing only the compression power, a COP value of 6.9 results for the MVCS at TCOND = 29.5 oC and TEVAP = 7.2 oC, while for HRS the COP value is around 3.1 for identical conditions. Results from the analysis contradict former publications, but are consistent with recent findings reported in literature.

A Bag of Concepts Approach for Biomedical Document Classification Using Wikipedia Knowledge*. Spanish-English Cross-language Case Study.

OBJECTIVES: The ability to efficiently review the existing literature is essential for the rapid progress of research. This paper describes a classifier of text documents, represented as vectors in spaces of Wikipedia concepts, and analyses its suitability for classification of Spanish biomedical documents when only English documents are available for training. We propose the cross-language concept matching (CLCM) technique, which relies on Wikipedia interlanguage links to convert concept vectors from the Spanish to the English space. METHODS: The performance of the classifier is compared to several baselines: a classifier based on machine translation, a classifier that represents documents after performing Explicit Semantic Analysis (ESA), and a classifier that uses a domain-specific semantic annotator (MetaMap). The corpus used for the experiments (Cross-Language UVigoMED) was purpose-built for this study, and it is composed of 12,832 English and 2,184 Spanish MEDLINE abstracts. RESULTS: The performance of our approach is superior to any other state-of-the art classifier in the benchmark, with performance increases up to: 124% over classical machine translation, 332% over MetaMap, and 60 times over the classifier based on ESA. The results have statistical significance, showing p-values < 0.0001. CONCLUSION: Using knowledge mined from Wikipedia to represent documents as vectors in a space of Wikipedia concepts and translating vectors between language-specific concept spaces, a cross-language classifier can be built, and it performs better than several state-of-the-art classifiers.

Knowledge of the brain death concept by personnel in Spanish and Latin-American healthcare centers.

BACKGROUND: The knowledge and acceptance of the concept of brain death (BD) among health care personnel is fundamental. OBJECTIVE: To analyze the level of understanding of the BD concept among personnel in Spanish and Latin American healthcare centers and to determine the factors affecting this attitude. MATERIAL AND METHODS: Data from 12 hospitals and 32 primary care centers in 4 countries within the International Collaborative Donor Project were selected (Spain, Mexico, Cuba and Costa Rica (n=4378)). RESULTS: 62% of the personnel (n=2714) understood BD and believed that this was the death of an individual. Of the rest, 30% (n=1333) did not understand it and the remaining 8% (n=331) believed it did not mean the death of a patient. 83% (n=931) of physicians understood BD, compared to 75% (n=895) of nurses, 55% (n=299) of healthcare assistants, 53% (n=108) of non-healthcare university-educated personnel and 36% (n=481) of those without a university education (p<0.001). 68% (n=1084) of Mexicans understood BD compared to 66% (n=134) of Cubans, 58% (n=1411) of Spaniards, and 52% (n=85) (p<0.001) of Costa Ricans. There were significant relationships between knowledge of the concept and the following: type of healthcare center (p<0.001), clinical service (p<0.001), having spoken about organ donation within the family (p<0.001) and one's partner's attitude to the subject (p<0.001). A direct relationship has been found between understanding the concept and attitude toward deceased donation (p<0.001). CONCLUSIONS: The understanding of BD by personnel from healthcare centers was not as good as expected. There were marked differences depending on job category.

Arritmias ventriculares malignas en pacientes con cardiodesfibrilador implantable: signos eléctricos predictoresde recidivas / Malignant ventricular arrhythmias in patients with implantable cardioverter-defibrillators: electrical signals which are predictors of recurrence

Introducción: Existe un número creciente de pacientes con cardiodesfibriladores, lasrecidivas son frecuentes y los choques eléctricos constituyen el principal factor reductor de la calidad de vida. Objetivo: Identificar los predictores electrocardiográficos de recidivas de arritmias ventriculares malignas en estos sujetos. Método: De un universo de 76 pacientes a los que se les había implantado un cardiodesfibrilador automático implantable, se seleccionaron 46 y se confeccionaron dos grupos. El A estuvo constituido por 27 pacientes, con al menos un episodio de arritmias ventriculares malignas tras el implante del dispositivo; y el B, por los 19 sujetos sin recurrencias. Las mediciones (QTc prolongado, dispersión anormal del QT, Tpico-Tfinal y su dispersiónanormal) se promediaron en tres latidos consecutivos en cada derivación, de forma manual, por dos observadores independientes. Resultados: En el grupo A predominó la cardiopatía estructural y la fracción de eyección inferior a 35 por ciento. Estuvieron igualmente representados la fragmentación del complejo QRS, la onda T bimodal y el patrón de repolarización precoz. Hubo diferencias significativas en los valores medios del intervalo QT (428 vs. 390 ms), p=0.004; del QT corregido (476 vs. 436 ms), p=0.011; y del intervalo Tpico-Tfinal (108 vs. 87 ms), p=0.006. No existieron en la dispersión del QT (51 vs. 48 ms), la dispersión del TpicoTfinal (35 vs. 27 ms), ni en la duración del QRS (121 vs. 105 ms). Conclusiones: Los intervalos QT, QTc y Tpico-Tfinal son predictores electrocardiográficos de recidivas de arritmias ventriculares en pacientes con cardiodesfibriladores. Palabras clave: Cardiodesfibrilador implantable, Predictores eléctricos, Recidivas,Arritmias ventriculares malignas(AU)

Attitudes of non-medical staff in hospitals in Spain, Mexico, Cuba and Costa Rica towards organ donation.

INTRODUCTION: Non-medical staff members in hospitals are highly credible at population level, and are a source of opinion even though they do not have sufficient medical training. OBJECTIVES: To analyse the attitudes of non-medical professionals of Spanish and Latin American hospitals towards organ donation and identify the factors that influence these attitudes. MATERIAL AND METHOD: Through the "Proyecto Colaborativo Internacional Donante" (International Collaborative Donor Project), a stratified random sample was selected from non-medical services of eleven hospitals: 3 Spanish (n=277), 5 Mexican (n=632), 2 Cuban (n=42) and 1 Costa Rican (n=101). RESULTS: Of the 1052 professionals surveyed, 72% (n=754) were in favour of donating an organ after death. By country, 98% of Cubans, 80% of Mexicans, 66% of Costa Ricans and 52% of Spanish were in favour (P<.001). The most influential variables were: 1) country, with results being more positive in Mexico (odds ratio [OR]=2.197), 2) believing in the possibility that they will require a transplant (OR=2.202), 3) having discussed the issue with their family (OR=3.23), 4) the positive attitude of their partner towards donation (OR=3.322), 5) not being concerned about possible mutilation of their body after donation (OR=3.378), 6) preferring options other than burial (OR=2.525), 7) accepting an autopsy (OR=2.958). CONCLUSIONS: The attitude of non-medical staff members of hospitals towards the donation of their own organs varies greatly depending on the country of the respondent. Psychosocial factors that influence these attitudes are similar to those described at the population level.

[Health education in schools for adults: by a teacher or health education lecture?]. / Educación para la salud en escuelas de adultos: Por medio del profesor o mediante charla de educación sanitaria?

OBJECTIVE: To compare the results of two ways of teaching the rational use of medicines to students of centres of permanent education of adults (CPEA): one taught by the normal teachers (after training by health personnel) and one through a lecture given by the health staff. DESIGN: Intervention study without randomised distribution and with a control group. SETTING: Five CPEA in an urban centre. PARTICIPANTS: 385 students and 15 CPEA teachers. INTERVENTIONS: Three groups: a) "teachers" group: consisting of students who received education on medicines in the class-room through their teachers, who had been previously trained by health personnel; b) "lecture" group: students who had received a health education lecture on medicines given by health staff; c) non-intervention group. All three groups were administered a questionnaire before and after the intervention. Both questionnaires were paired. MEASUREMENTS AND MAIN RESULTS: 248 people completed the first questionnaire and 149 the second. Significant gains in knowledge were only found in the teachers intervention group (p < 0.01; 7.8% increase in score). Dividing the students into terciles made these gains significantly greater (11.7%) in the students of the teachers group who in the first questionnaire had intermediate scores than in the students in the other groups who had intermediate scores. CONCLUSIONS: Intervention with teachers seems more effective than either a health education lecture or no intervention, especially in the improvement in knowledge of students who already had beforehand intermediate knowledge.

Educación para la salud en escuelas de adultos: ¿por medio del profesor o mediante charla de educación sanitaria? / Health education in schools for adults: through the teacher or a health education lecture?

Objetivo. Comparar los resultados de dos modalidades de enseñanza sobre uso racional de medicamentos en alumnos de centros de educación permanente de adultos (CEPA): la realizada a través del profesorado (formado previamente por los sanitarios) o mediante charla de educación impartida por el personal sanitario. Diseño. Estudio de intervención sin distribución aleatoria, con grupo control. Emplazamiento. Cinco CEPA de un núcleo urbano. Participantes. Trescientos ochenta y cinco alumnos y 15 profesores de CEPA. Intervenciones. Tres grupos: a)grupo 'profesores', constituido por alumnos que recibieron educación sobre medicamentos en el aula, mediante sus profesores, los cuales habían sido formados previamente por los sanitarios; b)grupo 'charla': alumnos que recibieron una charla de educación sanitaria sobre medicamentos impartida por los sanitarios, y c)grupo no intervención. En los 3 grupos se realizó encuesta previa y posterior a la intervención. Ambas encuestas fueron apareadas. Mediciones y resultados principales. Doscientos cuarenta y ocho sujetos completaron la primera encuesta y 149 la segunda. Sólo se encontraron ganancias significativas de conocimiento en el grupo de intervención con profesores (p < 0,01; 7,8 por ciento de ganancia de puntos relativa). Si dividíamos a los alumnos en terciles, estas ganancias eran superiores (11,7 por ciento) significativamente en los alumnos del grupo 'profesores' con puntuaciones previas intermedias en la primera encuesta, en comparación con los alumnos de puntuación intermedia de los otros grupos. Conclusiones. La intervención mediante 'profesores' parece mostrarse más efectiva que la realizada mediante 'charla de educación sanitaria' o la 'no intervención', y se diferencia de éstas en la mejoría de conocimientos en los alumnos con conocimientos previos intermedios (AU)