Machine learning in predicting severe acute respiratory infection outbreaks / Aprendizado de máquina na previsão de surtos de síndrome respiratória aguda grave / Aprendizaje automático en la predicción de brotes de síndrome respiratorio agudo grave

Abstract: Severe acute respiratory infection (SARI) outbreaks occur annually, with seasonal peaks varying among geographic regions. Case notification is important to prepare healthcare networks for patient attendance and hospitalization. Thus, health managers need adequate resource planning tools for SARI seasons. This study aims to predict SARI outbreaks based on models generated with machine learning using SARI hospitalization notification data. In this study, data from the reporting of SARI hospitalization cases in Brazil from 2013 to 2020 were used, excluding SARI cases caused by COVID-19. These data were prepared to feed a neural network configured to generate predictive models for time series. The neural network was implemented with a pipeline tool. Models were generated for the five Brazilian regions and validated for different years of SARI outbreaks. By using neural networks, it was possible to generate predictive models for SARI peaks, volume of cases per season, and for the beginning of the pre-epidemic period, with good weekly incidence correlation (R2 = 0.97; 95%CI: 0.95-0.98, for the 2019 season in the Southeastern Brazil). The predictive models achieved a good prediction of the volume of reported cases of SARI; accordingly, 9,936 cases were observed in 2019 in Southern Brazil, and the prediction made by the models showed a median of 9,405 (95%CI: 9,105-9,738). The identification of the period of occurrence of a SARI outbreak is possible using predictive models generated with neural networks and algorithms that employ time series.

Resumo: Surtos de síndrome respiratória aguda grave (SRAG) ocorrem anualmente, com picos sazonais variando entre regiões geográficas. A notificação dos casos é importante para preparar as redes de atenção à saúde para o atendimento e internação dos pacientes. Portanto, os gestores de saúde precisam ter ferramentas adequadas de planejamento de recursos para as temporadas de SRAG. Este estudo tem como objetivo prever surtos de SRAG com base em modelos gerados com aprendizado de máquina usando dados de internação por SRAG. Foram incluídos dados sobre casos de hospitalização por SRAG no Brasil de 2013 a 2020, excluindo os casos causados pela COVID-19. Estes dados foram preparados para alimentar uma rede neural configurada para gerar modelos preditivos para séries temporais. A rede neural foi implementada com uma ferramenta de pipeline. Os modelos foram gerados para as cinco regiões brasileiras e validados para diferentes anos de surtos de SRAG. Com o uso de redes neurais, foi possível gerar modelos preditivos para picos de SRAG, volume de casos por temporada e para o início do período pré-epidêmico, com boa correlação de incidência semanal (R2 = 0,97; IC95%: 0,95-0,98, para a temporada de 2019 na Região Sudeste). Os modelos preditivos obtiveram uma boa previsão do volume de casos notificados de SRAG; dessa forma, foram observados 9.936 casos em 2019 na Região Sul, e a previsão feita pelos modelos mostrou uma mediana de 9.405 (IC95%: 9.105-9.738). A identificação do período de ocorrência de um surto de SRAG é possível por meio de modelos preditivos gerados com o uso de redes neurais e algoritmos que aplicam séries temporais.

Resumen: Brotes de síndrome respiratorio agudo grave (SRAG) ocurren todos los años, con picos estacionales que varían entre regiones geográficas. La notificación de los casos es importante para preparar las redes de atención a la salud para el cuidado y hospitalización de los pacientes. Por lo tanto, los gestores de salud deben tener herramientas adecuadas de planificación de recursos para las temporadas de SRAG. Este estudio tiene el objetivo de predecir brotes de SRAG con base en modelos generados con aprendizaje automático utilizando datos de hospitalización por SRAG. Se incluyeron datos sobre casos de hospitalización por SRAG en Brasil desde 2013 hasta 2020, salvo los casos causados por la COVID-19. Se prepararon estos datos para alimentar una red neural configurada para generar modelos predictivos para series temporales. Se implementó la red neural con una herramienta de canalización. Se generaron los modelos para las cinco regiones brasileñas y se validaron para diferentes años de brotes de SRAG. Con el uso de redes neurales, se pudo generar modelos predictivos para los picos de SRAG, el volumen de casos por temporada y para el inicio del periodo pre-epidémico, con una buena correlación de incidencia semanal (R2 = 0,97; IC95%: 0,95-0,98, para la temporada de 2019 en la Región Sudeste). Los modelos predictivos tuvieron una buena predicción del volumen de casos notificados de SRAG; así, se observaron 9.936 casos en 2019 en la Región Sur, y la predicción de los modelos mostró una mediana de 9.405 (IC95%: 9.105-9.738). La identificación del periodo de ocurrencia de un brote de SRAG es posible a través de modelos predictivos generados con el uso de redes neurales y algoritmos que aplican series temporales.

Contributions of educational interventions in the management of Computer Vision Syndrome: a review of the literature / Aportes de las intervenciones educativas en el manejo del Síndrome Visual Informático: una revisión de literatura / Contribuições das intervenções educacionais no Manejo da Síndrome da Visão Computacional: uma revisão de literatura

Objective: To identify health education interventions that have demonstrated improvements in the visual and ocular health of computer-using workers with Computer Vision Syndrome. Method: Bibliographic review of original articles in Spanish and English, published between 2017 and June 2022 in PubMed, Scopus, MEDLINE (EBSCO), Redalyc, and Ovid databases. Results: Out of 1,695 articles, 11 complied with the protocol. Of these, 90.90% were published from 2020 to June 2022 and India had the highest number of publications (27.27%). Most of the studies were experimental or quasi-experimental (36.36%), and for the qualitative synthesis they were classified in educational interventions with technology 54.54% (n=6) and those that handled traditional education 45.45% (n=5). Conclusion: Health education interventions were shown to contribute to the improvement of visual and ocular health of computer users with Computer Vision Syndrome. It is necessary to investigate and divulge results about the topic, which contribute to the processes of promotion of visual and ocular health, as well as in the prevention of Computer Vision Syndrome in the workplace

Objetivo: Identificar intervenciones de educación para la salud que hayan demostrado me-joras en la salud visual y ocular de trabajadores usuarios de computadoras con Síndrome de Visión por Computador. Método: Revisión bibliográfica de artículos originales en español e inglés, publicados entre 2017 y junio de 2022 en las bases de datos PubMed, Scopus, MEDLINE (EBSCO), Redalyc y Ovid. Resultados: De 1.695 artículos, 11 cumplieron con el protocolo. De estos, el 90,90% se publicaron desde 2020 hasta junio de 2022 y la India tuvo el mayor número de publicaciones (27,27%). La mayoría de los estudios fueron experimentales o cuasi-experimentales (36,36%), y para la síntesis cualitativa se clasificaron en intervenciones educativas con tecnología 54,54% (n=6) y las que manejaban educación tradicional 45,45% (n=5). Conclusión: Se demostró que las intervenciones de educación en salud contribuyen a la mejora de la salud visual y ocular de los usuarios de computadora con Síndrome de Visión por Computador. Es necesario investigar y divulgar resultados sobre el tema, que contribuyan a los procesos de promoción de la salud visual y ocular, así como en la prevención del Síndrome de Visión por Computador en el ámbito laboral

Objetivo: Identificar intervenções de educação em saúde que demonstraram melhorias na saúde visual e ocular de trabalhadores usuários de computador com Síndrome de Visão de Computa-dor. Método: Revisão bibliográfica de artigos originais em espanhol e inglês, publicados entre 2017 e junho de 2022 nas bases de dados PubMed, Scopus, MEDLINE (EBSCO), Redalyc e Ovid. Resultados: Dos 1.695 artigos, 11 estavam de acordo com o protocolo. Destes, 90,90% foram publicados de 2020 a junho de 2022 e a Índia apresentou o maior número de publicações (27,27%). A maioria dos estudos foi experimental ou quase-experimental (36,36%), e para a síntese qualitativa foram classificados em intervenções educativas com tecnologia 54,54% (n=6) e aquelas que tratavam da educação tradicional 45,45% (n=5). Conclusão: As intervenções de educação em saúde demonstraram contribuir para a melhoria da saúde visual e ocular de usuários de computador com Síndrome de Visão de Computador. É preciso investigar e divulgar resulta-dos sobre o tema, que contribuam nos processos de promoção da saúde visual e ocular, bem como na prevenção da Síndrome da Visão do Computador no ambiente de trabalho

Relação entre videogames de ação, mindfulness e medo da COVID-19 em universitários / Relationship between action video games, mindfulness and fear of COVID-19 in university students / Relación entre videojuegos de acción, mindfulness y miedo al COVID-19 en estudiantes universitarios

A interação com videogame aumentou significativamente na pandemia de COVID-19. Por outro lado, um aspecto atencional que pode apresentar alterações relacionadas à quantidade de interação com videogames de ação é o mindfulness. Portanto, o objetivo deste estudo foi verificar uma possível relação entre o uso de videogames de ação (em horas semanais), o mindfulness e o medo da COVID-19. Para tanto, solicitou-se a jogadores e não jogadores de videogames de ação com idades entre 18 e 29 anos (n = 384, M = 21,6, DP = 2,6) que respondessem à Escala de Medo da COVID-19 e à Escala de Facetas do Mindfulness. Os resultados não demonstraram relação significativa entre uso de videogames de ação e mindfulness, mas apontaram que jogadores de videogame de ação apresentaram menos medo da COVID-19. Discute-se como o escapismo proporcionado pelo jogo pode explicar, em parte, uma diminuição da atenção a informações relativas à doença

Interaction with video games increased significantly in the COVID-19 pandemic. On the other hand, an attentional aspect that may show changes related to the amount of interaction with action video games is mindfulness. Therefore, the objective of this study was to verify a possible relationship between the use of action video games (in weekly hours), mindfulness and fear of COVID-19. To this end, players and non-players of action video games aged between 18 and 29 years (n = 384, M = 21.6, SD = 2.6) were asked to respond to the Covid Fear Scale and the Facets of Mindfulness. Results did not demonstrate a significant relationship between the use of action video games and mindfulness, but showed that action video game players were less afraid of COVID-19. It is discussed how the escapism provided by the game can partly explain a decrease in attention to information related to the disease

La interacción con videojuegos aumentó en la pandemia de COVID-19. Por otro lado, un aspecto atencional que puede presentar cambios relacionados con la cantidad de interacción con los videojuegos de acción es el mindfulness. Luego, el objetivo de este estudio fue verificar una relación entre uso de video-juegos de acción, mindfulness y miedo al COVID-19. Se pidió a jugadores y no jugadores de videojuegos de acción de entre 18 y 29 años (n = 384, M = 21,6, SD = 2,6) que respondieran a la Escala de Miedo al COVID y la Escala de Facetas de Mindfulness. Los resultados no demostraron una relación significativa entre uso de videojuegos de acción y mindfulness, pero señalaron que jugadores de videojuegos de acción tenían menos miedo a la COVID-19. Se discute cómo el escapismo proporcionado por el juego explicaría en parte una disminución en la atención a la información relacionada con la enfermedad

Digital repair for a patient with limited mouth opening: a case report and literature review / 口腔疾病防治

Objective@#To explore an accurate method to obtain an intraoral model of patients with specific limited mouth opening (microstomia) due to systemic scleroderma.@*Methods@#This study followed medical ethics, and informed consent has been obtained from patients. A case of Ken's Type I mandibular dentition defect scleroderma with limited mouth opening was addressed with digital technology as the leading method combined with the traditional impression method of segmental impression. Individual trays were made based on the patient's left and right mandibular dentition, and segmented molds were obtained. Simultaneously, intraoral scanning was performed to obtain the morphological data of both the soft and hard tissues of the upper and lower mandibles. After each part of the model was obtained, the mandibular model was scanned and digitally aligned to form the final denture model, and the final removable partial denture was designed and made by computer aided design/computer aided manufacturing (CAD/CAM) technology. At the same time, combined with the literature, the diagnosis and treatment of removable partial denture in patients with limited mouth opening were retrospectively analyzed.@*Results@#The denture was well retained and achieved a good repair effect. The patients expressed satisfaction with the mastication efficiency and other functions of the denture. The findings of the literature review show that the integration of digital technology with the traditional impression method, along with computer fitting, can accurately obtain the patient's oral model and facilitate successful follow-up repairs. However, when the anterior mandibular dentition of the patient is absent, the margin of error is increased in this procedure, which deserves further exploration.@*Conclusion@#Utilizing digital technology as the leading method, combined with the traditional impression method of segmental impression, for the repair of dental defects in patients with limited mouth opening, has proven to be effective. Thus, patients report a positive medical experience with high satisfaction, indicating that this approach is worthy of clinical promotion.

Challenges of computer-assisted orthognathic surgery in clinical application / 口腔疾病防治

@#After years of development, the advantages of computer-assisted orthognathic surgery have been widely recognized. However, the clinical application of this technology is challenging. Each step may generate errors from data acquisition, computer-assisted diagnosis, and computer-assisted surgical design, causing errors to be transferred from the virtual surgical plan to the operation. The accumulation and amplification of errors will affect the final surgical effect. Currently, digital devices, such as intraoral scanners, are being explored for error control, utilizing automation methods and algorithms, and implementing personalized bone positioning methods. Moreover, there are still many problems that have not been fully resolved, such as precise simulation of postoperative soft tissue, functional assessment of mandibular movement, and absorbable internal fixation materials. Fully understanding computer-assisted orthognathic surgery's limitations could provide direction for optimizing existing methods while helping clinicians avoid risks and maximize its advantages to achieve the best outcome. Many emerging and cutting-edge technologies, such as personalized titanium plates, artificial intelligence, and surgical robots, will further promote the development of this discipline. We can expect future optimization of digital orthognathic surgical technology by innovations in automation, intelligence, and personalization.

Effect of brain-computer interface based on visual, auditory and motor feedback combined with transcranial direct current stimulation on upper limb function in stroke patients / 中国康复理论与实践

ObjectiveTo explore the effect of brain-computer interface (BCI) based on visual, auditory and motor feedback combined with transcranial direct current stimulation (tDCS) on upper limb function in stroke patients. MethodsFrom March to October, 2023, 45 stroke inpatients in Xuzhou Rehabilitation Hospital and Xuzhou Central Hospital were divided into BCI group (n = 15), tDCS group (n = 15) and combined group (n = 15) randomly. All the groups received routine rehabilitation, while BCI group received BCI training, tDCS group received tDCS, while the combined group received tDCS and followed by BCI training immediately, for four weeks. They were assessed with Fugl-Meyer Assessment-Upper Extremities (FMA-UE), Action Research Arm Test (ARAT), modified Barthel Index (MBI) and delta-alpha ratio (DAR) and power ratio index (PRI) of electroencephalogram before and after treatment. ResultsThe scores of FMA-UE, ARAT and MBI increased in all the groups after treatment (|t| > 5.350, P < 0.001), and all these indexes were the best in the combined group (F > 3.366, P < 0.05); while DAR and PRI decreased in all the groups (|t| > 2.208 , P < 0.05), they were the best in the combined group (F > 5.224, P < 0.01). ConclusionBCI based on visual, auditory and motor feedback combined with tDCS can further improve the motor function of upper limbs and the activities of daily living of stroke patients.

Clinical study of polyetheretherketone resin-bonded bridge for restoring anterior missing teeth in patients with periodontitis / 口腔疾病防治

Objective@#To study the clinical effect of a polyetheretherketone (PEEK) bonding bridge on the loss of 3 internal incisors in patients with periodontitis.@*Methods@#This study was reviewed and approved by the ethics committee, and informed consent was obtained from the patients. Thirty-eight patients with periodontitis and 3 missing central or lateral teeth were selected to undergo restoration with a PEEK bonding bridge and then returned to the hospital 3, 6, 12, and 24 months after the restoration was completed. The survival rate of the restorations was assessed by the modified USPHS/Ryge criteria. The plaque index, gingival index, periodontal probing depth and attachment loss of the abutments were recorded, and the changes in periodontal tissues after restoration were observed and compared.@*Results@#Over 24 months of clinical follow-up observation of 38 patients, only 1 patient underwent secondary bonding after partial debonding (evaluated as grade B), while bonding was successful in the other 37 cases (evaluated as grade A). The plaque index, gingival index and periodontal probing depth were significantly lower after restoration than before (P<0.05). There was no significant change in attachment loss between before and after restoration (P>0.05).@*Conclusion@#For periodontitis patients missing 3 internal incisors, short-term PEEK bonding bridge repair has good clinical efficacy.

Chest CT Imaging Features of Indeterminate Pulmonary Nodules and Outcomes in Patients with High-grade Soft Tissue Sarcoma: A Single-center Retrospective Study / 肿瘤防治研究

Objective To explore the imaging features, clinical outcome, and prognosis of indeterminate pulmonary nodules (IPN) in patients with high-grade soft tissue sarcoma. Methods A retrospective study of 82 patients with high-grade soft tissue sarcoma who have IPNs. The clinical characteristics, imaging features of IPN, and survival of patients were analyzed with statistical software. Results The IPN size of 82 patients was 6.453±0.864 mm. IPN diameter, shape, density, and nodule discovery interval may be CT imaging features related to malignancy tendency. Age (HR=1.047, 95%CI: 1.007-1.088) and interval between each nodule discovery (HR=3.194, 95%CI: 1.052-9.694) are independent factors that affect the survival of patients with malignant IPN. Conclusion The imaging features of chest CT may provide important guidance for determining the nature and survival prognosis of benign and malignant nodules.

Performance analysis of pretrained convolutional neural network models for ophthalmological disease classification / Análise de desempenho de modelos de rede neural convolucional pré-treinados para classificação de doenças oftalmológicas

ABSTRACT Purpose: This study aimed to evaluate the classification performance of pretrained convolutional neural network models or architectures using fundus image dataset containing eight disease labels. Methods: A publicly available ocular disease intelligent recognition database has been used for the diagnosis of eight diseases. This ocular disease intelligent recognition database has a total of 10,000 fundus images from both eyes of 5,000 patients for the following eight diseases: healthy, diabetic retinopathy, glaucoma, cataract, age-related macular degeneration, hypertension, myopia, and others. Ocular disease classification performances were investigated by constructing three pretrained convolutional neural network architectures including VGG16, Inceptionv3, and ResNet50 models with adaptive moment optimizer. These models were implemented in Google Colab, which made the task straight-forward without spending hours installing the environment and supporting libraries. To evaluate the effectiveness of the models, the dataset was divided into 70%, 10%, and 20% for training, validation, and testing, respectively. For each classification, the training images were augmented to 10,000 fundus images. Results: ResNet50 achieved an accuracy of 97.1%; sensitivity, 78.5%; specificity, 98.5%; and precision, 79.7%, and had the best area under the curve and final score to classify cataract (area under the curve = 0.964, final score = 0.903). By contrast, VGG16 achieved an accuracy of 96.2%; sensitivity, 56.9%; specificity, 99.2%; precision, 84.1%; area under the curve, 0.949; and final score, 0.857. Conclusions: These results demonstrate the ability of the pretrained convolutional neural network architectures to identify ophthalmological diseases from fundus images. ResNet50 can be a good architecture to solve problems in disease detection and classification of glaucoma, cataract, hypertension, and myopia; Inceptionv3 for age-related macular degeneration, and other disease; and VGG16 for normal and diabetic retinopathy.

RESUMO Objetivo: Avaliar o desempenho de classificação de modelos ou arquiteturas de rede neural convolucional pré--treinadas usando um conjunto de dados de imagem de fundo de olho contendo oito rótulos de doenças diferentes. Métodos: Neste artigo, o conjunto de dados de reconhecimento inteligente de doenças oculares publicamente disponível foi usado para o diagnóstico de oito rótulos de doenças diferentes. O banco de dados de reconhecimento inteligente de doenças oculares tem um total de 10.000 imagens de fundo de olho de ambos os olhos de 5.000 pacientes para oito categorias que contêm rótulos saudáveis, retinopatia diabética, glaucoma, catarata, degeneração macular relacionada à idade, hipertensão, miopia, outros. Investigamos o desempenho da classificação de doenças oculares construindo três arquiteturas de rede neural convolucional pré-treinadas diferentes, incluindo os modelos VGG16, Inceptionv3 e ResNet50 com otimizador de Momento Adaptativo. Esses modelos foram implementados no Google Colab o que facilitou a tarefa sem gastar horas instalando o ambiente e suportando bibliotecas. Para avaliar a eficácia dos modelos, o conjunto de dados é dividido em 70% para treinamento, 10% para validação e os 20% restantes utilizados para teste. As imagens de treinamento foram expandidas para 10.000 imagens de fundo de olho para cada tal. Resultados: Observou-se que o modelo ResNet50 alcançou acurácia de 97,1%, sensibilidade de 78,5%, especificidade de 98,5% e precisão de 79,7% e teve a melhor área sob a curva e pontuação final para classificar a categoria da catarata (área sob a curva=0,964, final=0,903). Em contraste, o modelo VGG16 alcançou uma precisão de 96,2%, sensibilidade de 56,9%, especificidade de 99,2% e precisão de 84,1%, área sob a curva 0,949 e pontuação final de 0,857. Conclusão: Esses resultados demonstram a capacidade das arquiteturas de rede neural convolucional pré-treinadas em identificar doenças oftalmológicas a partir de imagens de fundo de olho. ResNet50 pode ser uma boa solução para resolver problemas na detecção e classificação de doenças como glaucoma, catarata, hipertensão e miopia; Inceptionv3 para degeneração macular relacionada à idade e outras doenças; e VGG16 para retinopatia normal e diabética.

Effect of the COVID-19 pandemic on cataract surgery by residents who had routine surgical simulator training during residency

ABSTRACT Purpose: To assess the effect of the coronavirus disease 2019 (COVID-19) pandemic on cataract surgery by residents who had mandatory surgical simulator training during residency. Methods: In this retrospective, observational analytical study, the total number of cataract surgeries and surgical complications by all senior residents of 2019 (2019 class; prepandemic) and 2020 (2020 class; affected by the reduced number of elective surgeries due to the COVID-19 pandemic) were collected and compared. All residents had routine mandatory cataract surgery training on a virtual surgical simulator during residency. The total score obtained by these residents on cataract challenges of the surgical simulator was also evaluated. Results: The 2020 and 2019 classes performed 1275 and 2561 cataract surgeries, respectively. This revealed a reduction of 50.2% in the total number of procedures performed by the 2020 class because of the pandemic. The incidence of surgical complications was not statistically different between the two groups (4.2% in the 2019 class and 4.9% in the 2020 class; p=0.314). Both groups also did not differ in their mean scores on the simulator's cataract challenges (p<0.696). Conclusion: Despite the reduction of 50.2% in the total number of cataract surgeries performed by senior residents of 2020 during the COVID-19 pandemic, the incidence of surgical complications did not increase. This suggests that surgical simulator training during residency mitigated the negative effects of the reduced surgical volume during the pandemic.

Digital analysis of unilateral ptosis repair: external levator advancement vs. Müller's muscle conjunctival resection

ABSTRACT Purpose: Evaluation of lid contour and marginal peak point changes to compare outcomes of external levator advancement and Müller's muscle conjunctival resection surgery in unilateral ptosis. Methods: We reviewed the charts of unilateral ptosis patients who underwent external levator advancement or Müller's muscle conjunctival resection. Eyelid contour analysis was conducted on preoperative and 6-month postoperative digital images. This was performed with the multiple margin reflex distances technique, measuring the vertical distance from a line intersecting the center of the pupil to the eyelid margin at 10 positions at 2 mm intervals. The marginal peak point changes were analyzed digitally using the coordinates of the peak point according to the pupil center. Each position's mean distance was compared preoperatively, postoperatively, and with the fellow eyelid. Results: Sixteen patients underwent external levator advancement and 16 patients had Müller's muscle conjunctival resection. The mean margin reflex distance was improved by both techniques (1.46 vs. 2.43 mm and 1.12 vs. 2.25 mm, p=0.008 and p=0.0001 respectively) and approached that of the fellow eyelid (2.43 vs. 2.88 and 2.25 vs. 2.58 mm, p=0.23 and p=0.19, respectively). However, statistically significant lid margin elevation was limited to between the N6 and T6 points in the external levator advancement group. Whereas, significant elevation was achieved along the whole lid margin in the Müller's muscle conjunctival resection group. The marginal peak point was shifted slightly laterally in the external levator advancement group (p=0.11). Conclusions: Both techniques provide effective lid elevation, however, the external levator advancement's effect lessens toward the canthi while Müller's muscle conjunctival resection provides more uniform elevation across the lid margin. The margin reflex distance alone is not sufficient to reflect contour changes.

Artificial intelligence to predict bed bath time in Intensive Care Units / Inteligencia artificial para predecir la hora del baño en cama en Unidades de Cuidados Intensivos / Inteligência artificial para predição do tempo de banho no leito em Unidades de Terapia Intensiva

ABSTRACT Objectives: to assess the predictive performance of different artificial intelligence algorithms to estimate bed bath execution time in critically ill patients. Methods: a methodological study, which used artificial intelligence algorithms to predict bed bath time in critically ill patients. The results of multiple regression models, multilayer perceptron neural networks and radial basis function, decision tree and random forest were analyzed. Results: among the models assessed, the neural network model with a radial basis function, containing 13 neurons in the hidden layer, presented the best predictive performance to estimate the bed bath execution time. In data validation, the squared correlation between the predicted values and the original values was 62.3%. Conclusions: the neural network model with radial basis function showed better predictive performance to estimate bed bath execution time in critically ill patients.

RESUMEN Objetivos: evaluar el rendimiento predictivo de diferentes algoritmos de inteligencia artificial para estimar el tiempo de ejecución del baño en cama en pacientes críticos. Métodos: estudio metodológico, que utilizó algoritmos de inteligencia artificial para predecir el tiempo de baño en cama en pacientes críticos. Se analizaron los resultados de modelos de regresión múltiple, redes neuronales perceptrón multicapa y función de base radial, árbol de decisión y random forest. Resultados: entre los modelos evaluados, el modelo de red neuronal con función de base radial, que contiene 13 neuronas en la capa oculta, presentó el mejor desempeño predictivo para estimar el tiempo de ejecución del baño en cama. En la validación de datos, la correlación al cuadrado entre los valores predichos y los valores originales fue del 62,3%. Conclusiones: el modelo de red neuronal con función de base radial mostró mejor rendimiento predictivo para estimar el tiempo de ejecución del baño en cama en pacientes críticos.

RESUMO Objetivos: avaliar a performance preditiva de diferentes algoritmos de inteligência artificial para estimar o tempo de execução do banho no leito em pacientes críticos. Métodos: estudo metodológico, que utilizou algoritmos de inteligência artificial para predizer o tempo de banho no leito em pacientes críticos. Foram analisados os resultados dos modelos de regressão múltipla, redes neurais perceptron multicamadas e função de base radial, árvore de decisão e random forest. Resultados: entre os modelos avaliados, o modelo de rede neural com função de base radial, contendo 13 neurônios na camada oculta, apresentou melhor performance preditiva para estimar o tempo de execução do banho no leito. Na validação dos dados, o quadrado da correlação entre os valores preditos e os valores originais foi de 62,3%. Conclusões: o modelo de rede neural com função de base radial apresentou melhor performance preditiva para estimar o tempo de execução do banho no leito em pacientes críticos.

Diagnostic value of a computer-assisted diagnosis system for the ultrasound features in thyroid nodules

ABSTRACT Objective: To explore the diagnostic value of the TUIAS (SW_TH01/II) computer-aided diagnosis (CAD) software system for the ultrasound Thyroid Imaging Reporting and Data System (TI-RADS) features in thyroid nodules. Materials and methods: This retrospective study enrolled patients with thyroid nodules in Shanghai East Hospital between January 2017 and October 2021. The novel CAD software (SW_TH01/II) and three sonographers performed a qualitative analysis of the ultrasound TI-RADS features in aspect ratio, margin irregularity, margin smoothness, calcification, and echogenicity of the thyroid nodules. Results: A total of 225 patients were enrolled. The accuracy, sensitivity, and specificity of the CAD software in "aspect ratio" were 95.6%, 96.2%, and 95.4%, in "margin irregularity" were 90.7%, 90.5%, and 90.9%, in "margin smoothness" were 85.8%, 88.5%, and 83.0%, in "calcification" were 83.6%, 81.7%, and 82.0%, in "homogeneity" were 88.9%, 90.6%, and 82.2%, in "major echo" were 85.3%, 88.0%, and 85.4%, and in "contains very hypoechoic echo" were 92.0%, 90.0%, and 92.4%. The analysis time of the CAD software was significantly shorter than for the sonographers (2.7 ± 1.6 vs. 29.7 ± 12.7 s, P < 0.001). Conclusion: The CAD system achieved high accuracy in describing thyroid nodule features. It might assist in clinical thyroid nodule analysis.

Cross-cultural validation into Portuguese of a questionnaire to assess computer vision syndrome in workers exposed to digital devices / Validação intercultural em português de um questionário para avaliar a síndrome visual do computador em trabalhadores expostos a dispositivos digitais

ABSTRACT Purpose: As digital devices are increasingly used at work, valid and reliable tools are needed to assess their effect on visual health. This study aimed to translate, cross-culturally adapt, and validate the Computer Vision Syndrome Questionnaire (CVS-Q©) into Portuguese. Methods: A 5-phase process was followed: direct translation, synthesis of translation, back-translation, consolidation by an expert committee, and pretest. To run the pretest, a cross-sectional pilot study was conducted with 26 participants who completed the prefinal Portuguese version of the CVS-Q© and were asked about difficulties, comprehensibility, and suggestions to improve the questionnaire. To evaluate the reliability and validity of the Portuguese version of the CVS-Q©, a cross-sectional validation study was performed in a different sample (280 workers). Results: In the pretest, 96.2% had no difficulty in completing it, and 84.0% valued it as clear and understandable. CVS-Q© in Portuguese (Questionário da Síndrome Visual do Computador, CVS-Q PT©) was then obtained. Validation revealed the scale's good internal consistency (Cronbach's alpha=0.793), good temporal stability (intraclass correlation coefficient=0.847; 95% CI 0.764-0.902, kappa=0.839), adequate sensitivity and specificity (78.5% and 70.7%, respectively), good discriminant capacity (area under the curve=0.832; 95% CI 0.784-0.879), and adequate convergent validity with the ocular surface disease index (Spearman correlation coefficient=0.728, p<0.001). The factor analysis provided a single factor accounting for 37.7% of the explained common variance. A worker who scored ≥7 points would have computer vision syndrome. Conclusions: CVS-Q PT© can be considered an intuitive and easy-to-understand tool with good psychometric properties to measure computer vision syndrome in Portuguese workers exposed to digital devices. This questionnaire will assist in making decisions on preventive measures, interventions, and treatment and comparing exposed populations in different Portuguese-speaking countries.

RESUMO Objetivos: À medida que a utilização de equipamentos digitais no emprego aumenta, a avaliação do seu efeito na saúde visual necessita de ferramentas válidas e robustas. Este estudo teve como objetivo traduzir, adaptar culturalmente e validar para português o Questionário da Síndrome Visual do Computador (CVS-Q©). Métodos: O procedimento foi realizado em 5 fases: tradução direta, síntese da tradução, tradução inversa, consolidação por um painel de especialistas, e pré-teste. Para fazer o pré-teste foi realizado um estudo piloto transversal aplicado a uma amostra de 26 participantes que completaram a versão pré-final da versão portuguesa do CVS-Q©, questionando por dificuldades, compreensão e sugestões de melhoria do questionário. Para avaliar a confiança e validade da versão portuguesa do CVS-Q© foi realizado um estudo transversal de validação em uma amostra diferente (280 funcionários). Resultados: No préteste, 96.2% dos participantes não apresentaram dificuldades no preenchimento do questionário, enquanto 84.0% indicaram que era claro e compreensível. Obteve-se, então, o CVS-Q© em português (Questionário da Síndrome Visual do Computador, CVS-Q PT©). A sua validação revelou uma boa consistência interna da sua escala (Cronbach's alpha=0.793), boa estabilidade tem poral (coeficiente de correlação interclasse=0.847; 95% CI 0.764-0.902, kappa=0.839), sensibilidades e especificidades adequadas (78.5% e 70.7%, respetivamente), boa capacidade de discriminação (área abaixo da curva=0.832; 95% CI 0.784-0.879), e uma adequada validade da convergência com o índice de doença da superfície ocular (ocular surface disease index - OSDI; coeficiente de correlação de Spearman=0.728, p<0.001). A análise fatorial revelou um único fator responsável por explicar a variância comum em 37.7%. Um funcionário com uma pontuação ≥7 pontos sofria de síndrome visual do computador. Conclusão: O CVS-Q PT© pode ser considerada uma ferramenta intuitiva, de fácil interpretação e com boas pro priedades psicométricas para avaliar a síndrome visual do computador em funcionários portugueses expostos a ecrãs digitais. Este questionário facilitará as decisões sobre medidas preventivas, intervenções e tratamento, e a comparação entre as populações expostas em diferentes países de língua portuguesa.

Microtensile bond strength of resin cements to 3-D printed and milled temporary restorative resins / Resistencia de unión en microtracción de cementos resinosos a resinas para provisionales impresas y fresadas

Abstract To evaluate the microtensile bond strength (µTBS) of two resin cements to 3D printed and milled CAD/CAM resins used for provisional fixed partial dentures. Blocks (5 x 5 x 5 mm) of three 3D-printed resins (Cosmos3DTemp / Yller; Resilab3D Temp / Wilcos and SmartPrint BioTemp, / MMTech) were printed (Photon, Anycubic Technology Co.). A milled material (VitaCAD-Temp, VITA) was used as control. Half the specimens were sandblasted and the rest were untreated. Two blocks were bonded with the corresponding resin cement: PanaviaV5 (Kuraray Noritake) and RelyX Ultimate (3M Oral Care). After 24 hours, the bonded blocks were sectioned into 1 x 1 mm side sticks. Half the beams were tested for µTBS and the other half was thermocycled (5000 cycles, 30s dwell-time, 5s transfer time) before µTBS testing. A four way Generalized Linear Model (material*sandblasting*cement*aging) analysis was applied. VITA exhibited the lowest µTBS, regardless of the cement, sandblasting and thermocycling. Sandblasting significantly improved the µTBS of VIT, especially after aging, but did not improve the µTBS of 3D printed resins. Sandblasting was not beneficial for 3D printed resins, although is crucial for adhesive cementation of milled temporary resins. Airborne particle abrasion affects the integrity of 3D-printed resins, without producing a benefit on the microtensile bond strength of these materials. However, sandblasting is crucial to achieve a high bond strength on milled temporary resins.

Resumen Evaluar la resistencia adhesiva en microtracción (µTBS) de dos cementos resinosos a resinas CAD/CAM impresas y fresadas indicadas para restauraciones provisionales. Bloques (5 x 5 x 5mm) de tres resinas impresas (Cosmos3DTemp / Yller; Resilab3D Temp / Wilcos and SmartPrint BioTemp, / MMTech) y una resina fresada (VitaCAD-Temp, VITA) fueron fabricados. La mitad de los especímenes fueron arenados y el resto no recibió tratamiento mecánico. Dos bloques con condiciones de tratamiento iguales fueron cementados con cemento resinoso (PanaviaV5 / Kuraray Noritake y RelyX Ultimate / 3M Oral Care). Después de 24 horas los bloques fueron seccionados en palitos de 1 mm² de área. En la mitad de los especímenes se midió la TBS inmediatamente y el resto fue termociclado (5000 ciclos, 30s remojo, 5s transferencia) antes de la prueba de TBS. Se aplica un análisis estadístico por Modelo Linear General con 4 factores (material*arenado*cemento*termociclado). La resina VITA presentó la menor µTBS, independientemente del cemento usado, el arenado y el termociclado. Sin embargo, el arenado aumentó la µTBS de VIT, especialmente después del termociclado. Por otro lado, el arenado no resultó en un aumento significativo de la µTBS de las resinas impresas. El arenado no fue beneficiosos para las resinas impresas, aunque es un paso crucial para la cementación adhesive de las resinas fresadas. El arenado afecta la integridad de las capas de las resinas impresas, sin generar un beneficio en la TBS.

Utilidad de la tecnología CAD/CAM en la fabricación de prótesis dentales

La tecnología CAD/CAM es una forma innovadora relacionada con la implementación de técnicas digitales para mejorar las restauraciones prostéticas en un paciente, entre ellas, las destinadas a la estética dental. El presente estudio tiene el objetivo de describir la utilidad de la tecnología CAD/CAM en la fabricación de prótesis dentales. Para ello se realizó una revisión de la literatura médica disponible en las bases de datos PubMed/Medline, Scopus y SciELO, mediante fórmulas de búsqueda avanzada; se seleccionaron artículos en idioma español e inglés. En la actualidad, con esta tecnología se ha logrado combinar estética, resistencia y precisión en la restauración directa, además de garantizarse una mayor duración y años de funcionalidad para cada una de las prótesis, coronas e implantes. La calidad de vida y satisfacción referidas por los pacientes portadores de piezas producidas con esta tecnología, es superior a las manifestadas por aquellos tratados con piezas de fabricación tradicional. El uso de técnicas de inteligencia artificial y biomateriales representará un cambio cualitativo y cuantitativo en el uso de los sistemas CAD/CAM.

CAD/CAM technology is an innovative way related to the implementation of digital techniques to improve prosthetic restorations in a patient, including those intended for dental aesthetics. The objective of this study is to describe the usefulness of CAD/CAM technology in the dental prostheses manufacture. A review of the medical literature available in the PubMed/Medline, Scopus and SciELO databases was carried out, using advanced search formulas; Articles in Spanish and English were selected. Currently, with this technology it has been possible to combine aesthetics, resistance and precision in direct restoration, in addition to guaranteeing greater duration and years of functionality for each of the prostheses, crowns and implants. The quality of life and satisfaction reported by patients wearing parts produced with this technology is higher than those reported by those treated with traditionally manufactured parts. The use of artificial intelligence and biomaterials techniques will represent a qualitative and quantitative change in the use of CAD/CAM systems.

Contribución de la Facultad de Ciencias Médicas de Cienfuegos a la utilización de la tecnología computacional en la docencia médica superior. Reseña del empleo de simulaciones clínicas en el periodo 1990-2007

El artículo ha tenido como objetivo reseñar, de forma cronológica, los acontecimientos más relevantes relacionados con la utilización de simulaciones computarizadas en el proceso docente, en el contexto particular de la Facultad de Ciencias Médicas de Cienfuegos durante el periodo 1990-2007. Entre los acontecimientos identificados se encuentran los siguientes: la elaboración e introducción de simulaciones en la asignatura Medicina Interna correspondiente al tercer año de la carrera (curso 1990-1991); la introducción de la simulación, con fines evaluativos, en el internado de Medicina Interna (1997-2000); el desarrollo de un nuevo software para la elaboración de simulaciones (2002); y la extensión del uso de simulaciones a los seminarios de actualización terapéutica correspondientes al internado de Pediatría (2007). Se evidenció que la contribución realizada por la institución docente al tema abordado, no solo consistió en la elaboración de ejercicios de simulación y su introducción en la práctica formativa, sino también en la ejecución de acciones dirigidas a la capacitación de profesores, el perfeccionamiento de las herramientas utilizadas (programas, metodologías) y la socialización de las experiencias; todo lo cual se acompañó de una amplia actividad investigativa que mereció reconocimientos a diferentes niveles.

The objective of this article is to review chronologically, the most relevant events related to the use of computerized simulations in the teaching process, in the particular context of the Cienfuegos Medical Sciences Faculty from 1990 to 2007. Among the identified events are: the development and introduction of simulations in the Internal Medicine subject corresponding to the third year of the degree (course 1990-1991); the introduction of simulation, for evaluation purposes, in the Internal Medicine internship (1997-2000); the development of a new software for the elaboration of simulations (2002); and the extension of the use of simulations to therapeutic update seminars corresponding to the Pediatrics internship (2007). It was evidenced that the contribution made by the educational institution to the topic addressed, not only consisted in the preparation of simulation exercises and their introduction in the training practice, but also in the teacher training, the improvement of the tools used (programs, methodologies) and the sharing of experiences; all of which was accompanied by extensive research activity that deserved recognition at different levels.

Habilidades digitales y tecnoestrés en docentes universitarios mayores de 60 años / Digital skills and technostress in university professors aged 60 years and over i: en

Introducción: Las limitaciones en el uso de las tecnologías en los docentes de la educación superior conducen al aislamiento social y la exclusión e impiden demostrar las competencias profesionales. Objetivo: Describir las habilidades digitales en docentes universitarios adultos mayores y su relación con el tecnoestrés. Métodos: Se realizó un estudio cualitativo, de mayo a noviembre del 2022, de 19 docentes en las edades de 60 y más años de la Universidad Nacional San Luis Gonzaga de Ica, en Perú. Para ello, se desarrolló un taller de capacitación y se evaluó la comprensión de 6 herramientas teórico-prácticas de la categoría docente en el proceso de enseñanza-aprendizaje a través de la ejecución de actividades (cuestionario, chat y tareas) en la plataforma virtual Moodle. Asimismo, se orientó marcar los criterios de identificación de la investigación formativa y, para la calificación, se establecieron 3 intervalos de puntuación. Se aplicó una encuesta fundamentada en la demostración de las habilidades digitales y el estado emocional en relación con la tecnología. Resultados: El valor promedio de la calificación fue 14,73±0,42 y se obtuvieron los siguientes porcentajes para cada intervalo de puntuación: I) 57,9; II) 31,6 y III) 10,5. Igualmente, 73,7 % requirió asistencia técnica para interactuar con la enseñanza virtual, mientras que 84,2 % se agobió con el uso de la tecnología. Existió correlación (p=0,0256) entre la puntuación asignada en las habilidades digitales y el tecnoestrés. Conclusiones: Los docentes universitarios mayores de 60 años mostraron deficiencias en las habilidades digitales, lo cual condujo a la aparición de tecnoestrés.

Introduction: Limitations in the use of technologies in higher education professors lead to social isolation and exclusion and prevent the demonstration of professional skills. Objective: Describe digital skills in elderly university professors and their relationship with technostress. Methods: A qualitative study was carried out, from May to November, 2022, of 19 professors aged 60 years and over from San Luis Gonzaga National University in Ica, Peru. To this purpose, a training workshop was developed and the understanding of 6 theoretical-practical tools of teaching category in the teaching learning process was evaluated through the implementation of activities (questionnaire, chat and tasks) on the online platform Moodle. Likewise, the aim was to mark the identification criteria of training research and, for grading, 3 scoring intervals were established. A survey was applied based on the demonstration of digital skills and the emotional state concerning technology. Results: The mean value of score was 14.73±0.42 and the following percentages were obtained for each score interval: I) 57.9; II) 31.6 and III) 10.5. Also, 73.7% required technical assistance to interact with virtual teaching, while 84.2% were overwhelmed with the use of technology. There was a correlation (p=0.0256) between the score assigned in digital skills and technostress. Conclusions: University professors over 60 years of age showed deficiencies in the digital skills, which led to the appearance of technostress.

Normatização dos escores da escala eHealth Literacy Scale para avaliação do letramento digital em saúde / Standardization of eHealth Literacy Scale scores for assessing digital health literacy / Estandarización de las puntuaciones de la escala eHealth Literacy Scale para evaluar la alfabetización digital en salud

Objetivo: analisar os dados de normatização dos escores da versão brasileira do instrumento eHealth Literacy Scale (eHeals) para avaliação do letramento digital em saúde. Método: estudo transversal com 502 adultos brasileiros, realizado em 2019. Dados coletados pelo instrumento eHeals e questionário sociodemográfico. Foram aplicadas árvores de decisão e análise discriminante. Estudo aprovado pelo Comite de Ética em Pesquisa. Resultados: a análise discriminante determinou as faixas de classificação do eHeals a partir da distribuição dos escores. A árvore de decisão indicou que a escolaridade afetou de forma relevante os resultados da escala. Os indivíduos com escolaridade até o ensino fundamental II incompleto: baixo (até 10), médio (11 a 25), alto (27 a 40), e escolaridade acima: baixo (até 25), médio (25 a 32) e alto LDS (33 a 40). Conclusão: a classificação dos níveis de letramento digital em saúde de adultos pelo eHeals deve ser controlada pelos níveis de escolaridade dos participantes.

Objective: to analyze the normative data of the scores of the Brazilian version of the eHealth Literacy Scale (eHeals) instrument for assessing digital health literacy. Method: cross-sectional study with 502 Brazilian adults in 2019. Data collected using the eHeals instrument and sociodemographic questionnaire. Decision trees and discriminant analysis were applied. Study approved by the Research Ethics Committee. Results: Discriminant analysis determined the eHeals classification ranges based on the distribution of scores. The decision tree indicated that education significantly affected the scale results. Thus, individuals with incomplete elementary school education up to II: low (up to 10), medium (11 to 25), high (27 to 40), and higher education: low (up to 25), medium (25 to 32) and high LDS (33 to 40). Conclusion: the classification of digital health literacy levels using eHeals in adults should be controlled by the participants' education levels.

Objetivo: analizar los datos de estandarización de las puntuaciones de la versión brasileña del instrumento eHealth Literacy Scale (eHeals) para evaluar la alfabetización digital en salud. Método: estudio transversal con 502 adultos brasileños que tuvo lugar en 2019. La recolección de datos se hizo mediante el instrumento eHeals y un cuestionario sociodemográfico. Se aplicaron árboles de decisión y análisis discriminante. El Comité de Ética en Investigación aprobó el estudio. Resultados: El análisis discriminante determinó los rangos de clasificación de eHeals con base en la distribución de puntuaciones. El árbol de decisión indicó que la educación afectó significativamente los resultados de la escala. Individuos con educación primaria incompleta: baja (hasta 10), media (11 a 25), alta (27 a 40), y educación superior a esa mencionada: baja (hasta 25), media (25 a 32) y alto LDS (33 a 40). Conclusión: la clasificación de los niveles de alfabetización en salud digital en adultos con eHeals debe ser controlada por los niveles de educación de los participantes.

Competencias digitales de estudiantes de la maestría en Cuidados Paliativos y Manejo del Dolor

Objetivo: Determinar las competencias digitales de los estudiantes de la maestría en Cuidados Paliativos y Manejo del Dolor de la Facultad de Medicina de la Universidad Nacional Mayor de San Marcos en el año 2022. Materiales y métodos: Investigación de diseño no experimental, descriptivo y de corte transversal. La población de estudio estuvo conformada por los alumnos de la maestría en Cuidados Paliativos y Manejo de Dolor matriculados en el año 2022. Se empleó una muestra no probabilística. Los datos se recolectaron a través de la encuesta Cuestionario de competencias digitales en educación superior (CDES), compuesta por 46 indicadores distribuidos en cinco factores, que tiene una fiabilidad de 0,96 según alfa de Cronbach. Se respetó la confidencialidad de los datos y la autonomía en las decisiones de los participantes. Resultados: Se trabajó con una muestra final de 59 alumnos. La edad promedio fue 38,03 años y el 76,3 % fueron mujeres. Todos los estudiantes contaban con una computadora personal y acceso a internet. El análisis descriptivo determinó un predominio de la valoración "muy importante": 49,2 % para el factor "ciudadanía digital"; 47,5 % para el factor "comunicación y colaboración"; 45,8 % para "creatividad e innovación" y "acceso y uso de la información"; y 44,1 % para el factor "alfabetización digital". Según el análisis global de competencias digitales, 49,2 % manifestó una valoración "muy importante" y 42,4 %, "importante"; no hubo resultados para la denominación "nada importante". Conclusiones: Todos los estudiantes disponen de una computadora personal y cuentan con acceso a internet, lo que ratifica el creciente interés por incluir los aspectos relacionados con la competencia digital en la educación universitaria. El factor "alfabetización tecnológica" presentó menor valoración, mientras que el factor "ciudadanía digital" tuvo mayor valoración. El 91,6 % de estudiantes valora la competencia digital entre importante y muy importante, lo que podría considerarse como muy favorable.

Objective: To determine the digital skills among students of the master's program in Palliative Care and Pain Management at Universidad Nacional Mayor de San Marcos School of Medicine in 2022. Materials and methods: A non-experimental, descriptive and cross-sectional research. The study population was comprised of students of the master's program in Palliative Care and Pain Management enrolled in the year 2022. A non-probability sample was used. Data were collected through the survey "Digital Skills in Higher Education Questionnaire" (CDES), consisting of 46 indicators distributed in five factors with a reliability of 0.96 according to Cronbach's alpha. Data confidentiality and participants' autonomy were respected. Results: The final sample was made up of 59 students, the average age was 38.03 years and 76.3 % were women. All students had a personal computer and Internet access. The descriptive analysis showed that the "very important" rating prevailed: 49.2 % for the "digital citizenship" factor, 47.5 % for the "communication and collaboration" factor, 45.8 % for the "creativity and innovation" and the "access and use of information" factors, and 44.1 % for the "digital literacy" factor. According to the digital skills global analysis, 49.2 % and 42.4 % chose the "very important" and "important" ratings, respectively. There were no results for the "not at all important" rating. Conclusions: All students had a personal computer and Internet access, which confirms the growing interest in including aspects related to digital skills in university education. The "digital literacy" and the "digital citizenship" factors had a lower and higher rating, respectively, compared to the other factors. A total of 91.6 % of the students considered that digital skills are important and very important, which could be considered as highly favorable.