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.

Inteligencia artificial en enfermedades infecciosas / Artificial intelligence in infectious diseases

Estamos asistiendo a una verdadera revolución tecnológi-ca en el campo de la salud. Los procesos basados en la aplicación de la inteligencia artificial (IA) y el aprendizaje automático (AA) están llegando progresivamente a todas las áreas disciplinares, y su aplicación en el campo de las enfermedades infecciosas es ya vertiginoso, acelerado por la pandemia de COVID-19.Hoy disponemos de herramientas que no solamente pue-den asistir o llevar adelante el proceso de toma de deci-siones basadas en guías o algoritmos, sino que también pueden modificar su desempeño a partir de los procesos previamente realizados. Desde la optimización en la identificación de microorganis-mos resistentes, la selección de candidatos a participar en ensayos clínicos, la búsqueda de nuevos agentes terapéu-ticos antimicrobianos, el desarrollo de nuevas vacunas, la predicción de futuras epidemias y pandemias, y el segui-miento clínico de pacientes con enfermedades infecciosas hasta la asignación de recursos en el curso de manejo de un brote son actividades que hoy ya pueden valerse de la inteligencia artificial para obtener un mejor resultado. El desarrollo de la IA tiene un potencial de aplicación expo-nencial y sin dudas será uno de los determinantes principa-les que moldearán la actividad médica del futuro cercano.Sin embargo, la maduración de esta tecnología, necesaria para su inserción definitiva en las actividades cotidianas del cuidado de la salud, requiere la definición de paráme-tros de referencia, sistemas de validación y lineamientos regulatorios que todavía no existen o son aún solo inci-pientes

We are in the midst of a true technological revolution in healthcare. Processes based upon artificial intelligence and machine learning are progressively touching all disciplinary areas, and its implementation in the field of infectious diseases is astonishing, accelerated by the COVID-19 pandemic. Today we have tools that can not only assist or carry on decision-making processes based upon guidelines or algorithms, but also modify its performance from the previously completed tasks. From optimization of the identification of resistant pathogens, selection of candidates for participating in clinical trials, the search of new antimicrobial therapeutic agents, the development of new vaccines, the prediction of future epidemics and pandemics, the clinical follow up of patients suffering infectious diseases up to the resource allocation in the management of an outbreak, are all current activities that can apply artificial intelligence in order to improve their final outcomes.This development has an exponential possibility of application, and is undoubtedly one of the main determinants that will shape medical activity in the future.Notwithstanding the maturation of this technology that is required for its definitive insertion in day-to-day healthcare activities, should be accompanied by definition of reference parameters, validation systems and regulatory guidelines that do not exist yet or are still in its initial stages

Sex Determination by the Machine Learning Algorithms Through Using Morphometric Measurements of the Carpal, Metacarpal, and Phalangeal Bones / Determinación del Sexo Mediante Algoritmos de Aprendizaje Automático Mediante el Uso de Mediciones Morfométricas de los Huesos del Carpo, el Metacarpo y las Falanges

SUMMARY: In the study, it was aimed to predict sex from hand measurements using machine learning algorithms (MLA). Measurements were made on MR images of 60 men and 60 women. Determined parameters; hand length (HL), palm length (PL), hand width (HW), wrist width (EBG), metacarpal I length (MIL), metacarpal I width (MIW), metacarpal II length (MIIL), metacarpal II width (MIIW), metacarpal III length (MIIL), metacarpal III width (MIIIW), metacarpal IV length (MIVL), metacarpal IV width (MIVW), metacarpal V length (MVL), metacarpal V width (MVW), phalanx I length (PILL), measured as phalanx II length (PIIL), phalanx III length (PIIL), phalanx IV length (PIVL), phalanx V length (PVL). In addition, the hand index (HI) was calculated. Logistic Regression (LR), Random Forest (RF), Linear Discriminant Analysis (LDA), K-nearest neighbour (KNN) and Naive Bayes (NB) were used as MLAs. In the study, the KNN algorithm's Accuracy, SEN, F1 and Specificity ratios were determined as 88 %. In this study using MLA, it is understood that the highest accuracy belongs to the KNN algorithm. Except for the hand's MIIW, MIIIW, MIVW, MVW, HI variables, other variables were statistically significant in terms of sex difference.

En el estudio, el objetivo era predecir el sexo a partir de mediciones manuales utilizando algoritmos de aprendizaje automático (MLA). Las mediciones se realizaron en imágenes de RM de 60 hombres y 60 mujeres. Parámetros determinados; longitud de la mano (HL), longitud de la palma (PL), ancho de la mano (HW), ancho de la muñeca (EBG), longitud del metacarpiano I (MIL), ancho del metacarpiano I (MIW), longitud del metacarpiano II (MIIL), ancho del metacarpiano II (MIIW), longitud del metacarpiano III (MIIL), ancho del metacarpiano III (MIIIW), longitud del metacarpiano IV (MIVL), ancho del metacarpiano IV (MIVW), longitud del metacarpiano V (MVL), ancho del metacarpiano V (MVW), longitud de la falange I (PILL), medido como longitud de la falange II (PIIL), longitud de la falange III (PIIL), longitud de la falange IV (PIVL), longitud de la falange V (PVL). Además, se calculó el índice de la mano (HI). Regresión logística (LR), Random Forest (RF), Análisis discriminante lineal (LDA), K-vecino más cercano (KNN) y Naive Bayes (NB) se utilizaron como MLA. En el estudio, las proporciones de precisión, SEN, F1 y especificidad del algoritmo KNN se determinaron en un 88 %. En este estudio que utiliza MLA, se entiende que la mayor precisión pertenece al algoritmo KNN. Excepto por las variables MIIW, MIIIW, MIVW, MVW, HI de la mano, otras variables fueron estadísticamente significativas en términos de diferencia de sexo.

Chat GPT: origen, evolución, retos e impactos en la educación / Chat GPT: Origen, Evolution, Challenges and Impacts on Education

Introducción: Los avances de unas tecnologías y la obsolescencia de otras marchan a una velocidad inimaginable, especialmente en este siglo xxi. En los últimos meses de 2022 y primeros meses de 2023 muchas incógnitas y controversias en diferentes campos han surgido en torno a los Chat GPS, una innovación que presenta desafíos nunca pensados para la sociedad actual, así como nuevos retos que impactarán de manera directa en la formación y/o desempeño de profesores, estudiantes, profesionales de la salud, juristas, políticos, informáticos, bibliotecarios, científicos y cualquier ciudadano. Objetivo: Identificar algunas características del chat GPT y su posible impacto en el educación. Posicionamiento de los autores: Se leen en las noticias y reportajes valoraciones de especialistas; se han realizado encuentros virtuales y exposiciones; y están disponibles diversos artículos y videos sobre este tema, algunos llegan a ser elaborados con el propio asistente. Por la novedad del tema, la reciente incorporación como herramienta para el desarrollo profesional, así como por el interés mostrado en los últimos días por la comunidad de profesores de las ciencias médicas cubanas, y considerando que esta herramienta es resultado del desarrollo de la inteligencia artificial, cabe preguntarse: ¿en qué consiste? y ¿cuáles son sus perspectivas? Conclusiones: Resulta oportuno acercarse al tema desde las posibilidades y los retos que abre a la educación y el aprendizaje, en particular a la docencia médica(AU)

Introduction: The advances of some technologies and the obsolescence of others are marching at an unimaginable speed, especially in this twenty-first century. In the last months of 2022 and first months of 2023, many questions and controversies in different fields have arisen with respect to Chat GPT, an innovation that presents challenges never thought of before for today's society, as well as new challenges that will have a direct impact on the training and/or performance of professors, students, health professionals, law practitioners, politicians, computer scientists, librarians, scientists and any citizen. Objective: To identify some technological characteristics of Chat GPT. Positioning of the authors: In news and reports, assessments by specialists are read; virtual meetings and presentations have been held; and several articles and videos on this topic are available, some of them even elaborated by the assistant itself. Due to the novelty of the subject, its recent assimilation as a tool for professional development, as well as the interest shown in recent days by the community of professors of Cuban medical sciences and considering that this tool is the result of the development of artificial intelligence, it is worth wondering what it consists in and what its prospects are. Conclusions: It is appropriate to approach the subject with a focus on the possibilities and challenges that it opens to education and learning (AU)

Crista Galli Morphometry and Morphology: An Anatomical, Radiological, and Machine Learning Application Study / Crista Galli Morfometría y Morfología: Un Estudio de Aplicación Anatómica, Radiológica y de Aprendizaje Automático

SUMMARY: The study purposed to examine the morphometry and morphology of crista galli in cone beam computed tomography (CBCT) and apply a new analysis, supervised Machine Learning techniques to find the answers to research questions "Can sex be determined with crista galli morphometric measurements?" or "How effective are the crista galli morphometric measurements in determining sex?". Crista galli dimensions including anteroposterior, superoinferior, and laterolateral were measured and carried out on 200 healthy adult subjects (98 females; 102 males) aged between 18-79 years. Also, crista galli was classified with two methods called morphological types and Keros classification. In this study, the Chi-square test, Student's t-test, and Oneway ANOVA were performed. Additionally, Machine Learning techniques were applied. The means of the CGH, CGW, and CGL were found as 14.96 mm; 3.96 mm, and 12.76 mm in males, respectively. The same values were as 13.54 mm; 3.51 mm and 11.59±1.61 mm in females, respectively. The CG morphometric measurements of males were higher than those of females. There was a significant difference between sexes in terms of morphological classification type. Also, when the sex assignment of JRip was analyzed, out of 102 male instances 62 of them were correctly predicted, and for 98 female instances, 70 of them were correctly predicted according to their CG measurements. The JRip found the following classification rule for the given dataset: "if CGH<=14.4 then sex is female, otherwise sex is male". The accuracy of this rule is not high, but it gives an idea about the relationship between CG measurements and sex. Although the issue that CG morphometric measurements can be used in sex determination is still controversial, it was concluded in the analysis that CG morphometric measurements can be used in sex determination. Also, Machine Learning Techniques give an idea about the relationship between CG measurements and sex.

En el estudio se propuso examinar la morfometría y la morfología de la crista galli del hueso etmoides usando tomografía computarizada de haz cónico (CBCT) y aplicar un nuevo análisis, técnicas de aprendizaje automático supervisado para encontrar las respuestas a las preguntas de investigación "¿Se puede determinar el sexo con mediciones morfométricas de la crista galli?" o "¿Qué tan efectivas son las medidas morfométricas de la crista galli para determinar el sexo?". Las dimensiones de la crista galli, incluidas los diámetros anteroposterior, superoinferior y laterolateral, se midieron y realizaron en 200 sujetos adultos sanos (98 mujeres; 102 hombres) con edades comprendidas entre los 18 y los 79 años. La crista galli se clasificó con dos métodos llamados tipos morfológicos y clasificación de Keros. En este estudio, se realizaron la prueba de Chicuadrado, la prueba t de Student y ANOVA de una vía. Adicionalmente, se aplicaron técnicas de Machine Learning. Las medias de CGH, CGW y CGL se encontraron en 14,96 mm; 3,96 mm y 12,76 mm en hombres, respectivamente. Los mismos valores fueron 13,54 mm; 3,51 mm y 11,59 ± 1,61 mm en mujeres, respectivamente. Las medidas morfométricas del CG de los hombress fueron más altas que las de las mujeres. Hubo una diferencia significativa entre sexos en cuanto al tipo de clasificación morfológica. Además, cuando se analizó la asignación de sexo de JRip, de 102 instancias masculinas, 62 de ellas se predijeron correctamente, y de 98 instancias femeninas, 70 de ellas se predijeron correctamente de acuerdo con las mediciones de CG. El JRip encontró la siguiente regla de clasificación para el conjunto de datos dado: "si CGH<=14.4, por tanto el sexo es femenino, de lo contrario, el sexo es masculino". La precisión de esta regla no es alta, pero da una idea de la relación entre las medidas del CG y el sexo. Aunque la pregunta si las medidas morfométricas CG se pueden usar en la determinación del sexo sigue aún siendo controvertida. Se concluyó en el análisis que las medidas morfométricas CG se pueden usar en la determinación del sexo. Además, las técnicas de aprendizaje automático dan una idea de la relación entre las medidas de CG y el sexo.

Aprendizado de máquina nos serviços farmacêuticos: uma revisão integrativa / Machine learning in pharmaceutical services: an integrative review

A crescente digitalização e aplicação de inteligência artificial (IA) em problemas complexos do mundo real, tem potencial de melhorar os serviços de saúde, inclusive da atuação dos farmacêuticos no processo do cuidado. O objetivo deste estudo foi identificar na literatura científica, estudos que testam algoritmos de aprendizado de máquina (Machine Learning ­ ML) aplicados as atividades de farmacêuticos clínicos no cuidado ao paciente. Trata-se de uma revisão integrativa, realizada nas bases de dados, Pubmed, Portal BVS, Cochrane Library e Embase. Artigos originais, relacionados ao objetivo proposto, disponíveis e publicados antes de 31 de dezembro de 2021, foram incluídos, sem limitações de idioma. Foram encontrados 831 artigos, sendo 5 incluídos relacionados as atividades inseridas nos serviços de revisão da farmacoterapia (3) e monitorização terapêutica (2). Foram utilizadas técnicas supervisionadas (3) e não supervisionadas (2) de ML, com variedade de algoritmos testados, sendo todos os estudos publicados recentemente (2019-2021). Conclui-se que a aplicação da IA na farmácia clínica, ainda é discreta, sinalizando os desafios da era digital.

The growing application of artificial intelligence (AI) in complex real-world problems has shown an enormous potential to improve health services, including the role of pharmacists in the care process. Thus, the objective of this study was to identify, in the scientific literature, studies that addressed the use of machine learning (ML) algorithms applied to the activities of clinical pharmacists in patient care. This is an integrative review, conducted in the databases Pubmed, VHL Regional Portal, Cochrane Library and Embase. Original articles, related to the proposed topic, which were available and published before December 31, 2021, were included, without language limitations. There were 831 articles retrieved 5 of which were related to activities included in the pharmacotherapy review services (3) and therapeutic monitoring (2). Supervised (3) and unsupervised (2) ML techniques were used, with a variety of algorithms tested, with all studies published recently (2019­2021). It is concluded that the application of AI in clinical pharmacy is still discreet, signaling the challenges of the digital age.

Análise da generalização de algoritmos de machine learning e suas aplicações na otimização de decisões em saúde / Generalization analysis of machine learning algorithms and their applications in optimizing health decisions

A utilização de algoritmos de inteligência artificial tem crescido rapidamente nos últimos anos, aumentando o seu potencial de aplicação em saúde pública. Algoritmos de machine learning (ML) são capazes de auxiliar na predição de desfechos complexos e na tornada de decisões por parte dos profissionais da área. da. saúde. Esta tese tem como objetivo analisar a capacidade de generalização dos algoritmos na área da saúde e aplicar modelos de ML para predições utilizando dados tabulares frequentemente coletados nos sistemas de saúde. A tese será defendida sob a forma de três artigos científicos. O primeiro artigo realizou uma revisão sistemática da literatura sobre a capacidade de generalização de modelos de ML em saúde. Os resultados indicaram que, apesar de ainda limitada, a literatura sobre generalização em saúde está crescendo nos últimos anos em parte como uma demanda das próprias revistas científicas. O segundo artigo desenvolveu e avaliou a performance da validação externa de um algoritmo de ML no contexto da predição de risco de mortalidade neonatal. O modelo foi desenvolvido utilizando Extreme Gradient Boosting (XGB) em dados de São Paulo de 2012 a 2015, incluindo 807.932 nascidos vivos e 5.518 óbitos neonatais. Foi realizada a validação externa do algoritmo em 1.161 municípios brasileiros, incluindo todas as capitais de estado para o ano ele 2016, totalizando 2.848.052 nascidos vivos e 23.948 óbitos neonatais. Os resultados mostraram que os municípios que ofertam estruturas de maior complexidade obtiveram uma performance similar ou mesmo superior ao modelo base desenvolvido com dados do município de São Paulo. No terceiro e último artigo desta tese, foi realizada uma análise da aplicação da técnica de generalização conhecida como transfer learning nos dados da Rede IACOV-BR para predizer óbito entre pacientes internados por Covid-19 usando dados de prontuário de 16.236 pacientes de 18 hospitais brasileiros coletados no primeiro trimestre de 2020 durante o início da pandemia de Covid-19 no Brasil. A abordagem desse artigo propôs uma comparação entre uma nova solução capaz de predizer o progresso clínico dos pacientes com Covid- 19 versus a abordagem já aplicada para predições tabulares em saúde. Os resultados indicam que apesar de promissora, a técnica de transfer learning convencional não se mostrou superior aos resultados de performance obtidos localmente com os algoritmos de boosting utilizados para dados tabulares. Os resultados desta tese apontam para a importância da generalização dos algoritmos de i\IL em saúde, ao mesmo tempo que os desafios técnicos ainda persistem em relação à manutenção da performance preditiva nas diferentes localidades.

The use of artificial intelligence algorithms has significantly increased in recent years, increasing their potential for application in public health. ML algorithms (ML) can assist in the prediction of complex outcomes and in decision-making by healthcare professionals. This thesis aims to analyze the algorithmic generalization capability in healthcare and apply ML models for the prediction of health outcomes from tabular data frequently collected in healthcare systems. The thesis will be defended as three scientific articles. The first article conducted a systematic literature review on the generalization capability of ML models in healthcare. The results indicated that, although still limited, the literature on generalization in healthcare has been growing in recent years, in part as demand from journals themselves. The second article evaluated the performance of external validation of an ML algorithm in the context of predicting neonatal mortality risk. The model was developed using Extreme Gradient Boosting (XGB) on São Paulo data from 2012 to 2015, including 807,932 live births and 5,518 neonatal deaths. External validation of the algorithm was performed in 1,161 Brazilian municipalities, including all state capitals in 2016, totaling 2,848,052 live births and 23,948 neonatal deaths. The results showed that municipalities offering more complex structures obtained similar or even superior performance to the base model developed with data from the municipality of São Paulo. In the third and final article of this thesis, an analysis of the application of the generalization technique known as transfer learning was performed on IACOV-BR Network data to predict death from Covid-19 using medical record data from 16,236 patients from 18 Brazilian hospitals collected in the first quarter of 2020 during the early Covid-19 pandemic in Brazil. The results indicate that, although promising, the conventional transfer learning technique did not prove superior to locally obtained performance results with traditional boosting algorithms. The approach of this article proposed a comparison between a new solution for predicting the clinical progress of Covid-19 patients versus the approach already applied for tabular predictions in healthcare. The results of this thesis point to the importance of the generalization of ML algorithms in healthcare, while technical challenges persist regarding the maintenance of predictive performance in different locations.

A oferta de práticas integrativas e complementares cresce na crise: uma abordagem de ciência de dados / The delivery of integrative and complementary practices grows in times of crisis: a data science approach

Utilizando dados do Programa Nacional de Melhoria do Acesso e da Qualidade da Atenção Básica (PMAQ) observamos, com uma análise descritiva, que a oferta de Práticas Integrativas e Complementares (PICs) na Atenção Básica do Sistema Único de Saúde, pelas Equipes de Saúde da Família (eSF) cresceu continuamente entre 2012 e 2018, período marcado por crise econômica e política. Por outro lado, o crescimento da oferta de PICs não foi uniforme entre as regiões do país, sendo menor nas regiões Centro-Oeste e Norte. Observamos que a oferta de PICs está associada à região, ao porte municipal e ao IDH municipal. Observamos também que a oferta de PICs é maior quando há Núcleo de Apoio à Saúde da Família estruturado no município, quando as eSF participam do Programa Academia da Saúde e quando o gestor da saúde não é formado em medicina. Receber apoio do gestor municipal de saúde, receber ações de educação permanente e realizar planejamento das suas ações também está associado à oferta de PICs pelas eSF. Além disso, utilizando uma estrutura de análise causal baseada no uso de gráficos acíclicos direcionados e análise de sensibilidade, concluímos que a formação do gestor influencia diretamente a oferta de PICs, privilegiando gestores formados em odontologia e psicologia. Utilizando uma abordagem de aprendizagem de máquina, identificamos modelos capazes de prever a oferta de PICs (área sob a curva ROC variando entre 0,70 e 0,88) pelas eSF. Estes modelos mostraram que, dentre outras características, o tamanho populacional, o IDH municipal e a distribuição de renda são relevantes em prever a expansão da oferta de PICs.

Using data from the National Program for Improving Access and Quality of Primary Care (PMAQ), we observed, through descriptive analysis, that the provision of Integrative and Complementary Practices (ICPs) in the Basic Care of the Unified Health System, by Family Health Teams (FHTs), grew continuously between 2012 and 2018, a period marked by economic and political crisis. On the other hand, the growth in the provision of ICPs was not uniform across the country's regions, being lower in the Central-West and Northern regions. We observed that the provision of ICPs is associated with the region, municipal size, and municipal Human Development Index (HDI). We also noted that the provision of ICPs is higher when there is a structured Family Health Support Center in the municipality, when FHTs participate in the Health Academy Program, and when the health manager is not a medical professional. Receiving support from the municipal health manager, undergoing continuous education actions, and planning their actions are also associated with the provision of ICPs by FHTs. Additionally, using a causal analysis framework based on directed acyclic graphs and sensitivity analysis, we concluded that the managers education directly influences ICP provision, favoring managers with backgrounds in dentistry and psychology. Using a machine learning approach, we identified models capable of predicting the provision of ICPs (area under the ROC curve ranging between 0.70 and 0.88) by FHTs. These models showed that, among other characteristics, population size, municipal HDI, and income distribution are relevant in predicting the expansion of ICP provision.

Inteligência artificial para a vigilância de doenças crônicas não-transmissíveis / Artificial intelligence for non-communicable chronic diseases surveillance

As doenças crônicas não transmissíveis (DCNT) representam um desafio significativo para a saúde global, exercendo impacto substancial nos sistemas de saúde em todo o mundo e demandando ações de vigilância e gestão. Nos últimos anos, a utilização de algoritmos de Machine Learning (ML) tem se mostrado uma abordagem promissora para aprimorar ao cuidado e a gestão de saúde. Nesse sentido, esta tese buscou desenvolver algoritmos de ML que contribuam para a vigilância, prevenção e tratamento de DCNT, com o objetivo de colaborar com a saúde pública através de dados e inteligência artificial (IA). Para isso, foram desenvolvidos, em parceria com a Secretaria de Estado da Saúde de São Paulo, quatro manuscritos com distintas aplicações, que compõem a coletânea de artigos desta tese. No primeiro artigo, foi desenvolvida uma revisão sistemática da literatura para explorar o uso de algoritmos de ML na predição da hipertensão arterial. Vinte e um artigos publicados entre janeiro de 2018 e maio de 2021 foram analisados, demonstrando o potencial dos algoritmos de ML para predizer a hipertensão e aprimorar as decisões clínicas preventivas, ainda que alguns dos trabalhos avaliados tenham apresentado problemas de seleção de variáveis e adoção de boas práticas preditivas. O segundo artigo concentrou-se na predição do risco de mortalidade em pacientes com neoplasias malignas no estado de São Paulo. Utilizando dados longitudinais, algoritmos de ML foram testados, alcançando altos valores de Área sob a curva ROC (AUC-ROC) para diferentes tipos de câncer (acima de 0,90). Os resultados apontaram para o potencial para predizer o risco de óbito em pacientes com câncer no estado de São Paulo. O terceiro artigo explorou o uso de algoritmos de ML não supervisionados para a regionalização dos municípios do estado de São Paulo com base nos perfis de morbimortalidade por DCNT. Por meio do agrupamento dos 645 municípios, o estudo identificou áreas contíguas com morbidades e mortalidades semelhantes. Esta abordagem demonstrou o potencial da utilização de ML no fornecimento de informações para o planejamento e a gestão dos sistemas de saúde. Por fim, no quarto artigo buscou-se desenvolver algoritmos de ML para a avaliação da performance da gestão de saúde crônica nos municípios do estado de São Paulo. Para isso, foram calculados os valores esperados de mortalidade prematura ajustada pela idade para cada um dos municípios no período de 2010 a 2019, a partir de um algoritmo de ML. Esses valores esperados, quando comparados com o observado nesses municípios, apontaram para a presença de casos de overachievers ou underachievers, que podem direcionar políticas de saúde e a atenção a nível estadual. As pesquisas apresentadas nesses artigos têm o potencial de contribuir para o avanço das aplicações de ML no campo da saúde pública, abrindo caminhos para estratégias mais eficazes no enfrentamento das DCNT e na promoção de saúde da população.

Chronic non-communicable diseases (NCD) pose a significant challenge for global health, exerting a substantial impact on health systems worldwide, requiring surveillance and management actions. In recent years, the use of machine learning (ML) algorithms has shown promise to improve health care and management. In this sense, this thesis sought to develop ML algorithms that contribute to the surveillance, prevention, and treatment of NCD, with the aim of collaborating with public health through data and artificial intelligence (AI). To this end, four manuscripts with different applications were developed, in partnership with the São Paulo State Department of Health, which make up the collection of articles for this thesis. In the first article, a systematic literature review was developed to explore the use of ML algorithms in the prediction of arterial hypertension. Twenty-one articles published between January 2018 and May 2021 were analyzed, demonstrating the potential of ML algorithms to predict hypertension and improve preventive clinical decisions, although some of the studies evaluated presented problems of variable selection and adoption of good predictive practices. The second article was focused on predicting the risk of mortality in patients with malignant neoplasms in the state of São Paulo, Brazil. Using longitudinal data, several ML algorithms were tested, achieving high values of Area Under the ROC Curve (AUC-ROC) for different types of cancer (above 0.90). The results highlighted the potential to predict the risk of death in cancer patients in the state of São Paulo. The third article explored the use of unsupervised ML algorithms for the regionalization of municipalities in the state of São Paulo based on morbidity and mortality profiles due to NCD. By grouping the 645 municipalities, the study identified contiguous areas with similar morbidities and mortality. This approach demonstrated the potential of using ML in providing information for the planning and management of health systems. Finally, the fourth article sought to develop ML algorithms to support the evaluation of the performance of chronic health management in the municipalities of the state of São Paulo. To this end, we calculated expected values of age-adjusted premature mortality for each of the municipalities in the period from 2010 to 2019, from a ML algorithm. These expected values, when compared with those observed in these municipalities, indicate cases of overachievers or underachievers, which can guide the direction of health policies and care at the state level. The research presented in these articles contributes to the advancement of ML applications in the field of public health, opening paths for more effective strategies in coping with NCD and in promoting the health of the population.

Machine learning model predicts the occurrence of acute kidney injury after open surgery for abdominal aortic aneurysm repair / 中南大学学报(医学版)

OBJECTIVES@#Abdominal aortic aneurysm is a pathological condition in which the abdominal aorta is dilated beyond 3.0 cm. The surgical options include open surgical repair (OSR) and endovascular aneurysm repair (EVAR). Prediction of acute kidney injury (AKI) after OSR is helpful for decision-making during the postoperative phase. To find a more efficient method for making a prediction, this study aims to perform tests on the efficacy of different machine learning models.@*METHODS@#Perioperative data of 80 OSR patients were retrospectively collected from January 2009 to December 2021 at Xiangya Hospital, Central South University. The vascular surgeon performed the surgical operation. Four commonly used machine learning classification models (logistic regression, linear kernel support vector machine, Gaussian kernel support vector machine, and random forest) were chosen to predict AKI. The efficacy of the models was validated by five-fold cross-validation.@*RESULTS@#AKI was identified in 33 patients. Five-fold cross-validation showed that among the 4 classification models, random forest was the most precise model for predicting AKI, with an area under the curve of 0.90±0.12.@*CONCLUSIONS@#Machine learning models can precisely predict AKI during early stages after surgery, which allows vascular surgeons to address complications earlier and may help improve the clinical outcomes of OSR.

Using machine learning algorithm to predict the risk of post-traumatic stress disorder among firefighters in Changsha / 中南大学学报(医学版)

OBJECTIVES@#Firefighters are prone to suffer from psychological trauma and post-traumatic stress disorder (PTSD) in the workplace, and have a poor prognosis after PTSD. Reliable models for predicting PTSD allow for effective identification and intervention for patients with early PTSD. By collecting the psychological traits, psychological states and work situations of firefighters, this study aims to develop a machine learning algorithm with the aim of effectively and accurately identifying the onset of PTSD in firefighters, as well as detecting some important predictors of PTSD onset.@*METHODS@#This study conducted a cross-sectional survey through convenient sampling of firefighters from 20 fire brigades in Changsha, which were evenly distributed across 6 districts and Changsha County, with a total of 628 firefighters. We used the synthetic minority oversampling technique (SMOTE) to process data sets and used grid search to finish the parameter tuning. The predictive capability of several commonly used machine learning models was compared by 5-fold cross-validation and using the area under the receiver operating characteristic curve (ROC-AUC), accuracy, precision, recall, and F1 score.@*RESULTS@#The random forest model achieved good performance in predicting PTSD with an average AUC score at 0.790. The mean accuracy of the model was 90.1%, with an F1 score of 0.945. The three most important predictors were perseverance, forced thinking, and reflective deep thinking, with weights of 0.165, 0.158, and 0.152, respectively. The next most important predictors were employment time, psychological power, and optimism.@*CONCLUSIONS@#PTSD onset prediction model for Changsha firefighters constructed by random forest has strong predictive ability, and both psychological characteristics and work situation can be used as predictors of PTSD onset risk for firefighters. In the next step of the study, validation using other large datasets is needed to ensure that the predictive models can be used in clinical setting.

Advances in machine learning for predicting protein functions / 生物工程学报

Proteins play a variety of functional roles in cellular activities and are indispensable for life. Understanding the functions of proteins is crucial in many fields such as medicine and drug development. In addition, the application of enzymes in green synthesis has been of great interest, but the high cost of obtaining specific functional enzymes as well as the variety of enzyme types and functions hamper their application. At present, the specific functions of proteins are mainly determined through tedious and time-consuming experimental characterization. With the rapid development of bioinformatics and sequencing technologies, the number of protein sequences that have been sequenced is much larger than those can be annotated, thus developing efficient methods for predicting protein functions becomes crucial. With the rapid development of computer technology, data-driven machine learning methods have become a promising solution to these challenges. This review provides an overview of protein function and its annotation methods as well as the development history and operation process of machine learning. In combination with the application of machine learning in the field of enzyme function prediction, we present an outlook on the future direction of efficient artificial intelligence-assisted protein function research.

An interpretable machine learning-based prediction model for risk of death for patients with ischemic stroke in intensive care unit / 南方医科大学学报

OBJECTIVE@#To construct an inherent interpretability machine learning model as an explainable boosting machine model (EBM) for predicting one-year risk of death in patients with severe ischemic stroke.@*METHODS@#We randomly divided the data of 2369 eligible patients with severe ischemic stroke in the MIMIC-Ⅳ(2.0) database, who were admitted in ICU in 2008 to 2019, into a training dataset (80%) and a test dataset (20%), and assessed the prognosis of the patients using the EBM model. The prediction performance of the model was evaluated by calculating the area under the receiver operating characteristic (AUC) curve. The calibration curve and Brier score were used to evaluate the degree of calibration of the model, and a decision curve was generated to assess the net clinical benefit.@*RESULTS@#The EBM model constructed in this study had good discrimination power, calibration and net benefit, with an AUC of 0.857 (95% CI: 0.831-0.887) for predicting prognosis of severe ischemic stroke. Calibration curve analysis showed that the standard curve of the EBM model was the closest to the ideal curve. Decision curve analysis showed that the model had the greatest net benefit rate at the prediction probability threshold of 0.10 to 0.80. The top 5 independent predictive variables based on the EBM model were age, SOFA score, mean heart rate, mechanical ventilation, and mean respiratory rate, whose significance scores ranged from 0.179 to 0.370.@*CONCLUSION@#This EBM model has a good performance for predicting the risk of death within one year in patients with severe ischemic stroke and allows clinicians to better understand the contributing factors of the patients' outcomes through the model interpretability.

Efficacy of machine learning models versus Cox regression model for predicting prognosis of esophagogastric junction adenocarcinoma / 南方医科大学学报

OBJECTIVE@#To compare the performance of machine learning models and traditional Cox regression model in predicting postoperative outcomes of patients with esophagogastric junction adenocarcinoma (AEG).@*METHODS@#This study was conducted among 203 AEG patients with complete clinical and follow-up data, who were treated in our hospital between September, 2015 and October, 2020. The clinicopathological data of the patients were processed for analysis using R language package and divided into training and validation datasets at the ratio of 3:1. The Cox proportional hazards regression model and 4 machine learning models were constructed for analyzing the datasets. ROC curves, calibration curves and clinical decision curves (DCA) were plotted. Internal validation of the machine learning models was performed to assess their predictive efficacy. The predictive performance of each model was evaluated by calculating the area under the curve (AUC), and the model fitting was assessed using the calibration curve.@*RESULTS@#For predicting 3-year survival based on the validation dataset, the AUC was 0.870 for Cox proportional hazard regression model, 0.901 for eXtreme Gradient Boosting (XGBoost), 0.791 for random forest, 0.832 for support vector machine, and 0.725 for multilayer perceptron; For predicting 5-year survival, the AUCs of these models were 0.915, 0.916, 0.758, 0.905, and 0.737, respectively. For internal validation, the AUCs of the 4 machine learning models decreased in the order of XGBoost (0.818), random forest (0.758), support vector machine (0.0.804), and multilayer perceptron (0.745).@*CONCLUSION@#The machine learning models show better predictive efficacy for survival outcomes of patients with AEG than Cox proportional hazard regression model, especially when proportional odds assumption or linear regression models are not applicable. XGBoost models have better performance than the other machine learning models, and the multi-layer perception model may have poor fitting results for a limited data volume.

A review on cardiovascular disease risk prediction models in the elderly / 中华流行病学杂志

Risk prediction models play an important role in the primary prevention of cardiovascular diseases (CVD) in the elderly population. There are fifteen papers about CVD risk prediction models developed for the elderly domestically and internationally, of which the definitions of disease outcome vary widely. Ten models were reported with insufficient information about study methods or results. Ten models were at high risk of bias. Thirteen models presented moderate discrimination in internal validation, and only four models have undertaken external validation. The CVD risk prediction models for the elderly differed from those for the general population in terms of model algorithm and the effect size of association between predictor and outcome, and the prediction performance of the models for the elderly attenuated. In the future, high-quality external validation researches are necessary to provide more solid evidence. Different ways, including adding new predictors, using competing risk model algorithms, machine learning methods, or joint models, and altering the prediction time horizon, should be explored to optimize the current models.

Design and implementation of Internet of Things for emergency medical devices based on cloud-edge-device architecture / 生物医学工程学杂志

Internet of Things (IoT) technology plays an important role in smart healthcare. This paper discusses IoT solution for emergency medical devices in hospitals. Based on the cloud-edge-device architecture, different medical devices were connected; Streaming data were parsed, distributed, and computed at the edge nodes; Data were stored, analyzed and visualized in the cloud nodes. The IoT system has been working steadily for nearly 20 months since it run in the emergency department in January 2021. Through preliminary analysis with collected data, IoT performance testing and development of early warning model, the feasibility and reliability of the in-hospital emergency medical devices IoT was verified, which can collect data for a long time on a large scale and support the development and deployment of machine learning models. The paper ends with an outlook on medical device data exchange and wireless transmission in the IoT of emergency medical devices, the connection of emergency equipment inside and outside the hospital, and the next step of analyzing IoT data to develop emergency intelligent IoT applications.

Authenticity discrimination of Pulsatillae Radix based on dry-process REIMS fingerprinting combined with machine learning / 中国中药杂志

In this study, rapid evaporative ionization mass spectrometry(REIMS) fingerprints of 388 samples of roots of Pulsatilla chinensis(PC) and its common counterfeits, roots of P. cernua and roots of Anemone tomentosa were analyzed based on REIMS combined with machine learning. The samples were determined by REIMS through dry burning, and the REIMS data underwent cluster analysis, similarity analysis(SA), and principal component analysis(PCA). After dimensionality reduction by PCA, the data were analyzed by similarity analysis and self-organizating map(SOM), followed by modeling. The results indicated that the REIMS fingerprints of the samples showed the characteristics of variety differences and the SOM model could accurately distinguish PC, P. cernua, and A. tomentosa. REIMS combined with machine learning algorithm has a broad application prospect in the field of traditional Chinese medicine.