Serial values of hematologic variables and deep venous thrombosis: Red cell distribution width is associated with deep venous thrombosis

Abstract Introduction As 30 to 50% of deep venous thrombosis (DVT) cases remain idiopathic, an increased focus on hematologic variables may therefore reveal novel correlates of DVT. Very few studies have investigated the association of hematological parameters with DVT and the causal relationship between them is still to be elucidated. Therefore, we aimed to investigate the association between serial values of hematologic variables and DVT. Methods Complete blood count parameters were serially measured at baseline and then at approximately 3-month intervals for 12 months in 152 adults with the first episode of DVT and 152 age- and sex-matched controls. The odds ratio (OR) with the 95% confidence interval (95%CI) was calculated as a measure of association between hematological parameters and DVT. Results The red cell distribution width (RDW) was the only hematologic variable which showed an independent and consistent association with DVT at all time points (multivariable-adjusted OR [95%CI] 3.38 [1.28 - 8.91] at baseline, 2.24 [0.85 - 5.92] at 3 months and 2.12 [0.81 - 5.55] at 12 months for RDW > 14.0%). This association was higher for provoked DVT than unprovoked DVT and for DVT plus pulmonary embolism than DVT alone. No significant correlation was found between the high RDW and classical thrombotic risk factors, except malignancy. Conclusions We demonstrated an independent and consistent association of the high RDW with the first episode of DVT in adult patients. The study was probably underpowered to evaluate the association between the high RDW and recurrent DVT. Further large studies with long follow-up are needed to confirm this association.

Research progress on dental materials for preventing root caries / 口腔疾病防治

@#The high incidence and untreated rate of root caries, a common and frequently occurring oral disease with challenging treatment in elderly individuals, is the main cause of tooth loss among elderly people, as rapid development results in pulpitis and periapical periodontitis or residual crown and root, which has been regarded as one of the common chronic oral diseases seriously affecting the quality of life of elderly people. Thus, early intervention and prevention are important. Traditional dental materials for preventing root caries have been widely used in clinical practice; however, they have the disadvantages of tooth coloring, remineralization and low sterilization efficiency. A series of new dental materials for preventing root caries have gradually become a research hotspot recently, which have the advantages of promoting the mineralization of deep dental tissue, prolonging the action time and enhancing adhesion. Future caries prevention materials should be designed according to the characteristics of root surface caries and the application population and should be developed toward simplicity, high efficiency and low toxicity. This review describes current research regarding anti-caries prevention material application, serving as a theoretical underpinning for the research of root caries prevention materials, which is important for both promotion in the effective prevention of root caries and improvement in the status of oral health and the quality of life among old people.

MobileNetV3 network-based diagnosis of caries and periapical periodontitis from periapical films / 口腔疾病防治

Objective@#To research the effectiveness of deep learning techniques in intelligently diagnosing dental caries and periapical periodontitis and to explore the preliminary application value of deep learning in the diagnosis of oral diseases@*Methods@#A dataset containing 2 298 periapical films, including healthy teeth, dental caries, and periapical periodontitis, was used for the study. The dataset was randomly divided into 1 573 training images, 233 validation images, and 492 test images. By comparing various neural network models, the MobileNetV3 network model with better performance was selected for dental disease diagnosis, and the model was optimized by tuning the network hyperparameters. The accuracy, precision, recall, and F1 score were used to evaluate the model's ability to recognize dental caries and periapical periodontitis. Class activation map was used to visualization analyze the performance of the network model@*Results@#The algorithm achieved a relatively ideal intelligent diagnostic effect with precision, recall, and accuracy of 99.42%, 99.73%, and 99.60%, respectively, and the F1 score was 99.57% for classifying healthy teeth, dental caries, and periapical periodontitis. The visualization of the class activation maps also showed that the network model can accurately extract features of dental diseases.@*Conclusion@#The tooth lesion detection algorithm based on the MobileNetV3 network model can eliminate interference from image quality and human factors and has high diagnostic accuracy, which can meet the needs of dental medicine teaching and clinical applications.

Application status of artificial intelligence techniques in retinoblastoma / 国际眼科杂志(Guoji Yanke Zazhi)

Retinoblastoma is a kind of malignant eye tumor commonly seen in children, which is one of the main causes threatening children's vision and life. The diagnosis and evaluation of retinoblastoma has always been a hot topic in clinic. In the past few years, the application of artificial intelligence(AI)technology has made significant progress in the medical field, providing new opportunities and challenges for the diagnosis and treatment of retinoblastoma, for example, the use of AI algorithms to analyze massive clinical data, which can help doctors diagnose the disease more accurately and provide personalized treatment plans. In addition, AI technology also plays an important role in medical image analysis, genomics research and other aspects, which can help the development of new drugs and improve patient prognosis. This article reviews the application progress of AI in retinoblastoma.

Research progress of artificial intelligence in pathological subtypes classification and gene expression analysis of lung adenocarcinoma / 中国胸心血管外科临床杂志

@#Lung adenocarcinoma is a prevalent histological subtype of non-small cell lung cancer with different morphologic and molecular features that are critical for prognosis and treatment planning. In recent years, with the development of artificial intelligence technology, its application in the study of pathological subtypes and gene expression of lung adenocarcinoma has gained widespread attention. This paper reviews the research progress of machine learning and deep learning in pathological subtypes classification and gene expression analysis of lung adenocarcinoma, and some problems and challenges at the present stage are summarized and the future directions of artificial intelligence in lung adenocarcinoma research are foreseen.

Optical coherence tomography angiography manifestations of different degrees of nonproliferative diabetic retinopathy / 国际眼科杂志(Guoji Yanke Zazhi)

AIM: To investigate the differences in varying stages of non-proliferative diabetic retinopathy(NPDR)using optical coherence tomography angiography(OCTA).METHODS: Cross-sectional study. A total of 77 cases(77 eyes)of diabetic patients were included, and they were divided into non-diabetic retinopathy(NDR; 23 eyes)and non-proliferative diabetic retinopathy(NPDR; 54 eyes)groups, further subdivided into mild NPDR(20 eyes), moderate NPDR(20 eyes), and severe NPDR(14 eyes). Foveal avascular zone(FAZ)area, superficial and deep capillary plexus densities(SSP and DSP), and visual acuity(LogMAR)were compared between NDR and NPDR groups. Furthermore, the visual acuity, FAZ area and levels of SSP and DSP were compared in different degrees of NPDR. Correlation analysis were conducted to elucidate relationships between FAZ area, visual acuity, SSP, DSP, and severity of the disease.RESULTS: Compared with the NDR group, the visual acuity(LogMAR)and macular FAZ area increased, while SSP and DSP were decreased in the NPDR group(P<0.05); there were significant differences in visual acuity, FAZ area and SSP and DSP levels in different degrees of NPDR(P<0.05). Visual acuity(LogMAR)and FAZ area displayed a positive correlation with the severity of disease, while SSP and DSP showed a negative correlation.CONCLUSION: With the progression of NPDR, the visual acuity(LogMAR)and FAZ area increased, and the SSP and DSP decreased.

Application of artificial intelligence in ophthalmic plastic surgery / 国际眼科杂志(Guoji Yanke Zazhi)

The advancement of computers and data explosion have ushered in the third wave of artificial intelligence(AI). AI is an interdisciplinary field that encompasses new ideas, new theories, and new technologies, etc. AI has brought convenience to ophthalmology application and promoted its intelligent, precise, and minimally invasive development. At present, AI has been widely applied in various fields of ophthalmology, especially in oculoplastic surgery. AI has made rapid progress in image detection, facial recognition, etc., and its performance and accuracy have even surpassed humans in some aspects. This article reviews the relevant research and applications of AI in oculoplastic surgery, including ptosis, single eyelid, pouch, eyelid mass, and exophthalmos, and discusses the challenges and opportunities faced by AI in oculoplastic surgery, and provides prospects for its future development, aiming to provide new ideas for the development of AI in oculoplastic surgery.

Fundamentals of deep brain stimulation for Parkinson's disease in clinical practice: part 1 / Princípios da estimulação cerebral profunda na doença de Parkinson na prática clínica: parte 1

Abstract Deep brain stimulation (DBS) is recognized as an established therapy for Parkinson's disease (PD) and other movement disorders in the light of the developments seen over the past three decades. Long-term efficacy is established for PD with documented improvement in the cardinal motor symptoms of PD and levodopa-induced complications, such as motor fluctuations and dyskinesias. Timing of patient selection is crucial to obtain optimal benefits from DBS therapy, before PD complications become irreversible. The objective of this first part review is to examine the fundamental concepts of DBS for PD in clinical practice, discussing the historical aspects, patient selection, potential effects of DBS on motor and non-motor symptoms, and the practical management of patients after surgery.

Resumo Nas últimas três décadas, a estimulação cerebral profunda (ECP) se tornou um tratamento bem estabelecido para doença de Parkinson (DP) e outros transtornos do movimento. A eficácia a longo prazo na DP foi bem documentada para a melhora dos sintomas motores cardinais da DP e das complicações induzidas pelo uso do levodopa, como as flutuações motoras e as discinesias. O momento da seleção do paciente é crucial para se obter os benefícios ideais da ECP, antes que as complicações da DP se tornem irreversíveis. O objetivo desta primeira parte da revisão é examinar os conceitos fundamentais da ECP na prática clínica, discutindo os aspectos históricos, a seleção de pacientes, os potenciais efeitos da ECP nos sintomas motores e não motores da doença e o manejo prático dos pacientes após a cirurgia.

Intraoperative Wound Lavage System for Deep Neck Infection: A Retrospective Cohort Study

Abstract Introduction Multiple solutions are currently used to cleanse a deep neck infection (DNI), and a variety of devices are available to deliver wound irrigation solutions. An essential difference between these devices is the pressure that the irrigation solution exerts over the wound tissue. Objective To compare low-pressure and high-pressure irrigation delivery systems for wound cleansing in DNI. Methods we designed a retrospective cohort study and reviewed the medical records of patients operated on due to DNI from June 2016 to December 2017 at our institution. One cohort included patients treated with an intraoperative irrigation method that exerts low pressure over the irrigated tissue, and the other cohort, to a system capable of generating higher pressure. The Pearson Chi-squared test was used to analyze the data. Results A total of 42 patients whose ages ranged from 16 months to 72 years were included. The low-pressure irrigation system was used in 18 patients, and the high-pressure system was used in 24 patients. No statistical differences were observed regarding the irrigation methods, the complexity of the DNI, and the overall outcomes. Conclusions The present is the first study in which low- and high-pressure systems for wound lavage were evaluated in the treatment of DNI. When comparing these methods, we did not find one to be superior to the other; however, the additional cost associated with the high-pressure devices may not justify their in head and neck procedures.

Applications of Artificial Intelligence in Dentomaxillofacial Diagnosis

SUMMARY Introduction: The introduction of applications driven by artificial intelligence is revolutionizing dentomaxillofacial imaging. Objectives: Describe the current state of the applications of artificial intelligence in dentomaxillofacial diagnosis, evaluate its impact, and identify future directions for research and implementation. Method : A narrative review was carried out using systematic searches in databases such as PubMed, Google Scholar, IEEE Xplore, among others. The study focused on articles published from 2010 to the present. Research that applies artificial intelligence technologies in dentomaxillofacial diagnosis was included and its quality and relevance were evaluated using established tools. Results: Artificial intelligence, especially deep learning, has shown significant improvements in image segmentation, disease detection, and treatment planning in dentomaxillofacial imaging. Artificial intelligence techniques have allowed the automation of image analysis tasks, improving efficiency and diagnostic accuracy. Conclusions: Artificial intelligence has significant potential to revolutionize dentomaxillofacial imaging, as it offers improvements in diagnostic accuracy, efficiency in image interpretation, and treatment planning. Further research is needed to overcome technical, ethical, and privacy challenges and validate the clinical applicability of these technologies.

Introducción: La introducción de aplicaciones impulsadas por la inteligencia artificial está revolucionando la imagenología dentomaxilofacial. Objetivos: Describir el estado actual de las aplicaciones de la inteligencia artificial en el diagnóstico dentomaxilofacial; evaluar su impacto e identificar direcciones futuras para la investigación y la implementación. Método : Se realizó una revisión narrativa, utilizando búsquedas sistemáticas en bases de datos como PubMed, Google Scholar, IEEE Xplore, entre otras; el estudio se enfocó en artículos publicados desde 2010 hasta la actualidad. Se incluyeron investigaciones que aplican tecnologías de la inteligencia artificial en el diagnóstico dentomaxilofacial; se evaluó su calidad y relevancia mediante las herramientas establecidas. Resultados: La inteligencia artificial, especialmente el aprendizaje profundo, ha mostrado mejoras significativas en la segmentación de imágenes, la detección de enfermedades y la planificación del tratamiento en imagenología dentomaxilofacial. Las técnicas de inteligencia artificial han permitido la automatización de tareas de análisis de imágenes, mejorado la eficiencia y la precisión diagnóstica. Conclusiones: La inteligencia artificial posee un potencial significativo para revolucionar la imagenología dentomaxilofacial, pues ofrece mejoras en la precisión diagnóstica, eficiencia en la interpretación de imágenes y en la planificación del tratamiento. Se necesitan más investigaciones para superar desafíos técnicos, éticos y de privacidad y validar la aplicabilidad clínica de estas tecnologías.

Treatment of Parkinson's disease by deep brain stimulation: a bibliometric analysis

ABSTRACT BACKGROUND: For more than 30 years, deep brain stimulation (DBS) has been a therapeutic tool for Parkinson's disease (PD) treatment. DBS can ameliorate several motor and non-motor symptoms and improve the patients' quality of life. OBJECTIVES: To analyze the global scientific production of original and review articles on Parkinson's disease treatment using deep brain stimulation. DESIGN AND SETTING: Descriptive, bibliometric study with a quantitative approach. METHOD: The research protocol was conducted in March 2023 using the Web of Science database. Six hundred eighty-four articles were included in the analysis. Data were imported into RStudio Desktop Software, linked to R Software. The Bibliometrix R package, its Biblioshiny web interface, and VOSviewer software were used for the analysis. RESULTS: The international production began in 1998. Movement Disorders is the journal with the largest number of published articles and the most cited. Michael Okun and Andres Lozano are the authors who produced the most in this area. The University of Florida is the most active affiliated institution in Brazil. The United States has the largest number of collaborations and is mainly published by local researchers. In contrast, countries such as the United Kingdom and Canada have a high number of multi-country publications. The 15 most cited studies predominantly investigated subthalamic nucleus stimulation. CONCLUSION: DBS for Parkinson's disease is a relatively novel therapeutic approach, with studies that have expanded over the last twenty-five years. Most scientific production was quantitative and restricted to specialized journals. The United States, Europe, and China held the most articles.

Diagnóstico da retinopatia diabética por inteligência artificial por meio de smartphone / Diagnosis of diabetic retinopathy by artificial intelligence using smartphone

RESUMO Objetivo: Obter imagens de fundoscopia por meio de equipamento portátil e de baixo custo e, usando inteligência artificial, avaliar a presença de retinopatia diabética. Métodos: Por meio de um smartphone acoplado a um dispositivo com lente de 20D, foram obtidas imagens de fundo de olhos de pacientes diabéticos; usando a inteligência artificial, a presença de retinopatia diabética foi classificada por algoritmo binário. Resultados: Foram avaliadas 97 imagens da fundoscopia ocular (45 normais e 52 com retinopatia diabética). Com auxílio da inteligência artificial, houve acurácia diagnóstica em torno de 70 a 100% na classificação da presença de retinopatia diabética. Conclusão: A abordagem usando dispositivo portátil de baixo custo apresentou eficácia satisfatória na triagem de pacientes diabéticos com ou sem retinopatia diabética, sendo útil para locais sem condições de infraestrutura.

ABSTRACT Introduction: To obtain fundoscopy images through portable and low-cost equipment using artificial intelligence to assess the presence of DR. Methods: Fundus images of diabetic patients' eyes were obtained by using a smartphone coupled to a device with a 20D lens. By using artificial intelligence (AI), the presence of DR was classified by a binary algorithm. Results: 97 ocular fundoscopy images were evaluated (45 normal and 52 with DR). Through AI diagnostic accuracy around was 70% to 100% in the classification of the presence of DR. Conclusion: The approach using a low-cost portable device showed satisfactory efficacy in the screening of diabetic patients with or without diabetic retinopathy, being useful for places without infrastructure conditions.

Comparison of Efficacy and Safety of Midazolam versus Nitrous Oxide as Sedative Agents during Paediatric Dental Treatment: A Systematic Review / Comparison of Efficacy and Safety of Midazolam versus Nitrous Oxide as Sedative Agents during Paediatric Dental Treatment: A Systematic Review

ABSTRACT Objective: To identify and study the existing literature on the efficacy and safety of midazolam compared to inhalation of nitrous oxide in children undergoing dental treatment. Material and Methods: Electronic resources such as PubMed Central, Cochrane Database of Systematic Reviews, Lilacs, Science Direct, and SIGLE were thoroughly searched. The title scan was used to find randomised controlled trials reviewed for inclusion by reading the abstract. Studies comparing the sedative, behavioural, and anxiolytic effects and safety in children undergoing dental treatment under midazolam and nitrous oxide inhalation were included. The Cochrane Reviews system software, Revman 5.4.1, was used to assess the quality of the included studies. Results: 11328 articles were identified by screening the electronic databases, of which 10906 were eliminated after titles were read and duplicates were removed. Ten full-text articles were examined, of which three were excluded as they did not match the eligibility criteria. Hence, a total of 7 studies were included. Midazolam and nitrous oxide inhalation were not statistically different in terms of the success of treatment and behaviour modification. However, midazolam showed a deeper level of sedation and resulted in amnesia in more children when compared to nitrous oxide sedation. All of the included studies were found to have a high risk of bias. Conclusion: Though all the studies included showed an increased risk of bias, midazolam and nitrous oxide inhalation seem equally effective sedative agents for controlling behaviour in children undergoing dental treatment. Midazolam shows a deeper sedation level when given orally and produces a higher rate of anterograde amnesia.

A mudança de paradigma no tratamento do tromboembolismo venoso grave / The paradigm shift in treatment of severe venous thromboembolism

Resumo A embolia pulmonar (EP) é a terceira maior causa de morte cardiovascular e a principal de morte evitável intra-hospitalar no mundo. O conceito PERT® (do inglês, pulmonary embolism response team) envolve seu diagnóstico e tratamento precoce e multidisciplinar. A trombose venosa profunda (TVP) é a sua causa inicial na maioria dos casos e é responsável por complicações como a recidiva tromboembólica, a síndrome pós-trombótica e a hipertensão pulmonar tromboembólica crônica. Uma abordagem inicial semelhante ao PERT nos casos de TVP ilíaco-femoral grave pode reduzir não apenas o risco imediato de EP e morte, mas também suas sequelas tardias. Novas técnicas percutâneas e aparatos de trombectomia mecânica para o tromboembolismo venoso (TEV) vêm demonstrando resultados clínicos encorajadores. Propomos o desenvolvimento de um conceito ampliado de resposta rápida ao TEV, que envolve não apenas a EP (PERT®) mas também os casos graves de TVP: o time de resposta rápida para o TEV (TRETEV®), ou do inglês Venous Thromboembolism Response Team (VTERT®).

Abstract Pulmonary embolism (PE) is the third leading cause of cardiovascular death and the main cause of preventable in-hospital death in the world. The PERT® (Pulmonary Embolism Response Team) concept involves multidisciplinary diagnosis and immediate treatment. Deep venous thrombosis (DVT) is the initial cause of most cases of PE and is responsible for complications such as chronic thromboembolic recurrence, postthrombotic syndrome, and chronic thromboembolic pulmonary hypertension. An aggressive approach to severe cases of iliofemoral DVT similar to the PERT® system can not only reduce the immediate risk of PE and death but can also reduce later sequelae. New percutaneous techniques and mechanical thrombectomy devices for venous thromboembolism (VTE) have shown encouraging clinical results. We propose the development of an expanded concept of rapid response to VTE, which involves not only PE (PERT®) but also severe cases of DVT: the Venous Thromboembolism Response Team (VTERT®).

Is Deep Hypothermic Cardiac Arrest Mandatory in Aortic Arch Surgeries?

ABSTRACT Cannulation strategies in aortic arch surgeries are a matter of immense discussion. Majority of time deep hypothermic circulatory arrest (DHCA) is the way out, but it does come with its set of demerits. Here we demonstrate a case with aortic arch dissection dealt with dual cannulation strategy in axillary and femoral artery without need for DHCA and ensuring complete neuroprotection of brain and spinal cord without hinderance of time factor. Inception of new ideas like this may decrease the need for DHCA and hence its drawbacks, thus decreasing the morbidity and mortality associated.

Brazilian version of the Pasero Opioid-Induced Sedation Scale: cross-cultural adaptation study / Versión brasileña de la escala Pasero Opioid-Induced Sedation Scale: estudio de adaptación transcultural / Versão brasileira da Pasero Opioid-Induced Sedation Scale: estudo de adaptação transcultural

ABSTRACT Objective: Perform a cross-cultural adaptation of the Pasero Opioid-induced Sedation Scale to the Brazilian setting. Method: This is a methodological study using Beaton's framework, which consists in six stages: translation, synthesis of translations, re-translation, expert committee, pre-test, and sending the adapted version of the instrument to the author of the original. The study was carried out from April to December 2021. The research was conducted in a private hospitalin the city of São Paulo, in the adult hospitalization and critical care units. It was approved by the research ethics committee. Results: After translation, translation synthesis and back-translation steps, the version was evaluated by the expert committee, requiring two rounds to obtain acceptable CVI values above 0.80. In the pre-test phase, the scale was well understood, with a CVI of 0.98. Conclusion: The scale was adapted for the Brazilian context; however, further studies will be needed to analyze validity and reliability evidence.

RESUMEN Objetivo: Realizar la adaptación transcultural de la escala de Pasero Opioid-induced Sedation Scale para el contexto brasileño. Método: Estudio metodológico, utilizando el marco de referencia de Beaton, que consta de seis fases: traducción, síntesis de traducciones, traducción inversa, comité de expertos, prueba previa, y envío del instrumento adaptado ala autora del instrumento original. El estudio se realizó de abril a diciembre de 2021, y a la investigación se condujo en un hospital privado, ubicado en la ciudad de São Paulo, en las unidades de hospitalización de adultos y cuidados críticos. Recibió la aprobación del comité de ética. Resultados: Después de las etapas de traducción, síntesis de traducción y traducción inversa, la versión fue evaluada por un comité de expertos, con dos rondas para obtener valores aceptables de índice de validez de contenido superiores a 0,80. En la fase previa a la prueba, la escala mostró una buena comprensión, con una puntuación de 0,98. Conclusión: La escala fue adaptada para el contexto brasileño, sin embargo, serán necesarios más estudios para analizar las evidencias de validez y confiabilidad.

RESUMO Objetivo: Realizar adaptação transcultural da escala Pasero Opioid-Induced Sedation para o cenário brasileiro. Método: Estudo metodológico, utilizado referencial de Beaton, composto por seis fases: tradução, síntese das traduções, retradução, comitê de especialistas, pré-teste e envio dos instrumentos adaptados ao autor do instrumento original. Estudo foi realizado de abril a dezembro de 2021. A pesquisa desenvolveu-se em um hospital privado, localizado no município de São Paulo, nas unidades de internação e críticas adultos. Recebeu aprovação do comitê de ética. Resultados: Após as etapas de tradução, síntese de tradução e retrotradução a versão foi avaliada pelo comitê de especialistas, com duas rodadas para obtenção de valores aceitáveis de índice de validade de conteúdo acima de 0,80. Na fase de pré-teste a escala apresentou boa compreensão com score de 0,98. Conclusão: A escala foi adaptada para o contexto brasileiro, no entanto, novos estudos serão necessários para análises de evidências de validade e confiabilidade.

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.

Infección de los espacios profundos del cuello de origen dentario / Odontogenic deep neck infections

RESUMEN Antecedentes: los pacientes con infecciones cervicales pueden presentar cuadros de extrema gravedad que ponen en riesgo su vida. Parece increíble que en pleno siglo XXI alguien muera por la infección de una muela, pero es real. Objetivo: describir los resultados con el diagnóstico y tratamiento de una serie de pacientes con infecciones de los espacios profundos del cuello de origen dentario, y establecer criterios para su manejo. Material y métodos: se realizó un estudio descriptivo y retrospectivo a partir de los registros en nuestra base datos entre septiembre de 2006 y junio de 2022. Se incluyeron sólo pacientes con infecciones cervicales de origen dentario. Se evaluaron las variables demográficas, las relacionadas al origen de la complicación, el tratamiento realizado y la evolución de los pacientes. Resultados: la muestra quedó conformada por 499 pacientes, con promedio de edad de 29 años (12- 70); 288 (57.7%) eran hombres. Consultaron en forma tardía 269 (53,9%) y se automedicaron en forma inicial 271 pacientes (54.3%). La mayoría no había recibido tratamiento de la pieza dentaria en el centro de atención primaria. Se realizó tratamiento quirúrgico 267 casos (53.5%), y el resto pudo tratarse de forma conservadora. La evolución fue favorable en 497 pacientes (99.6 %), y dos fallecieron por mediastinitis. Conclusión: las infecciones odontógenas deben ser diagnosticadas y tratadas apropiadamente en forma precoz a fin de evitar cuadros de extrema gravedad. Las campañas de educación poblacional y la instrucción de los médicos/odontólogos de centros de atención primaria y servicios de guardia podría mejorar esta problemática.

ABSTRACT Background: Patients with deep infections may present with extremely serious and life-threatening conditions. It is unbelievable that someone could die from a molar infection in the 21st century, but it is real. Objective: The aim of the present study is to describe the diagnosis and treatment results of a series of patients with odontogenic deep neck infections, and to establish criteria for the management of these infections. Material and methods: We conducted a retrospective and descriptive study based on records from a database from September 2006 to June 2022. Only patients with odontogenic deep neck infections were included. The demographic variables, those related to the origin of the complication, the treatment performed, and the patients' progress were evaluated. Results: The sample was made up of 499 patients; mean age was 29 years (12-70) and 288 (57.7%) were men. Late visits and self-medication were recorded in 269 patients (53.9%) and 271 patients (54.3%), respectively. Most of them had not received treatment for the affected tooth at the primary healthcare center. Surgical treatment was performed in 267 cases (53.5%), and the rest were managed with conservative approach. The disease had a favorable course in 497 patients (99.6%) and two patients died of mediastinitis. Conclusion: Odontogenic infections should be adequately diagnosed and treated correctly and early to avoid extremely serious complications. Population-based educational campaigns and training for physicians and dentists working in primary care centers and emergency departments could improve this issue.

El lifting cervicofacial de plano profundo: Presentación de la técnica y resultados

Objetivo: El lifting cervicofacial es una técnica que busca devolver una apariencia juvenil y descansada al rostro del paciente. Originalmente, esta técnica se limitaba solamente a una disección en el plano cutáneo. El lifting de plano profundo o deep plane facelft, en cambio, utiliza un plano de disección anatómico por debajo del sistema musculoaponeurótico superficial (SMAS), permitiendo la lisis de los ligamentos de retención faciales y la máxima movilización de los tejidos superficiales, confiriéndole ventajas frente a otras técnicas. Se describe la técnica y se presenta nuestra experiencia. Material y Método: Serie de casos retrospectiva de pacientes sometidos a lifting de plano profundo en nuestro centro. Se describe la técnica quirúrgica, datos demográficos, antecedentes médico quirúrgicos y complicaciones post-operatorias. Resultados: Entre enero de 2021 y junio de 2023 se operaron 18 pacientes, todos de sexo femenino con un promedio de edad de 58,7 años. Solo 2 pacientes presentaron complicaciones (hematoma). Ningún paciente presentó lesión del nervio facial transitoria o permanente. Ningún paciente necesitó re-operación. Discusión y conclusión: La técnica de lifting de plano profundo o deep plane facelft es un método seguro y efectivo para tratar los signos del envejecimiento facial. Las complicaciones descritas por nuestro grupo son acordes a la literatura.

Aim: The facelift is a technique that aims to restore a more youthful and rested appearance to the aging face. Originally it was limited to a skin dissection only. The deep plane facelift, on the other hand, uses an anatomical dissection plane below the superficial muscular aponeurotic system (SMAS), allowing lysis of the facial retention ligaments and maximum mobilization of superficial tissues, with better outcomes than other techniques. The technique is described and our experience is presented. Material and Method: Retrospective case series of patients undergoing deep plane facelift. The surgical technique, demographic data, surgical medical history, and postoperative complications are described. Results: Between January 2021 and June 2023, 18 patients were operated, all female with an average age of 58,7 years old. Only 2 patients presented complications (hematoma). No patient presented facial nerve injury. No patient required re-operation. Discussion and Conclusion: The deep plane facelift is a safe and effective method to treat the signs of the aging face. The complications described are consistent with the literature.

Tomografía fotoacústica y Deep Learning en aplicacionesmédicas

En las últimas décadas, las imágenes fotoacústicas han demostrado su eficacia en el apoyo al diagnóstico de algunas enfermedades, así como en la investigación médica, ya que a través de ellas es posible obtener información del cuerpo humano con características específicas y profundidad de penetración, desde 1 cm hasta 6 cm dependiendo en gran medida del tejido estudiado, además de una buena resolución. Las imágenes fotoacústicas son comparativamente jóvenes y emergentes y prometen mediciones en tiempo real, con procedimientos no invasivos y libres de radiación. Por otro lado, aplicar Deep Learning a imágenes fotoacústicas permite gestionar datos y transformarlos en información útil que genere conocimiento. Estas aplicaciones poseen ventajas únicas que facilitan la aplicación clínica. Se considera que con estas técnicas se pueden proporcionar diagnósticos médicos confiables. Es por eso que el objetivo de este artículo es proporcionar un panorama general de los casos donde se combina el Deep Learning con técnicas fotoacústicas.

In recent decades, photoacoustic imaging has proven its effectiveness in supporting the diagnosis of some diseases as well as in medical research, since through them it is possible to obtain information of the human body with specific characteristics and depth of penetration, from 1 cm to 6 cm depending largely on the tissue studied, in addition to a good resolution. Photoacoustic imaging is comparatively young and emerging and promises real-time measurements, with non-invasive and radiation-free procedures. On the other hand, applying Deep Learning to photoacoustic images allows managing data and transforming them into useful information that generates knowledge. These applications have unique advantages that facilitate clinical application. It may be possible with these techniques to provide reliable medical diagnoses. That is why the aim of this article is to provide an overview of cases combining Deep Learning with photoacoustic techniques.