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.

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.

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.

Construction of a machine learning model for identifying clinical high-risk carotid plaques based on radiomics / 中国胸心血管外科临床杂志

@#Objective     To construct a radiomics model for identifying clinical high-risk carotid plaques. Methods     A retrospective analysis was conducted on patients with carotid artery stenosis in China-Japan Friendship Hospital from December 2016 to June 2022. The patients were classified as a clinical high-risk carotid plaque group and a clinical low-risk carotid plaque group according to the occurrence of stroke, transient ischemic attack and other cerebrovascular clinical symptoms within six months. Six machine learning models including eXtreme Gradient Boosting, support vector machine, Gaussian Naive Bayesian, logical regression, K-nearest neighbors and artificial neural network were established. We also constructed a joint predictive model combined with logistic regression analysis of clinical risk factors. Results    Finally 652 patients were collected, including 427 males and 225 females, with an average age of 68.2 years. The results showed that the prediction ability of eXtreme Gradient Boosting was the best among the six machine learning models, and the area under the curve (AUC) in validation dataset was 0.751. At the same time, the AUC of eXtreme Gradient Boosting joint prediction model established by clinical data and carotid artery imaging data validation dataset was 0.823. Conclusion     Radiomics features combined with clinical feature model can effectively identify clinical high-risk carotid plaques.

Development and prospects of predicting drug polymorphs technology / 药学学报

Most chemical medicines have polymorphs. The difference of medicine polymorphs in physicochemical properties directly affects the stability, efficacy, and safety of solid medicine products. Polymorphs is incomparably important to pharmaceutical chemistry, manufacturing, and control. Meantime polymorphs is a key factor for the quality of high-end drug and formulations. Polymorph prediction technology can effectively guide screening of trial experiments, and reduce the risk of missing stable crystal form in the traditional experiment. Polymorph prediction technology was firstly based on theoretical calculations such as quantum mechanics and computational chemistry, and then was developed by the key technology of machine learning using the artificial intelligence. Nowadays, the popular trend is to combine the advantages of theoretical calculation and machine learning to jointly predict crystal structure. Recently, predicting medicine polymorphs has still been a challenging problem. It is expected to learn from and integrate existing technologies to predict medicine polymorphs more accurately and efficiently.

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.

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.

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.

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.

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.

Herramientas de corte para optimizar parámetros de clasificación de especies maderables con redes neuronales convolucionales / Cutting tools to optimize classification parameters of timber species with convolutional neural networks

Introducción: La gran diversidad de especies maderables tropicales demanda el desarrollo de nuevas tecnologías de identificación con base en sus patrones o características anatómicas. La aplicación de redes neuronales convolucionales (CNN) para el reconocimiento de especies maderables tropicales se ha incrementado en los últimos años por sus resultados prometedores. Objetivo: Evaluamos la calidad de las imágenes macroscópicas con tres herramientas de corte para mejorar la visualización y distinción de las características anatómicas en el entrenamiento del modelo CNN. Métodos: Recolectamos las muestras entre el 2020 y 2021 en áreas de explotación forestal y aserraderos de Selva Central, Perú. Luego, las dimensionamos y, previo a la identificación botánica y anatómica, las cortamos en secciones transversales. Generamos una base de datos de imágenes macroscópicas de la sección transversal de la madera, a través del corte, con tres herramientas para ver su rendimiento en el laboratorio, campo y puesto de control. Resultados: Usamos tres herramientas de corte para obtener una alta calidad de imágenes transversales de la madera; obtuvimos 3 750 imágenes macroscópicas con un microscopio portátil que corresponden a 25 especies maderables. El cuchillo ''Tramontina'' es duradero, pero pierde el filo con facilidad y se necesita una herramienta para afilar, el cúter retráctil ''Pretul'' es adecuado para madera suave y dura en muestras pequeñas de laboratorio; el cuchillo ''Ubermann'' es apropiado para el campo, laboratorio y puesto de control, porque tiene una envoltura duradera y láminas intercambiables en caso de pérdida de filo. Conclusiones: La calidad de las imágenes es decisiva en la clasificación de especies maderables, porque permite una mejor visualización y distinción de las características anatómicas en el entrenamiento con los modelos de red neuronal convolucional EfficientNet B0 y Custom Vision, lo cual se evidenció en las métricas de precisión.

Introduction: The great diversity of tropical timber species demands the development of new technologies capable of identifying them based on their patterns or anatomical characteristics. The application of convolutional neural networks (CNN) for the recognition of tropical timber species has increased in recent years due to the promising results of CNNs. Objective: To evaluate the quality of macroscopic images with three cutting tools to improve the visualization and distinction of anatomical features in the CNN model training. Methods: Samples were collected from 2020 to 2021 in areas of logging and sawmills in the Central Jungle, Peru. They were later sized and, after botanical and anatomical identification, cut in cross sections. A database of macroscopic images of the cross-section of wood was generated through cutting with three different tools and observing its performance in the laboratory, field, and checkpoint. Results: Using three cutting tools, we obtained high quality images of the cross section of wood; 3 750 macroscopic images were obtained with a portable microscope and correspond to 25 timber species. We found the ''Tramontina'' knife to be durable, however, it loses its edge easily and requires a sharpening tool, the ''Pretul'' retractable cutter is suitable for cutting soft and hard wood in small laboratory samples and finally the ''Ubermann'' knife is suitable for use in the field, laboratory, and checkpoint, because it has a durable sheath and interchangeable blades in case of dullness. Conclusion: The quality of the images is decisive in the classification of timber species, because it allows a better visualization and distinction of the anatomical characteristics in training with the EfficientNet B0 and Custom Vision convolutional neural network models, which was evidenced in the precision metrics.

Métodos de aprendizaje automático para predecir el comportamiento epidemiológico de enfermedades arbovirales: revisión estructurada de literatura / Machine learning methods to predict epidemiological behavior of arbovirals diseases: structured literature review

Introducción: Los métodos de aprendizaje automático permiten manejar datos estructurados y no estructurados para construir modelos predictivos y apoyar la toma de decisiones. Objetivo: Identificar los métodos de aprendizaje automático aplicados para predecir el comportamiento epidemiológico de enfermedades arbovirales utilizando datos de vigilancia epidemiológica. Metodología: Se realizó búsqueda en EMBASE y PubMed, análisis bibliométrico y síntesis de la información. Resultados: Se seleccionaron 41 documentos, todos publicados en la última década. La palabra clave más frecuente fue dengue. La mayoría de los autores (88,3 %) participó en un artículo de investigación. Se encontraron 16 métodos de aprendizaje automático, el más frecuente fue Red Neuronal Artificial, seguido de Máquinas de Vectores de Soporte. Conclusiones: En la última década se incrementó la publicación de trabajos que pretenden predecir el comportamiento epidemiológico de arbovirosis por medio de diversos métodos de aprendizaje automático que incorporan series de tiempo de los casos, variables climatológicas, y otras fuentes de información de datos abiertos.

Introduction: Machine learning methods allow to manipulate structured and unstructured data to build predictive models and support decision-making. Objective: To identify machine learning methods applied to predict the epidemiological behavior of vector-borne diseases using epidemiological surveillance data. Methodology: A literature search in EMBASE and PubMed, bibliometric analysis, and information synthesis were performed. Results: A total of 41 papers were selected, all of them were published in the last decade. The most frequent keyword was dengue. Most authors (88.3 %) participated in a research article. Sixteen machine learning methods were found, the most frequent being Artificial Neural Network, followed by Support Vector Machines. Conclusions: In the last decade there has been an increase in the number of articles that aim to predict the epidemiological behavior of vector-borne diseases using by means of various machine learning methods that incorporate time series of cases, climatological variables, and other sources of open data information.

Advances in diffuse glial tumors diagnosis / Avanços no diagnóstico dos gliomas difusos

Abstract In recent decades, there have been significant advances in the diagnosis of diffuse gliomas, driven by the integration of novel technologies. These advancements have deepened our understanding of tumor oncogenesis, enabling a more refined stratification of the biological behavior of these neoplasms. This progress culminated in the fifth edition of the WHO classification of central nervous system (CNS) tumors in 2021. This comprehensive review article aims to elucidate these advances within a multidisciplinary framework, contextualized within the backdrop of the new classification. This article will explore morphologic pathology and molecular/genetics techniques (immunohistochemistry, genetic sequencing, and methylation profiling), which are pivotal in diagnosis, besides the correlation of structural neuroimaging radiophenotypes to pathology and genetics. It briefly reviews the usefulness of tractography and functional neuroimaging in surgical planning. Additionally, the article addresses the value of other functional imaging techniques such as perfusion MRI, spectroscopy, and nuclear medicine in distinguishing tumor progression from treatment-related changes. Furthermore, it discusses the advantages of evolving diagnostic techniques in classifying these tumors, as well as their limitations in terms of availability and utilization. Moreover, the expanding domains of data processing, artificial intelligence, radiomics, and radiogenomics hold great promise and may soon exert a substantial influence on glioma diagnosis. These innovative technologies have the potential to revolutionize our approach to these tumors. Ultimately, this review underscores the fundamental importance of multidisciplinary collaboration in employing recent diagnostic advancements, thereby hoping to translate them into improved quality of life and extended survival for glioma patients.

Resumo Nas últimas décadas, houve avanços significativos no diagnóstico de gliomas difusos, impulsionados pela integração de novas tecnologias. Esses avanços aprofundaram nossa compreensão da oncogênese tumoral, permitindo uma estratificação mais refinada do comportamento biológico dessas neoplasias. Esse progresso culminou na quinta edição da classificação da OMS de tumores do sistema nervoso central (SNC) em 2021. Esta revisão abrangente tem como objetivo elucidar esses avanços de forma multidisciplinar, no contexto da nova classificação. Este artigo irá explorar a patologia morfológica e as técnicas moleculares/genéticas (imuno-histoquímica, sequenciamento genético e perfil de metilação), que são fundamentais no diagnóstico, além da correlação dos radiofenótipos da neuroimagem estrutural com a patologia e a genética. Aborda sucintamente a utilidade da tractografia e da neuroimagem funcional no planejamento cirúrgico. Destacaremos o valor de outras técnicas de imagem funcional, como ressonância magnética de perfusão, espectroscopia e medicina nuclear, na distinção entre a progressão do tumor e as alterações relacionadas ao tratamento. Discutiremos as vantagens das diferentes técnicas de diagnóstico na classificação desses tumores, bem como suas limitações em termos de disponibilidade e utilização. Além disso, os crescentes avanços no processamento de dados, inteligência artificial, radiômica e radiogenômica têm grande potencial e podem em breve exercer uma influência substancial no diagnóstico de gliomas. Essas tecnologias inovadoras têm o potencial de revolucionar nossa abordagem a esses tumores. Em última análise, esta revisão destaca a importância fundamental da colaboração multidisciplinar na utilização dos recentes avanços diagnósticos, com a esperança de traduzi-los em uma melhor qualidade de vida e uma maior sobrevida.

Desarrollo de un modelo por inteligencia artificial con hemodinamia no invasiva para predecir preeclampsia en embarazos de alto riesgo / Artificial Intelligence Modeling with Non-Invasive Hemodynamics to Predict Preeclampsia in High-Risk Pregnancy

RESUMEN Introducción: la preeclampsia (PE) es la principal causa de morbimortalidad materno-fetal en nuestro país. Alteraciones hemodinámicas precoces durante el embarazo podrían predecir la evolución a PE. El machine learning (ML) permite el hallazgo de patrones ocultos que podrían detectar precozmente el desarrollo de PE. Objetivos: desarrollar un árbol de clasificación con variables de hemodinamia no invasiva para predecir precozmente desarrollo de PE. Material y métodos: estudio observacional prospectivo con embarazadas de alto riesgo (n=1155) derivadas del servicio de Obstetricia desde enero 2016 a octubre 2022 para el muestreo de entrenamiento por ML con árbol de clasificación j48. Se seleccionaron 112 embarazadas entre semanas 10 a 16, sin tratamiento farmacológico y que completaron el seguimiento con el término de su embarazo con evento final combinado (PE): preeclampsia, eclampsia y síndrome HELLP. Se evaluaron simultáneamente con cardiografía de impedancia y velocidad de onda del pulso y con monitoreo ambulatorio de presión arterial de 24 hs (MAPA). Resultados: presentaron PE 17 pacientes (15,18%). Se generó un árbol de clasificación predictivo con las siguientes variables: índice de complacencia arterial (ICA), índice cardíaco (IC), índice de trabajo sistólico (ITS), cociente de tiempos eyectivos (CTE), índice de Heather (IH). Se clasificaron correctamente el 93,75%; coeficiente Kappa 0,70, valor predictivo positivo (VPP) 0,94 y negativo (VPN) 0,35. Precisión 0,94, área bajo la curva ROC 0,93. Conclusión: las variables ICA, IC, ITS, CTE e IH predijeron en nuestra muestra el desarrollo de PE con excelente discriminación y precisión, de forma precoz, no invasiva, segura y con bajo costo.

ABSTRACT Background: Preeclampsia (PE) is the main cause of maternal-fetal morbidity and mortality in our country. Early hemodynamic changes during pregnancy could predict progression to PE. Machine learning (ML) enables the discovery of hidden patterns that could early detect PE development. Objectives: The aim of this study was to build a classification tree with non-invasive hemodynamic variables for the early prediction of PE occurrence. Results: Seventeen patients (15.18%) presented PE. A predictive classification tree was generated with arterial compliance index (ACI), cardiac index (CI), cardiac work index (CWI), ejective time ratio (ETR), and Heather index (HI). A total of 93.75% patients were correctly classified (Kappa 0.70, positive predictive value 0.94 and negative predictive value 0.35; accuracy 0.94, and area under the ROC curve 0.93). Conclusion: ACI, CI, CWI, ETR and HI variables predicted the early development of PE in our sample with excellent discrimination and accuracy, non-invasively, safely and at low cost.

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.