Realidad virtual y biomarcadores digitales: una herramienta clínica para el diagnóstico del autismo / Virtual reality and digital biomarkers: a clinical tool for early autism diagnosis

Resumen Introducción : El Trastorno del Espectro Autista (TEA) es un trastorno del neurodesarrollo, y sus procedimien tos tradicionales de evaluación encuentran ciertas li mitaciones. El actual campo de investigación sobre TEA está explorando y respaldando métodos innovadores para evaluar el trastorno tempranamente, basándose en la detección automática de biomarcadores. Sin embargo, muchos de estos procedimientos carecen de validez ecológica en sus mediciones. En este contexto, la reali dad virtual (RV) presenta un prometedor potencial para registrar objetivamente bioseñales mientras los usuarios experimentan situaciones ecológicas. Métodos : Este estudio describe un novedoso y lúdi co procedimiento de RV para la evaluación temprana del TEA, basado en la grabación multimodal de bio señales. Durante una experiencia de RV con 12 esce nas virtuales, se midieron la mirada, las habilidades motoras, la actividad electrodermal y el rendimiento conductual en 39 niños con TEA y 42 compañeros de control. Se desarrollaron modelos de aprendizaje automático para identificar biomarcadores digitales y clasificar el autismo. Resultados : Las bioseñales reportaron un rendimien to variado en la detección del TEA, mientras que el modelo resultante de la combinación de los modelos de las bioseñales demostró la capacidad de identificar el TEA con una precisión del 83% (DE = 3%) y un AUC de 0.91 (DE = 0.04). Discusión : Esta herramienta de detección pue de respaldar el diagnóstico del TEA al reforzar los resultados de los procedimientos tradicionales de evaluación.

Abstract Introduction : Autism Spectrum Disorder (ASD) is a neurodevelopmental condition which traditional as sessment procedures encounter certain limitations. The current ASD research field is exploring and endorsing innovative methods to assess the disorder early on, based on the automatic detection of biomarkers. How ever, many of these procedures lack ecological validity in their measurements. In this context, virtual reality (VR) shows promise for objectively recording biosignals while users experience ecological situations. Methods : This study outlines a novel and playful VR procedure for the early assessment of ASD, relying on multimodal biosignal recording. During a VR experience featuring 12 virtual scenes, eye gaze, motor skills, elec trodermal activity and behavioural performance were measured in 39 children with ASD and 42 control peers. Machine learning models were developed to identify digital biomarkers and classify autism. Results : Biosignals reported varied performance in detecting ASD, while the combined model resulting from the combination of specific-biosignal models demon strated the ability to identify ASD with an accuracy of 83% (SD = 3%) and an AUC of 0.91 (SD = 0.04). Discussion : This screening tool may support ASD diagnosis by reinforcing the outcomes of traditional assessment procedures.

Optimización de la interpretación de ecocardiogramas con la utilización de Machine Learning en el estudio WASE / Optimizing Echocardiograms Interpretation with the Application of Machine Learning in the WASE Study

RESUMEN Introducción: El número creciente de estudios ecocardiográficos y la necesidad de cumplir rigurosamente con las recomendaciones de guías internacionales de cuantificación, ha llevado a que los cardiólogos deban realizar tareas sumamente extensas y repetitivas, como parte de la interpretación y análisis de cantidades de información cada vez más abrumadoras. Novedosas técnicas de machine learning (ML), diseñadas para reconocer imágenes y realizar mediciones en las vistas adecuadas, están siendo cada vez más utilizadas para responder a esta necesidad evidente de automatización de procesos. Objetivos: Nuestro objetivo fue evaluar un modelo alternativo de interpretación y análisis de estudios ecocardiográficos, basado fundamentalmente en la utilización de software de ML, capaz de identificar y clasificar vistas y realizar mediciones estandarizadas de forma automática. Material y métodos: Se utilizaron imágenes obtenidas en 2000 sujetos normales, libres de enfermedad, de los cuales 1800 fueron utilizados para desarrollar los algoritmos de ML y 200 para su validación posterior. Primero, una red neuronal convolucional fue desarrollada para reconocer 18 vistas ecocardiográficas estándar y clasificarlas de acuerdo con 8 grupos (stacks) temáticos. Los resultados de la identificación automática fueron comparados con la clasificación realizada por expertos. Luego, algoritmos de ML fueron desarrollados para medir automáticamente 16 parámetros de eco Doppler de evaluación clínica habitual, los cuales fueron comparados con las mediciones realizadas por un lector experto. Finalmente, comparamos el tiempo necesario para completar el análisis de un estudio ecocardiográfico con la utilización de métodos manuales convencionales, con el tiempo necesario con el empleo del modelo que incorpora ML en la clasificación de imágenes y mediciones ecocardiográficas iniciales. La variabilidad inter e intraobservador también fue analizada. Resultados: La clasificación automática de vistas fue posible en menos de 1 segundo por estudio, con una precisión de 90 % en imágenes 2D y de 94 % en imágenes Doppler. La agrupación de imágenes en stacks tuvo una precisión de 91 %, y fue posible completar dichos grupos con las imágenes necesarias en 99% de los casos. La concordancia con expertos fue excelente, con diferencias similares a las observadas entre dos lectores humanos. La incorporación de ML en la clasificación y medición de imágenes ecocardiográficas redujo un 41 % el tiempo de análisis y demostró menor variabilidad que la metodología de interpretación convencional. Conclusión: La incorporación de técnicas de ML puede mejorar significativamente la reproducibilidad y eficiencia de las interpretaciones y mediciones ecocardiográficas. La implementación de este tipo de tecnologías en la práctica clínica podría resultar en reducción de costos y aumento en la satisfacción del personal médico.

ABSTRACT Background: The growing number of echocardiographic tests and the need for strict adherence to international quantification guidelines have forced cardiologists to perform highly extended and repetitive tasks when interpreting and analyzing increasingly overwhelming amounts of data. Novel machine learning (ML) techniques, designed to identify images and perform measurements at relevant visits, are becoming more common to meet this obvious need for process automation. Objectives: Our objective was to evaluate an alternative model for the interpretation and analysis of echocardiographic tests mostly based on the use of ML software in order to identify and classify views and perform standardized measurements automatically. Methods: Images came from 2000 healthy subjects, 1800 of whom were used to develop ML algorithms and 200 for subsequent validation. First, a convolutional neural network was developed in order to identify 18 standard echocardiographic views and classify them based on 8 thematic groups (stacks). The results of automatic identification were compared to classification by experts. Later, ML algorithms were developed to automatically measure 16 Doppler scan parameters for regular clinical evaluation, which were compared to measurements by an expert reader. Finally, we compared the time required to complete the analysis of an echocardiographic test using conventional manual methods with the time needed when using the ML model to classify images and perform initial echocardiographic measurements. Inter- and intra-observer variability was also analyzed. Results: Automatic view classification was possible in less than 1 second per test, with a 90% accuracy for 2D images and a 94% accuracy for Doppler scan images. Stacking images had a 91% accuracy, and it was possible to complete the groups with any necessary images in 99% of cases. Expert agreement was outstanding, with discrepancies similar to those found between two human readers. Applying ML to echocardiographic imaging classification and measurement reduced time of analysis by 41% and showed lower variability than conventional reading methods. Conclusion: Application of ML techniques may significantly improve reproducibility and efficiency of echocardiographic interpretations and measurements. Using this type of technologies in clinical practice may lead to reduced costs and increased medical staff satisfaction.

Inteligencia artificial. Aplicación en las imágenes cardiovasculares y la prevención cardiovascular / Artificial Intelligence in Cardiovascular Imaging and Cardiovascular Prevention

RESUMEN La inteligencia artificial (IA) está basada en programas computacionales que pueden imitar el pensamiento humano y automatizar algunos procesos. En el ámbito médico se está estudiando hace más de 50 años, pero en los últimos años el crecimiento ha sido exponencial. El campo de las imágenes cardiovasculares es particularmente atractivo para aplicarla, dado que, guiadas por IA, personas no expertas pueden adquirir imágenes completas, automatizar procesos y mediciones, orientar diagnósticos, detectar hallazgos no visibles al ojo humano, realizar diagnósticos oportunistas de afecciones no buscadas en el estudio índice pero evaluables a través de las imágenes disponibles, o identificar patrones de asociación dentro de una gran cantidad de datos como fuente de generación de hipótesis. En el campo de la prevención cardiovascular, la IA se ha aplicado en diferentes escenarios con fines diagnósticos, pronósticos y terapéuticos en el manejo de algunos factores de riesgo cardiovascular, como las dislipidemias o la hipertensión arterial. Si bien existen limitaciones con el uso de la IA tales como el costo, la accesibilidad y la compatibilidad de los programas, la validez externa de los resultados en determinadas poblaciones, o algunos aspectos éticos-legales (privacidad de los datos), esta tecnología está en crecimiento vertiginoso y posiblemente revolucione la práctica médica actual.

ABSTRACT Artificial intelligence (AI) is based on computer programs that imitate human thinking and automate certain processes. Artificial intelligence has been studied in the medical field for over 50 years, but in recent years, its growth has been exponential. The field of cardiovascular imaging is particularly attractive since AI can guide non-experts in image acquisition, automate processes and measurements, guide diagnoses, detect findings not visible to the human eye, make opportunistic diagnoses of unexpected conditions in the index test, or identify patterns of association within a large amount of data as a source of hypothesis generation. In the field of cardiovascular prevention, AI has been used for diagnostic, prognostic, and therapeutic purposes in managing cardiovascular risk factors such as dyslipidemia and hypertension. While there are limitations to the use of AI, such as cost, accessibility, compatibility of programs, external validity of results in certain populations, and ethical-legal aspects such as data privacy, this technology is rapidly growing and is likely to revolutionize current medical practice.

Artificial intelligence, applications and challenges in simulation-based education

The rapid advancement of Artificial Intelligence (AI) has taken the world by "surprise" due to the lack of regulation over this technological innovation which, while promising application opportunities in different fields of knowledge, including education, simultaneously generates concern, rejection and even fear. In the field of Health Sciences Education, clinical simulation has transformed educational practice; however, its formal insertion is still heterogeneous, and we are now facing a new technological revolution where AI has the potential to transform the way we conceive its application.

El rápido avance de la inteligencia artificial (IA) ha tomado al mundo por "sorpresa" debido a la falta de regulación sobre esta innovación tecnológica, que si bien promete oportunidades de aplicación en diferentes campos del conocimiento, incluido el educativo, también genera preocupación e incluso miedo y rechazo. En el campo de la Educación en Ciencias de la Salud la Simulación Clínica ha transformado la práctica educativa; sin embargo, aún es heterogénea su inserción formal, y ahora nos enfrentamos a una nueva revolución tecnológica, en la que las IA tienen el potencial de transformar la manera en que concebimos su aplicación.

The Efficacy of Tranexamic Acid in Reducing Perioperative Drainage in Cardiac Surgery with Cardiopulmonary Bypass

ABSTRACT Introduction: Although cardiopulmonary bypass procedures remain a critical treatment option for heart disease, they come with risks, including hemorrhage. Tranexamic acid is known to reduce morbidity and mortality in surgical hemorrhage. Objective: This study aimed to evaluate the efficacy of tranexamic acid, which is routinely used to treat hemorrhage, in decreasing the amount of intraoperative and postoperative drainage. Method: A total of 80 patients who underwent cardiac surgery with cardiopulmonary bypass were included in this retrospective study. Forty patients who received tranexamic acid during the operation were assigned to Group 1, while 40 patients who did not receive tranexamic acid were assigned to Group 2. Patient data were collected from the hospital computer system and/or archive records after applying exclusion criteria, and the data were recorded. Statistical analyses were then performed to compare the data. Results: Age, sex, height, weight, body surface area, flow, and ejection fraction percentages, preoperative hematological parameters, and intraoperative variables (except tranexamic acid) were similar between the groups (P>0.05). However, there were statistically significant differences between the groups in terms of intraoperative (through the heart-lung machine) and postoperative red blood cell transfusion rates, intraoperative and postoperative bleeding drainage amounts, as well as postoperative hematocrit, hemoglobin, platelet, and red blood cell levels (P<0.05). Conclusion: We concluded that intraoperative and postoperative use of tranexamic acid in patients who underwent coronary artery bypass grafting with cardiopulmonary bypass has positive effects on hematological parameters, reducing blood product use, and bleeding drainage amount.

Prediction of tuberculosis clusters in the riverine municipalities of the Brazilian Amazon with machine learning / Predição de áreas de aglomeração de tuberculose nos municípios ribeirinhos da Amazônia brasileira com aprendizagem de máquina

ABSTRACT Objective: Tuberculosis (TB) is the second most deadly infectious disease globally, posing a significant burden in Brazil and its Amazonian region. This study focused on the "riverine municipalities" and hypothesizes the presence of TB clusters in the area. We also aimed to train a machine learning model to differentiate municipalities classified as hot spots vs. non-hot spots using disease surveillance variables as predictors. Methods: Data regarding the incidence of TB from 2019 to 2022 in the riverine town was collected from the Brazilian Health Ministry Informatics Department. Moran's I was used to assess global spatial autocorrelation, while the Getis-Ord GI* method was employed to detect high and low-incidence clusters. A Random Forest machine-learning model was trained using surveillance variables related to TB cases to predict hot spots among non-hot spot municipalities. Results: Our analysis revealed distinct geographical clusters with high and low TB incidence following a west-to-east distribution pattern. The Random Forest Classification model utilizes six surveillance variables to predict hot vs. non-hot spots. The machine learning model achieved an Area Under the Receiver Operator Curve (AUC-ROC) of 0.81. Conclusion: Municipalities with higher percentages of recurrent cases, deaths due to TB, antibiotic regimen changes, percentage of new cases, and cases with smoking history were the best predictors of hot spots. This prediction method can be leveraged to identify the municipalities at the highest risk of being hot spots for the disease, aiding policymakers with an evidenced-based tool to direct resource allocation for disease control in the riverine municipalities.

RESUMO Objetivo: A tuberculose (TB) é a segunda doença infecciosa que mais mata no mundo, representando um problema de saúde pública no Brasil, especialmente na região amazônica. Este estudo analisa a TB nos municípios ribeirinhos" com o objetivo de identificar aglomerados de alta incidência, também conhecidos como "hot spots". Posteriormente, utilizando aprendizagem de máquina, visamos prever estes aglomerados por meio de variáveis de vigilância epidemiológica. Assim buscamos auxiliar o ente público no combate à TB nesta região. Métodos: Dados da incidência de TB nos "municípios ribeirinhos" foram coletados entre os anos de 2019 e 2022 do Departamento de Informática do Ministério da Saúde. O índice de Moran foi utilizado para a determinação de autocorrelação espacial global, enquanto o método Getis-Ord GI* foi empregado para a autocorrelação espacial local. Variáveis referentes ao diagnóstico, tratamento e características socioeconômicas associadas aos casos foram utilizadas para a predição de aglomerados de alta incidência por meio de um modelo Random Forest. Resultados: Foram identificados aglomerados com alta incidência de TB a oeste e baixa incidência a leste. O total de seis variáveis de vigilância epidemiológica foi identificado como relevante para a predição. Nosso modelo Random Forest alcança uma área sob a curva da característica operacional do receptor (AUC-ROC) de 0,81. Conclusão: Municípios com altas porcentagens de casos recorrentes, mortes por TB, mudança do esquema de tratamento, casos novos e casos com história de tabagismo estão associados a aglomerados de alta incidência. Esperamos que este método de identificação de possíveis aglomerados de TB seja útil para o ente público no combate à doença na região.

Aplicación de algoritmos de aprendizaje supervisado para identificación de factores sociodemográficos asociados a síntomas depresivos en adultos peruanos: modelo CHAID, 2022

Introducción: la sintomatología depresiva es altamente prevalente en la población peruana. El uso del algoritmo de árbol de decisiones podría beneficiar en hallar grupos especialmente vulnerables a padecer síntomas depresivos. Objetivo: determinar los grupos especialmente vulnerables a tener síntomas depresivos según factores sociodemográficos mediante algoritmo de árbol de decisiones por aprendizaje automático. Material y métodos: se aplicó un diseño observacional, descriptivo, retrospectivo y transversal. Los datos provinieron de la encuesta nacional demográfica y de salud. La población fue 32.062 adultos. La variable dependiente fue: presencia de síntomas depresivos, y como variables explicativas: grupo etario, lengua materna, grupo étnico, nivel educativo, edad de inicio de consumo de alcohol, consumo de alcohol, estado conyugal, sexo. Se utilizó el algoritmo de árbol de decisiones mediante detección automática de interacciones mediante chi-cuadrado (CHAID). Resultados: las variables significativas en el algoritmo fueron: sexo, tipo de lengua materna, estado conyugal, grupo etario, nivel educativo alcanzado, clasificando de forma correcta 75,80% de los casos de síntomas depresivos. Los nodos asociados principalmente a la presencia de síntomas depresivos fueron: nodo 2 (sexo femenino), nodo 6 (adultos desde 39 años), nodo 13 (educación hasta secundaria). Según sexo, en mujeres, las variables principalmente asociadas fueron los correspondientes al nodo 2 (adultos desde los 39 años), nodo 5 (educación hasta secundaria) y nodo 13 (lengua materna originaria). En hombres, los nodos asociados principalmente a síntomas depresivos fueron el nodo 2 (lengua materna originaria), nodo 6 (adultos desde los 39 años) y nodo 11 (nivel educativo alcanzado hasta secundaria). Conclusiones: el principal grupo sociodemográfico asociado al desarrollo de síntomas depresivos son el sexo femenino, desde los 39 años y cuya educación ha llegado a la etapa escolar. El uso de algoritmos de aprendizaje automático es útil para crear herramientas de cribado de poblaciones vulnerables a padecer síntomas depresivos.

Introduction: Depressive symptoms are highly prevalent in the Peruvian population. The use of the decision tree algorithm could be beneficial in finding groups especially vulnerable to suffering from depressive symptoms. Objective: To determine the groups especially vulnerable to having depressive symptoms according to sociodemographic factors using a machine learning decision tree algorithm. Material and methods: An observational, descriptive, retrospective and cross-sectional design was applied. Data came from the National Demographic and Health Survey. The population was 32,062 adults and the dependent variable was the presence of depressive symptoms, and as explanatory variables: age group, mother tongue, ethnic group, educational level, age of onset of alcohol consumption, alcohol consumption, marital status, sex. The decision tree algorithm using automatic chi-square interaction detection (CHAID) was used. Results: The significant variables in the algorithm were sex, type of mother tongue, marital status, age group, educational level achieved, correctly classifying 75.80% of the cases of depressive symptoms. The nodes mainly associated with the presence of depressive symptoms were: node 2 (female sex), node 6 (adults from 39 years old), and node 13 (education up to secondary school). According to sex, in women, the variables mainly associated were those corresponding to node 2 (adults from 39 years of age), node 5 (education up to secondary school) and node 13 (original mother tongue). In men, the nodes mainly associated with depressive symptoms were node 2 (native mother tongue), node 6 (adults from 39 years of age) and node 11 (educational level reached up to secondary school). Conclusions: The main sociodemographic group associated with the development of depressive symptoms is the female sex, from the age of 39 and whose education has reached the school stage. The use of machine learning algorithms is useful to create screening tools for populations vulnerable to suffering from depressive symptoms.

An emergency room influx and trauma cases prediction in a Brazilian ophthalmological hospital by an ophthalmologist without code experience / Predição do influxo de atendimentos e casos de trauma em um serviço de urgência oftalmológico brasileiro realizado por um oftalmologista sem experiência em programação

ABSTRACT Purpose: The emergency medical service is a fundamental part of healthcare, albeit crowded emergency rooms lead to delayed and low-quality assistance in actual urgent cases. Machine-learning algorithms can provide a smart and effective estimation of emergency patients' volume, which was previously restricted to artificial intelligence (AI) experts in coding and computer science but is now feasible by anyone without any coding experience through auto machine learning. This study aimed to create a machine-learning model designed by an ophthalmologist without any coding experience using AutoML to predict the influx in the emergency department and trauma cases. Methods: A dataset of 356,611 visits at Hospital da Universidade Federal de São Paulo from January 01, 2014 to December 31, 2019 was included in the model training, which included visits/day and the international classification disease code. The training and prediction were made with the Amazon Forecast by 2 ophthalmologists with no prior coding experience. Results: The forecast period predicted a mean emergency patient volume of 216.27/day in p90, 180.75/day in p50, and 140.35/day in p10, and a mean of 7.42 trauma cases/ day in p90, 3.99/day in p50, and 0.56/day in p10. In January of 2020, there were a total of 6,604 patient visits and a mean of 206.37 patients/day, which is 13.5% less than the p50 prediction. This period involved a total of 199 trauma cases and a mean of 6.21 cases/day, which is 55.77% more traumas than that by the p50 prediction. Conclusions: The development of models was previously restricted to data scientists' experts in coding and computer science, but transfer learning autoML has enabled AI development by any person with no code experience mandatory. This study model showed a close value to the actual 2020 January visits, and the only factors that may have influenced the results between the two approaches are holidays and dataset size. This is the first study to apply AutoML in hospital visits forecast, showing a close prediction of the actual hospital influx.

RESUMO Objetivo: Esse estudo tem como objetivo criar um modelo de Machine Learning por um oftalmologista sem experiência em programação utilizando auto Machine Learning predizendo influxo de pacientes em serviço de emergência e casos de trauma. Métodos: Um dataset de 366,610 visitas em Hospital Universitário da Universidade Federal de São Paulo de 01 de janeiro de 2014 até 31 de dezembro de 2019 foi incluído no treinamento do modelo, incluindo visitas/dia e código internacional de doenças. O treinamento e predição foram realizados com o Amazon Forecast por dois oftalmologistas sem experiência com programação. Resultados: O período de previsão estimou um volume de 206,37 pacientes/dia em p90, 180,75 em p50, 140,35 em p10 e média de 7,42 casos de trauma/dia em p90, 3,99 em p50 e 0,56 em p10. Janeiro de 2020 teve um total de 6.604 pacientes e média de 206,37 pacientes/dia, 13,5% menos do que a predição em p50. O período teve um total de 199 casos de trauma e média de 6,21 casos/dia, 55,77% mais casos do que a predição em p50. Conclusão: O desenvolvimento de modelos era restrito a cientistas de dados com experiencia em programação, porém a transferência de ensino com a tecnologia de auto Machine Learning permite o desenvolvimento de algoritmos por qualquer pessoa sem experiencia em programação. Esse estudo mostra um modelo com valores preditos próximos ao que ocorreram em janeiro de 2020. Fatores que podem ter influenciados no resultado foram feriados e tamanho do banco de dados. Esse é o primeiro estudo que aplicada auto Machine Learning em predição de visitas hospitalares com resultados próximos aos que ocorreram.

Performance Evaluation of Geometrically Different Pediatric Arterial Cannulae in a Pediatric Cardiopulmonary Bypass Model

ABSTRACT Objective: To define a reference chart comparing pressure drop vs. flow generated by a set of arterial cannulae currently utilized in cardiopulmonary bypass conditions in pediatric surgery. Methods: Cannulae from two manufacturers were selected considering their design and outer and inner diameters. Cannula performance was evaluated in terms of pressure drop vs. flow during simulated cardiopulmonary bypass conditions. The experimental circuits consisted of a Jostra HL-20 roller pump, a Quadrox-i pediatric oxygenator (Maquet Cardiopulmonary AG, Rastatt, Germany), and a custom pediatric tubing set. The circuit was primed with lactated Ringer's solution only (first condition) and with human packed red blood cells added (second condition) to achieve a hematocrit of 30%. Cannula sizes 8 to 16 Fr were inserted into the cardiopulmonary bypass circuit with a "Y" connector. The flow was adjusted in 100 ml/min increments within typical flow ranges for each cannula. Pre-cannula and post-cannula pressures were measured to calculate the pressure drop. Results: Utilizing a pressure drop limit of 100 mmHg, our results suggest a recommended flow limit of 500, 900, 1400, 2600, and 3100 mL/min for Braile arterial cannulae sizes 8, 10, 12, 14, and 16 Fr, respectively. For Medtronic DLP arterial cannulae sizes 8, 10, 12, 14, and 16 Fr, the recommended flow limit is 600, 1100, 1700, 2700, and 3300 mL/min, respectively. Conclusion: This study reinforces discrepancies in pressure drop between cannulae of the same diameter supplied by different manufacturers and the importance of independent translational research to evaluate components' performance.

Predicting the Need for Blood Transfusions in Cardiac Surgery: A Comparison between Machine Learning Algorithms and Established Risk Scores in the Brazilian Population

ABSTRACT Introduction: Blood transfusion is a common practice in cardiac surgery, despite its well-known negative effects. To mitigate blood transfusion-associated risks, identifying patients who are at higher risk of needing this procedure is crucial. Widely used risk scores to predict the need for blood transfusions have yielded unsatisfactory results when validated for the Brazilian population. Methods: In this retrospective study, machine learning (ML) algorithms were compared to predict the need for blood transfusions in a cohort of 495 cardiac surgery patients treated at a Brazilian reference service between 2019 and 2021. The performance of the models was evaluated using various metrics, including the area under the curve (AUC), and compared to the commonly used Transfusion Risk and Clinical Knowledge (TRACK) and Transfusion Risk Understanding Scoring Tool (TRUST) scoring systems. Results: The study found that the model had the highest performance, achieving an AUC of 0.7350 (confidence interval [CI]: 0.7203 to 0.7497). Importantly, all ML algorithms performed significantly better than the commonly used TRACK and TRUST scoring systems. TRACK had an AUC of 0.6757 (CI: 0.6609 to 0.6906), while TRUST had an AUC of 0.6622 (CI: 0.6473 to 0.6906). Conclusion: The findings of this study suggest that ML algorithms may offer a more accurate prediction of the need for blood transfusions than the traditional scoring systems and could enhance the accuracy of predicting blood transfusion requirements in cardiac surgery patients. Further research could focus on optimizing and refining ML algorithms to improve their accuracy and make them more suitable for clinical use.

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.

Food patterns associated with overweight in 7-11-year old children: machine-learning approach / Padrões alimentares associados ao excesso de peso em crianças de 7 a 11 anos: abordagem de aprendizado de máquina

Abstract Longitudinal study, whose objective was to present a better strategy and statistical methods, and demonstrate its use with the data across the 2013-2015 period in schoolchildren aged 7 to 11 years, covered with the same food questionnaire (WebCAAFE) survey in Florianopolis, southern Brazil. Six meals/snacks and 32 foods/beverages yielded 192 possible combinations denominated meal/snack-Specific Food/beverage item (MSFIs). LASSO algorithm (LASSO-logistic regression) was used to determine the MSFIs predictive of overweight/obesity, and then binary (logistic) regression was used to further analyze a subset of these variables. Late breakfast, lunch and dinner were all associated with increased overweight/obesity risk, as was an anticipated lunch. Time-of-day or meal-tagged food/beverage intake result in large number of variables whose predictive patterns regarding weight status can be analyzed by machine learning such as LASSO, which in turn may identify the patterns not amenable to other popular statistical methods such as binary logistic regression.

Resumo Estudo longitudinal cujo objetivo foi apresentar melhores estratégia e métodos estatísticos e demonstrar sua utilização com os dados do período 2013-2015 em escolares de 7 a 11 anos, contemplados com o mesmo questionário alimentar (WebCAAFE) em Florianópolis, Sul do Brasil. Seis refeições/lanches e 32 alimentos/bebidas resultaram em 192 combinações possíveis denominadas item refeição/lanche-alimentos/bebidas específicos (MSFIs). O algoritmo LASSO (LASSO-regressão logística) foi usado para determinar os MSFIs preditivos de sobrepeso/obesidade e, em seguida, a regressão binária (logística) foi usada para analisar um subconjunto dessas variáveis. Café da manhã, almoço e jantar tardios foram todos associados ao aumento do risco de sobrepeso/obesidade, assim como um almoço antecipado. O consumo de alimentos/bebidas marcados na hora do dia ou na refeição resulta em um grande número de variáveis ​​cujos padrões preditivos em relação ao status do peso podem ser analisados ​​por LASSO. Essa análise pode identificar os padrões não passíveis de outros métodos estatísticos populares, como a regressão logística binária.

Noninvasive Diagnostic Technique for Nonalcoholic Fatty Liver Disease Based on Features of Tongue Images / 中国结合医学杂志

OBJECTIVE@#To investigate a new noninvasive diagnostic model for nonalcoholic fatty liver disease (NAFLD) based on features of tongue images.@*METHODS@#Healthy controls and volunteers confirmed to have NAFLD by liver ultrasound were recruited from China-Japan Friendship Hospital between September 2018 and May 2019, then the anthropometric indexes and sampled tongue images were measured. The tongue images were labeled by features, based on a brief protocol, without knowing any other clinical data, after a series of corrections and data cleaning. The algorithm was trained on images using labels and several anthropometric indexes for inputs, utilizing machine learning technology. Finally, a logistic regression algorithm and a decision tree model were constructed as 2 diagnostic models for NAFLD.@*RESULTS@#A total of 720 subjects were enrolled in this study, including 432 patients with NAFLD and 288 healthy volunteers. Of them, 482 were randomly allocated into the training set and 238 into the validation set. The diagnostic model based on logistic regression exhibited excellent performance: in validation set, it achieved an accuracy of 86.98%, sensitivity of 91.43%, and specificity of 80.61%; with an area under the curve (AUC) of 0.93 [95% confidence interval (CI) 0.68-0.98]. The decision tree model achieved an accuracy of 81.09%, sensitivity of 91.43%, and specificity of 66.33%; with an AUC of 0.89 (95% CI 0.66-0.92) in validation set.@*CONCLUSIONS@#The features of tongue images were associated with NAFLD. Both the 2 diagnostic models, which would be convenient, noninvasive, lightweight, rapid, and inexpensive technical references for early screening, can accurately distinguish NAFLD and are worth further study.

Comparison of the Recent Efficacy of Robot-assisted and Thoracic Laparoscopic Minimally Invasive Mckeown Radical Resection of Esophageal Cancer based on Propensity Score Matching / 中山大学学报(医学科学版)

ObjectiveTo explore the safety and efficacy of robot-assisted minimally invasive esophagectomy （robot-assisted minimally invasive esophagectomy， RAMIE） and thoracic laparoscopy combined with minimally invasive esophageal resection （minimal invasive esophagectomy， MIE）. MethodsThe data of 188 patients treated with Da Vinci robot assisted minimally invasive esophageal resection （RAMIE） from April 2021 to December 2022 were analyzed. In the RAMIE group， 69 patients， 49 males and 20 female， age （67.2 ± 7.2）； 119 in the MIME group， respectively， 89 males and 30 female， age （69.1 ± 7.0）. At 1 ∶ 1， including 58 patients in the RAMIE group and 58 patients in the MIE group. The t-test， Wilcoxon rank-sum test， χ2 test， and so on. ResultsAfter PSM treatment， the clinical data between the two groups. There was no significant difference in operation time， postoperative tube days， and total number of lymph node dissection between the RAMIE and MIE groups （P <0.05）； the RAMIE group was better in terms of intraoperative bleeding and the MIE group， statistically significant （P <0.05）； the MIE group was better in drainage flow and lymph node dissection for three days （P <0.05）. In terms of postoperative complications， there was no statistical difference between RAMIE and MIE groups （P>0.05）. ConclusionThe recent efficacy of robot-assisted minimally invasive esophagectomy is comparable to that of thoracic laparoscopy and minimally invasive Mckeown esophagectomy； robotic-assisted minimally invasive esophagectomy can reduce intraoperative bleeding and have more advantages in left recurrent laryngeal nerve lymph node dissection.

Research progress on cardiovascular hemodynamic assessment based on computational fluid dynamics / 中国胸心血管外科临床杂志

@#Hemodynamics plays a vital role in the development and progression of cardiovascular diseases, and is closely associated with changes in morphology and function. Reliable detection of hemodynamic changes is essential to improve treatment strategies and enhance patient prognosis. The combination of computational fluid dynamics with cardiovascular imaging technology has extended the accessibility of hemodynamics. This review provides a comprehensive summary of recent developments in the application of computational fluid dynamics for cardiovascular hemodynamic assessment and a succinct discussion for potential future development.

Association of polycyclic aromatic hydrocarbon metabolite concentration with sleep quality in workers / 环境与职业医学

Background Sleep is a crucial physiological activity for the human body, and research has shown that air pollution can affect sleep quality. However, the association between polycyclic aromatic hydrocarbons (PAHs) exposure, neurotoxic compounds in air pollutants, and sleep quality remains uncertain. Objective To evaluate the association of PAHs exposure with sleep quality, and to provide evidence for improving sleep quality. Methods This study used a cross-sectional design. We selected 632 workers from a coking plant of a large state-owned enterprise as the exposure group, and 477 workers from the energy and power plant of the same enterprise as the control group. All workers worked in three shifts. A questionnaire survey was conducted to collect basic information including gender, years of service, age, educational level, smoking, alcohol consumption, consumption of fried foods, cooking frequency, types of cooking fuels. Worker's post-shift morning midstream urine was sampled to determine the concentrations of eight PAHs metabolites (OH-PAHs) using gas chromatography-tandem mass spectrometry (GC-MS). Worker's sleep quality was assessed using Pittsburgh Sleep Quality Index (PSQI). A higher PSQI score indicated a lower sleep quality. Associations of urinary OH-PAHs levels with sleep quality in the workers were analyzed using linear regression, Bayesian kernel-machine regression (BKMR), and quantile g-computation. Results The median (P25, P75) concentration of total OH-PAHs in the exposure group [88.84 (46.27, 151.96) μg·L−1] was higher than that in the control group [54.33 (24.86, 97.97) μg·L−1]. Additionally, the PSQI score (\begin{document}$ \overline{x}\pm {s} $\end{document}) in the exposure group (5.16±3.84) was higher than that in the control group (4.60±3.17). The multiple linear regression revealed that an increase in the sum of the concentrations of eight OH-PAHs after natural logarithmic transformation (lnΣ8OH-PAHs) was associated with an increase of 0.3646 (95%CI: 0.1337, 0.5955) in PSQI score, and an increase in lnΣlow-ring OH-PAHs was associated with an increase of 0.2954 (95%CI: 0.0941, 0.4967) in PSQI score. The BKMR analysis demonstrated that PSQI score was gradually increased as the increasing of lnΣ8OH-PAHs concentration. The quantile g-computation analysis indicated that a quantile increase in lnΣ8OH-PAHs concentration was associated with an increase of 0.4062% (95%CI: 0.1176%, 0.6949%) in PSQI score. Conclusion Compared to the controls, the coking workers show a higher concentration of urinary OH-PAHs and report worse sleep quality. The concentration of OH-PAHs is significantly negatively associated with sleep quality.

Association between exposure to multiple metals and lung function in welders by multi-pollutant statistical models / 环境与职业医学

Background Welders' exposure to welding fumes with multiple metals leads to decreased pulmonary function. Previous studies have focused on single metal exposure, while giving little attention to the impact of metal mixtures. Objective To assess the association between metal levels in urine and blood of welders and pulmonary function indicators, and to identify key metals for occupational health risk assessment. Methods Questionnaire surveys, lung function tests, urine and blood sampling were conducted among welders and control workers in a shipyard in Shanghai. Inductively coupled plasma mass spectrometry (ICP-MS) was used to detect the concentrations of 12 metals such as vanadium, chromium, and manganese in urine and blood. Spearman correlation was applied to analyze the correlations between the metals in urine and blood. Multiple linear regression, weighted quantile sum (WQS) and Bayesian kernel machine regression (BKMR) were used to analyze the relationships between mixed metal exposure and pulmonary function parameters, such as forced vital capacity (FVC), forced vital capacity as a percentage of predicted value (FVC%), forced expiratory volume in the first second (FEV1), forced expiratory volume in the first second as a percentage of predicted value (FEV1%), and forced expiratory volume in the first second/forced vital capacity (FEV1/FVC). Results This study enrolled 445 subjects, including 322 welders (72.36%) and 123 controls (27.64%). The mean age of the 445 participants was (37.64±8.80) years, and 87.19% participants were male. The welders had significantly higher levels of urinary cadmium (0.88 vs 0.58 μg·L−1), blood chromium (5.86 vs 5.06 μg·L−1), and blood manganese (24.24 vs 21.38 μg·L−1) than the controls (P<0.05). The Spearman correlation coefficients between the metals in urine and blood ranged from −0.46 to 0.68. After adjustment for confounders, the multiple linear regression indicted that the urine molybdenum of the welders was negatively correlated with FVC and FEV1. There were also negative correlations between the molybdenum in blood and FVC, FVC%, FEV1, and FEV1%, and between the copper in blood and FEV1/FVC. The WQS model showed that FEV1 and FVC decreased by 0.112 L and 0.353 L with each quartile increase of metal mixture concentrations in urine and blood among the welders respectively, and the leading contributors were copper, zinc, vanadium, and antimony. The BKMR model showed a negative overall effect of metal mixtures in urine and blood among the welders on FVC, FVC%, FEV1, and FEV1%, and the univariate exposure response-relationship between the molybdenum concentration in urine or blood and FVC, FVC%, FEV1, or FEV1% had an approximately linear decreasing trend. Meanwhile, there may be an interaction of cadmium with manganese, nickel, or vanadium, and an interaction of vanadium with iron, molybdenum, zinc, or copper, when different metals in urine among the welders interacted with FEV1%. Conclusion Exposure to multiple metals in welders leads to a decline in lung function, with molybdenum, antimony, copper, and zinc as the leading contributors.

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.

Correlation between Combined Urinary Metal Exposure and Grip Strength under Three Statistical Models: A Cross-sectional Study in Rural Guangxi / 生物医学与环境科学（英文）

OBJECTIVE@#This study aimed to investigate the potential relationship between urinary metals copper (Cu), arsenic (As), strontium (Sr), barium (Ba), iron (Fe), lead (Pb) and manganese (Mn) and grip strength.@*METHODS@#We used linear regression models, quantile g-computation and Bayesian kernel machine regression (BKMR) to assess the relationship between metals and grip strength.@*RESULTS@#In the multimetal linear regression, Cu (β = -2.119), As (β = -1.318), Sr (β = -2.480), Ba (β = 0.781), Fe (β = 1.130) and Mn (β = -0.404) were significantly correlated with grip strength ( P < 0.05). The results of the quantile g-computation showed that the risk of occurrence of grip strength reduction was -1.007 (95% confidence interval: -1.362, -0.652; P < 0.001) when each quartile of the mixture of the seven metals was increased. Bayesian kernel function regression model analysis showed that mixtures of the seven metals had a negative overall effect on grip strength, with Cu, As and Sr being negatively associated with grip strength levels. In the total population, potential interactions were observed between As and Mn and between Cu and Mn ( P interactions of 0.003 and 0.018, respectively).@*CONCLUSION@#In summary, this study suggests that combined exposure to metal mixtures is negatively associated with grip strength. Cu, Sr and As were negatively correlated with grip strength levels, and there were potential interactions between As and Mn and between Cu and Mn.

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.