Questões conjunturais sobre a regulação da IA / Conjunctural issues in AI regulation / Cuestiones coyunturales sobre la regulación de la IA

O texto parte da disputa em torno da regulação da inteligência artificial (IA) realmente existente, dividida entre dois polos, o da proteção da inovação e o da necessidade de mitigar riscos sociais e ambientais. Avança para apontar a colossal concentração de poder computacional e de dados nas mãos dos oligopólios digitais, as big techs. Levanta preocupações sobre o impacto dessa concentração na soberania digital e na capacidade do país em controlar suas infraestruturas e dados. Argumenta como a falta de transparência e explicabilidade nos sistemas de IA agrava os riscos de discriminação e exclusão social. Ainda, defende que a regulação da IA deve garantir direitos, salvaguardar a soberania e promover um ecossistema digital autônomo e inclusivo.

The text begins by addressing the debate surrounding the regulation of existing artificial intelligence (AI), divided between two poles: the protection of innovation and the need to mitigate social and environmental risks. It progresses to highlight the colossal concentration of computational power and data in the hands of digital oligopolies, the big tech companies. The text raises concerns about the impact of this concentration on digital sovereignty and the country's ability to control its infrastructures and data. It argues that the lack of transparency and explainability in AI systems exacerbates the risks of discrimination and social exclusion. The text advocates that AI regulation should ensure rights, safeguard sovereignty, and promote an autonomous and inclusive digital ecosystem.

El texto parte de la disputa en torno a la regulación de la inteligencia artificial (IA) existente, dividida entre dos polos: la protección de la innovación y la necesidad de mitigar riesgos sociales y ambientales. Avanza para señalar la colosal concentración de poder computacional y de datos en manos de los oligopolios digitales, las big tech. Plantea preocupaciones sobre el impacto de esta concentración en la soberanía digital y en la capacidad del país para controlar sus infraestructuras y datos. Argumenta que la falta de transparencia y explicabilidad en los sistemas de IA agrava los riesgos de discriminación y exclusión social. El texto defiende que la regulación de la IA debe garantizar derechos, salvaguardar la soberanía y promover un ecosistema digital autónomo e inclusivo.

Artificial Intelligence-Based Diagnosis of Obstructive Sleep Apnea Syndrome: A Scoping Review / Diagnóstico Basado en Inteligencia Artificial para el Síndrome Obstructivo de Apnea del Sueño: Una Revisión de Alcance

SUMMARY: To diagnose obstructive sleep apnea syndrome (OSAS), polysomnography is used, an expensive and extensive study requiring the patient to sleep in a laboratory. OSAS has been associated with features of facial morphology, and a preliminary diagnosis could be made using an artificial intelligence (AI) predictive model. This study aimed to analyze, using a scoping review, the AI-based technological options applied to diagnosing OSAS and the parameters evaluated in such analyses on craniofacial structures. A systematic search of the literature was carried out up to February 2024, and, using inclusion and exclusion criteria, the studies to be analyzed were determined. Titles and abstracts were independently selected by two researchers. Fourteen studies were selected, including a total of 13,293 subjects analyzed. The age of the sample ranged from 18 to 90 years. 9,912 (74.56 %) subjects were male, and 3,381 (25.43 %) were female. The included studies presented a diagnosis of OSAS by polysomnography; seven presented a control group of subjects without OSAS and another group with OSAS. The remaining studies presented OSAS groups in relation to their severity. All studies had a mean accuracy of 80 % in predicting OSAS using variables such as age, gender, measurements, and/or imaging measurements. There are no tests before diagnosis by polysomnography to guide the user in the likely presence of OSAS. In this sense, there are risk factors for developing OSA linked to facial shape, obesity, age, and other conditions, which, together with the advances in AI for diagnosis and guidance in OSAS, could be used for early detection.

Para diagnosticar el Síndrome Apnea Obstructiva del Sueño (SAOS) se utiliza la polisomnografía, el cual es un costoso y extenso estudio que exige que el paciente duerma en un laboratorio. El SAOS ha sido asociado con características de la morfología facial y mediante un modelo predictivo de la Inteligencia Artificial (IA), se podría realizar un diagnóstico preliminar. El objetivo de este estudio fue analizar por medio de una revisión de alcance, las opciones tecnológicas basadas en IA aplicadas al diagnóstico del SAOS, y los parámetros evaluados en dichos análisis en las estructuras craneofaciales. Se realizó una búsqueda sistemática de la literatura hasta febrero del 2024 y mediante criterios de inclusión y exclusión se determino los estudios a analizar. Los títulos y resúmenes fueron seleccionados de forma independiente por dos investigadores. Se seleccionaron 14 estudios, incluyeron un total de 13.293 sujetos analizados. El rango edad de la muestra oscilo entre 18 y 90 años. 9.912 (74.56 %) sujetos eran de sexo masculino y 3.381 (25,43 %) eran de sexo femenino. Los estudios incluidos presentaron diagnóstico de SAOS mediante polisomnografía, siete estudios presentaron un grupo control de sujetos con ausencia de SAOS y otro grupo con presencia de SAOS. Mientras que los demás estudios, presentaron grupos de SAOS en relación con su severidad. Todos los estudios tuvieron una precisión media del 80 % en la predicción de SAOS utilizando variables como la edad, el género, mediciones y/o mediciones imagenológicas. no existen exámenes previos al diagnóstico por polisomnografía que permitan orientar al usuario en la probable presencia de SAOS. En este sentido, existen factores de riesgo para desarrollar SAOS vinculados a la forma facial, la obesidad, la edad y otras condiciones, que sumados a los avances con IA para diagnóstico y orientación en SAOS podrían ser utilizados para la detección precoz del mismo.

Surface Models of the Four Chambers in Young Adult Hearts with Average Volumes Measured by Artificial Intelligence Tools / Modelos de Superficie de las Cuatro Cámaras en Corazones de Adultos Jóvenes con Volúmenes Promedio Medidos Mediante Herramientas de Inteligencia Artificial

SUMMARY: The average volumes of normal heart chambers in computed tomography (CT) are used not only as clinical criterions for heart disease diagnosis, but also as references in cardiology. With the development of artificial intelligence (AI), numerous CT data can be analyzed and segmented automatically. This study aimed to determine the average volumes of the four chambers in healthy adult hearts and present surface models with the average volume. Coronary CT angiographs of 508 Korean individuals (330 men and 178 women, 20 - 39 years old) were obtained. An automatic segmentation module for 3D Slicer was developed using machine learning in Anatomage KoreaTM. Using the module, the four chambers and heart valves in the CT were segmented and reconstructed into surface models. Surface models of the four chambers of identical hearts in the CT were produced using SimplewareTM. The volumes of structures were measured using Sim4life Light and statistically analyzed. After determining the average volumes of the four chambers, surface models of the average volumes were constructed. In both software measurements, the atrial volumes of females increased with age, and the ventricular volumes of males decreased significantly with age. The atrial and ventricular volumes of Simpleware were larger and smaller than those of Anatomage, respectively, because of errors in the Simpleware. Regarding the volume measurement, our module developed in this study was more accurate than the Simpleware. The average volume and three-dimensional models used in this study can be used not only for clinical purposes, but also for educational or industrial purposes.

Los volúmenes medios de las cámaras cardíacas normales en la tomografía computarizada (TC) se utilizan no sólo como criterios clínicos para el diagnóstico de enfermedades cardíacas, sino también como referencia en cardiología. Con el desarrollo de la inteligencia artificial (IA), numerosos datos de TC se pueden analizar y segmentar automáticamente. Este estudio tuvo como objetivo determinar los volúmenes promedio de las cuatro cámaras en corazones adultos sanos y presentar modelos de superficie con el volumen promedio. Se obtuvieron angiografías coronarias por TC de 508 individuos coreanos (330 hombres y 178 mujeres, de 20 a 39 años). Se desarrolló un módulo de segmentación automática para 3D Slicer utilizando aprendizaje automático en Anatomage KoreaTM. Utilizando el módulo, las cuatro cámaras y valvas cardíacas de la TC se segmentaron y reconstruyeron en modelos de superficie. Se produjeron modelos de superficie de las cuatro cámaras de corazones idénticos en la TC utilizando SimplewareTM. Los volúmenes de las estructuras se midieron utilizando Sim4life Light y se analizaron estadísticamente. Después de determinar los volúmenes promedio de las cuatro cámaras, se construyeron modelos de superficie de los volúmenes promedio. En ambas mediciones de software, los volúmenes atriales de las mujeres aumentaron con la edad y los volúmenes ventriculares de los hombres disminuyeron significativamente con la edad. Los volúmenes atrial y ventricular de Simpleware eran mayores y menores que los de Anatomage, respectivamente, debido a errores en Simpleware. En cuanto a la medición de volumen, nuestro módulo desarrollado en este estudio fue más preciso que el Simpleware. Los modelos tridimensionales y de volumen medio utilizados en este estudio se pueden utilizar no solo con fines clínicos, sino también con fines educativos o industriales.

La Inteligencia Artificial Generativa en la escena de la educación superior en ciencias de la salud / Generative Artificial Intelligence on the Scene of Higher Education in the Health Sciences

Introducción: este artículo se enfoca en la experiencia de un Instituto Universitario de gestión privada de la ciudad de Buenos Aires al abordar la inteligencia artificial (IA) en educación. El objetivo es compartir líneas de acción y resultados para promover la reflexión y apropiación crítica de esta tecnología en la comunidad educativa. Desarrollo: se presenta un relato de experiencia referido al diseño de cuatro líneas de acción para abordar el uso de aplicaciones de IA generativa (IAGen) en la educación superior en ciencias de la salud: elaboración de un estado de la cuestión; indagación de conocimientos en la comunidad educativa; capacitaciones para actores institucionales clave; producción de materiales guía. Resultados: se observa un creciente interés en la IAGen en la comunidad educativa. Se registran experiencias positivas con aplicaciones de IAGen, encontrándolas intuitivas y útiles para la investigación y la enseñanza. Sin embargo, se destacan desafíos, como la falta de conocimiento sobre cómo usar estas herramientas de manera eficaz. La formación ha sido clave para abordar estos desafíos y se ha llevado a cabo para integrantes del equipo del Departamento de Educación, autoridades y docentes. Conclusión: la IAGen está atravesando integralmente la educación superior en el campo de las ciencias de la salud. Las instituciones universitarias tienen la responsabilidad de promover el desarrollo de competencias digitales y criterios de uso responsables. A medida que la IAGen continúa desarrollándose, es esencial abordar nuevos desafíos y regulaciones, promoviendo la reflexión y la formación continua en la comunidad educativa. El trabajo interdisciplinario y la colaboración entre diversas áreas de gestión institucional son fundamentales para abordar estos cambios tecnológicos en la educación. (AU)

Introduction:This article focuses on the experience of a privately managed University Institute in Buenos Aires city when addressing artificial intelligence (AI) in education. The aim is to share strategies and outcomes to encourage reflection and critical engagement with this technology within the educational community. Development: We present a narrative of experience concerning the design of four lines of action to address the uses of generative AI applications (GenAI) in higher education in health sciences: drafting a state-of-the-art report; probing knowledge within the educational community; training sessions for core institutional actors; production of guide materials. Results: There is a growing interest in GenAI within the educational community. We register positive experiences with IAGen applications, finding them intuitive and useful for research and teaching. However, we highlight challenges, such as gaps in knowledge on how to use these tools most effectively. Training has been crucial in addressing these challenges and has been conducted for members of the Education Department team, authorities, and teachers. Conclusion: GenAI is fundamentally permeating higher education in the field of health sciences. University institutions are responsible for promoting the development of digital competencies and standards of responsible use. As GenAI continues to evolve, addressing new challenges and regulations is essential, encouraging reflection and ongoing training within the educational community. Interdisciplinary work and collaboration among various areas of institutional management are critical to address these technological changes in education. (AU)

Una revisión sistemática del uso de la inteligencia artificial en la educación / A systematic review of the use of artificial intelligence in education

Introducción. El uso de la inteligencia artificial (IA) en la educación ha sido objeto de una creciente atención en los últimos años. La IA se ha utilizado para mejorar la personalización del aprendizaje, la retroalimentación y la evaluación de los estudiantes. Sin embargo, también hay desafíos y limitaciones asociados. El objetivo de este trabajo fue identificar las principales tendencias y áreas de aplicación de la inteligencia artificial en la educación, así como analizar los beneficios y limitaciones de su uso en este ámbito. Métodos. Se llevó a cabo una revisión sistemática que exploró el empleo de la inteligencia artificial en el ámbito educativo. Esta revisión siguió una metodología de investigación basada en la búsqueda de literatura, compuesta por cinco etapas. La investigación se realizó utilizando Scopus como fuente de consulta primaria y se empleó la herramienta VOSviewer para analizar los resultados obtenidos. Resultados. Se encontraron numerosos estudios que investigan el uso de la IA en la educación. Los resultados sugieren que la IA puede mejorar significativamente la personalización del aprendizaje, proporcionando recomendaciones de actividades y retroalimentación adaptadas a las necesidades individuales de cada estudiante. Conclusiones. A pesar de las ventajas del uso de la IA en la educación, también hay desafíos y limitaciones que deben abordarse, como la calidad de los datos utilizados por la IA, la necesidad de capacitación para educadores y estudiantes, y las preocupaciones sobre la privacidad y la seguridad de los datos de los estudiantes. Es importante seguir evaluando los efectos del uso de la IA en la educación para garantizar su uso efectivo y responsable.

Introduction. The use of artificial intelligence (AI) in education has been the subject of increasing attention in recent years. AI has been used to improve personalized learning, feedback, and student assessment. However, there are also challenges and limitations. The aim of this study was to identify the main trends and areas of application of artificial intelligence in education, as well as to analyze the benefits and limitations of its use in this field. Methods. A systematic review was carried out on the use of artificial intelligence in education, using a literature search research methodology with five stages, based on the Scopus query and the tool for analyzing results with VOSviewer. Results. Numerous studies investigating the use of AI in education were found. The results suggest that AI can significantly improve personalized learning by providing activity recommendations and feedback tailored to the individual needs of each student. Conclusions. Despite the advantages of using AI in education, there are also challenges and limitations that need to be addressed, such as the quality of data used by AI, the need for training for educators and students, and concerns about the privacy and security of student data. It is important to continue evaluating the effects of AI use in education to ensure its effective and responsible use.

A sonographic evaluation on agreement and time efficiency of fetal central nervous system biometry using semi-automated five-dimensional ultrasound versus standard two dimensional ultrasound in a Philippine Tertiary Hospital / Philippine Journal of Obstetrics and Gynecology

Background@#Proper assessment and efficient diagnosis of central nervous system anomalies is essential in antenatal surveillance of pregnant patients. These anomalies are usually associated with genetic syndromes or severe malformations requiring timely intervention and antenatal counseling of the expectant couple.@*Objective@#The study aims to evaluate the agreement of cranial biometric measurements and to determine if there is a significant difference in the time needed to complete the evaluation using standard 2D and semi-automated 5D ultrasound.@*Methods@#An analytical cross-sectional study was employed on 93 women who underwent pelvic ultrasound scans from August to October 2022 in a tertiary hospital. Basic biometric fetal central nervous system (CNS) measurements were acquired using 2D ultrasound followed by 5D CNS ultrasound. Bland-Altman plots were used to evaluate the agreement of the measurements obtained. The difference in the time to completion was determined using independent t-test.@*Results and Conclusions@#Our study found that 5D CNS ultrasound measurements showed 96.8% agreement with 2D ultrasound in 90 out of 93 fetuses. The 5D CNS ultrasound takes a shorter time of 90 seconds (s) to completion in comparison to 99 s using the 2D method (p=0.076). Upon stratification of the study population per trimester, in the second trimester, it took 76 s with 5D CNS vs 89 s with 2D, resulting to a statistically significant 13-second difference (p=0.044). In the third trimester, 5D CNS took 105 s vs 108 s with 2D (p=0.614). The time to completion of the scan using this technology is faster when used for second trimester pregnancies but could be affected by fetal-dependent and operator-dependent factors. Therefore, application of this new technology has the potential to improve workflow efficiency after the necessary training on 3D sonography and 5D CNS ultrasound software.

Generative Artificial Intelligence (AI) in scientific publications / Journal of the ASEAN Federation of Endocrine Societies

@#Twenty-six years earlier in their famous chess rematch, an IBM Supercomputer called Deep Blue defeated then-world chess champion Garry Kasparov: it was the first-ever chess match won by a machine, a much celebrated milestone in the field of Artificial Intelligence. Just last year, the World Association of Medical Editors released the “WAME Recommendations on Chatbots and Generative Artificial Intelligence in Relation to Scholarly Publications,” a recognition of not just the expanding applications of AI in scholarly publishing but more so of the accompanying emergence of concerns on authenticity and accuracy. In recognition of this relevant topic, our Vice Editor in Chief, Dr. Cecile Jimeno, provided a well-attended and interesting talk during the last ASEAN Federation of Endocrine Society Convention in Thailand on the “Emerging Issues on the Use of Artificial Intelligence for Scientific Publications.”

Utilization of artificial intelligence in breast pathology: An overview

@#In the last decade, artificial intelligence (AI) has been increasingly used in various fields of medicine. Recently, the advent of whole slide images (WSI) or digitized slides has paved the way for AI-based anatomic pathology. This paper set out to review the potential integration of AI algorithms in the workflow, and the utilization of AI in the practice of breast pathology.

Artificial intelligence-based analysis of tumor-infiltrating lymphocyte spatial distribution for colorectal cancer prognosis / 中华医学杂志(英文版)

BACKGROUND@#Artificial intelligence (AI) technology represented by deep learning has made remarkable achievements in digital pathology, enhancing the accuracy and reliability of diagnosis and prognosis evaluation. The spatial distribution of CD3 + and CD8 + T cells within the tumor microenvironment has been demonstrated to have a significant impact on the prognosis of colorectal cancer (CRC). This study aimed to investigate CD3 CT (CD3 + T cells density in the core of the tumor [CT]) prognostic ability in patients with CRC by using AI technology.@*METHODS@#The study involved the enrollment of 492 patients from two distinct medical centers, with 358 patients assigned to the training cohort and an additional 134 patients allocated to the validation cohort. To facilitate tissue segmentation and T-cells quantification in whole-slide images (WSIs), a fully automated workflow based on deep learning was devised. Upon the completion of tissue segmentation and subsequent cell segmentation, a comprehensive analysis was conducted.@*RESULTS@#The evaluation of various positive T cell densities revealed comparable discriminatory ability between CD3 CT and CD3-CD8 (the combination of CD3 + and CD8 + T cells density within the CT and invasive margin) in predicting mortality (C-index in training cohort: 0.65 vs. 0.64; validation cohort: 0.69 vs. 0.69). The CD3 CT was confirmed as an independent prognostic factor, with high CD3 CT density associated with increased overall survival (OS) in the training cohort (hazard ratio [HR] = 0.22, 95% confidence interval [CI]: 0.12-0.38, P <0.001) and validation cohort (HR = 0.21, 95% CI: 0.05-0.92, P = 0.037).@*CONCLUSIONS@#We quantify the spatial distribution of CD3 + and CD8 + T cells within tissue regions in WSIs using AI technology. The CD3 CT confirmed as a stage-independent predictor for OS in CRC patients. Moreover, CD3 CT shows promise in simplifying the CD3-CD8 system and facilitating its practical application in clinical settings.

Expert consensus on fundus photograph-based cardiovascular risk assessment using artificial intelligence technology / 中华内科杂志

Cardiovascular risk assessment is a basic tenet of the prevention of cardiovascular disease. Conventional risk assessment models require measurements of blood pressure, blood lipids, and other health-related information prior to assessment of risk via regression models. Compared with traditional approaches, fundus photograph-based cardiovascular risk assessment using artificial intelligence (AI) technology is novel, and has the advantages of immediacy, non-invasiveness, easy performance, and low cost. The Health Risk Assessment and Control Committee of the Chinese Preventive Medicine Association, in collaboration with the Chinese Society of Cardiology and the Society of Health Examination, invited multi-disciplinary experts to form a panel to develop the present consensus, which includes relevant theories, progress in research, and requirements for AI model development, as well as applicable scenarios, applicable subjects, assessment processes, and other issues associated with applying AI technology to assess cardiovascular risk based on fundus photographs. A consensus was reached after multiple careful discussions on the relevant research, and the needs of the health management industry in China and abroad, in order to guide the development and promotion of this new technology.

The function of competitive intelligence in South African insurance post-COVID-19 outbreak

Background: Competitive intelligence (CI) involves monitoring competitors and providing organizations with actionable and meaningful intelligence. Some studies have focused on the role of CI in other industries post-COVID-19 pandemic. Objectives: This article aims to examine the impact of COVID-19 on the South African insurance sector and how the integration of CI and related technologies can sustain the South African insurance sector post-COVID-19 epidemic. Method: Qualitative research with an exploratory-driven approach was used to examine the impact of the COVID-19 pandemic on the South African insurance sector. Qualitative secondary data analyses were conducted to measure insurance claims and death benefits paid during the COVID-19 pandemic. Results: The research findings showed that the COVID-19 pandemic significantly impacted the South African insurance industry, leading to a reassessment of pricing, products, and risk management. COVID-19 caused disparities in death benefits and claims between provinces; not everyone was insured. Despite challenges, South African insurers remained well-capitalised and attentive to policyholders. Integrating CI and analytical technologies could enhance the flexibility of prevention, risk management, and product design. Conclusion: COVID-19 requires digital transformation and CI for South African insurers' competitiveness. Integrating artificial intelligence (AI), big data (BD), and CI enhances value, efficiency, and risk assessments. Contribution: This study highlights the importance of integrating CI strategies and related technologies into South African insurance firms' operations to aid in their recovery from the COVID-19 crisis. It addresses a research gap and adds to academic knowledge in this area.

Using the Chat Generative Pre-trained Transformer in academic writing in health: a scoping review / Uso del Chat Generative Pre-trained Transformer en la escritura académica en salud: una revisión de alcance / Uso do Chat Generative Pre-trained Transformer na escrita acadêmica em saúde: uma revisão do escopo

Objective: to map the scientific literature regarding the use of the Chat Generative Pre-trained Transformer, ChatGPT, in academic writing in health. Method: this was a scoping review, following the JBI methodology. Conventional databases and gray literature were included. The selection of studies was applied after removing duplicates and individual and paired evaluation. Data were extracted based on an elaborate script, and presented in a descriptive, tabular and graphical format. Results: the analysis of the 49 selected articles revealed that ChatGPT is a versatile tool, contributing to scientific production, description of medical procedures and preparation of summaries aligned with the standards of scientific journals. Its application has been shown to improve the clarity of writing and benefits areas such as innovation and automation. Risks were also observed, such as the possibility of lack of originality and ethical issues. Future perspectives highlight the need for adequate regulation, agile adaptation and the search for an ethical balance in incorporating ChatGPT into academic writing. Conclusion: ChatGPT presents transformative potential in academic writing in health. However, its adoption requires rigorous human supervision, solid regulation, and transparent guidelines to ensure its responsible and beneficial use by the scientific community.

Objetivo: mapear la literatura científica sobre el uso del Chat Generative Pre-trained Transformer , ChatGPT, en la escritura académica en salud. Método: se trató de una revisión de alcance, siguiendo la metodología del JBI. Se incluyeron bases de datos convencionales y literatura gris. La selección de los estudios se realizó previa eliminación de duplicados y evaluación individual y en pares. Los datos se extrajeron basándose en un guión elaborado y se presentaron en un formato descriptivo, tabular y gráfico. Resultados: el análisis de los 49 artículos seleccionados reveló que ChatGPT es una herramienta versátil, que contribuye a la producción científica, descripción de procedimientos médicos y elaboración de resúmenes alineados con los estándares de las revistas científicas. Se ha demostrado que su aplicación mejora la claridad de la redacción y beneficia áreas como la innovación y la automatización. También se observaron riesgos, como la posibilidad de falta de originalidad y cuestiones éticas. Las perspectivas futuras resaltan la necesidad de una regulación adecuada, adaptación ágil y búsqueda de un equilibrio ético en la incorporación del ChatGPT a la escritura académica. Conclusión: ChatGPT presenta un potencial transformador en la escritura académica en el área de la salud. Sin embargo, su adopción requiere una supervisión humana rigurosa, una regulación sólida y directrices transparentes para garantizar su uso responsable y beneficioso por parte de la comunidad científica.

Objetivo: mapear a literatura científica referente ao uso do Chat Generative Pre-trained Transformer , ChatGPT, na escrita acadêmica em saúde. Método: tratou-se de uma revisão de escopo, seguindo o método do JBI. Foram incluídas bases de dados convencionais e literatura cinzenta. A seleção dos estudos foi realizada após a remoção de duplicatas e avaliação individual e em pares. Os dados foram extraídos com base em um roteiro elaborado, e apresentados de forma descritiva, tabular e gráfica. Resultados: a análise dos 49 artigos selecionados mostrou que o ChatGPT é uma ferramenta versátil, que contribui para a produção científica, descrição de procedimentos médicos e elaboração de resumos alinhados aos padrões das revistas científicas. Sua aplicação melhorou a clareza da redação e beneficia áreas como inovação e automação. Também foram observados riscos, como a possibilidade de falta de originalidade e questões éticas. Perspectivas futuras destacam a necessidade de regulamentação adequada, adaptação ágil e busca por um equilíbrio ético na incorporação do ChatGPT na escrita acadêmica. Conclusão: o ChatGPT apresenta um potencial transformador na escrita acadêmica na área da saúde. Contudo, sua adoção requer supervisão humana rigorosa, regulamentação sólida e diretrizes transparentes para garantir seu uso responsável e benéfico pela comunidade científica.

Nursing workload: use of artificial intelligence to develop a classifier model / Carga de trabajo de enfermería: uso de inteligencia artificial para el desarrollo de modelo clasificador / Carga de trabalho de enfermagem: uso de inteligência artificial para o desenvolvimento de modelo classificador

Objective: to describe the development of a predictive nursing workload classifier model, using artificial intelligence. Method: retrospective observational study, using secondary sources of electronic patient records, using machine learning. The convenience sample consisted of 43,871 assessments carried out by clinical nurses using the Perroca Patient Classification System, which served as the gold standard, and clinical data from the electronic medical records of 11,774 patients, which constituted the variables. In order to organize the data and carry out the analysis, the Dataiku® data science platform was used. Data analysis occurred in an exploratory, descriptive and predictive manner. The study was approved by the Ethics and Research Committee of the institution where the study was carried out. Results: the use of artificial intelligence enabled the development of the nursing workload assessment classifier model, identifying the variables that most contributed to its prediction. The algorithm correctly classified 72% of the variables and the area under the Receiver Operating Characteristic curve was 82%. Conclusion: a predictive model was developed, demonstrating that it is possible to train algorithms with data from the patient's electronic medical record to predict the nursing workload and that artificial intelligence tools can be effective in automating this activity.

Objetivo: describir el desarrollo de un modelo clasificador predictivo de la carga de trabajo de enfermería, utilizando inteligencia artificial. Método: estudio observacional retrospectivo, en fuentes secundarias de registros electrónicos de pacientes, con uso de aprendizaje automático. La muestra por conveniencia se constituyó de 43.871 evaluaciones realizadas por enfermeras asistenciales con el Sistema de Clasificación de Pacientes de Perroca, que sirvieron como patrón oro, y datos clínicos del expediente electrónico de 11.774 pacientes, que constituyeron las variables. Para la organización de los datos y la realización de los análisis se utilizó la plataforma de ciencia de datos Dataiku ® . El análisis de los datos ocurrió de forma exploratoria, descriptiva y predictiva. Estudio aprobado por el Comité de Ética e Investigación de la institución campo del estudio. Resultados: el uso de inteligencia artificial posibilitó el desarrollo del modelo clasificador de evaluación de la carga de trabajo de enfermería, identificando las variables que más contribuyeron para su predicción. El algoritmo clasificó correctamente el 72% de las variables y el área bajo la curva Receiver Operating Characteristic fue del 82%. Conclusión: hubo el desarrollo de un modelo predictivo, demostrando que es posible entrenar algoritmos con datos del expediente electrónico del paciente para predecir la carga de trabajo de enfermería y que las herramientas de inteligencia artificial pueden ser efectivas para la automatización de esta actividad.

Objetivo: descrever o desenvolvimento de um modelo classificador preditivo da carga de trabalho de enfermagem, utilizando inteligência artificial. Método: estudo observacional retrospectivo, em fontes secundárias de registros eletrônicos de pacientes, com uso de aprendizado de máquina. A amostra por conveniência constituiu-se de 43.871 avaliações realizadas por enfermeiras assistenciais com o Sistema de Classificação de Pacientes de Perroca, as quais serviram como padrão ouro, e os dados clínicos do prontuário eletrônico de 11.774 pacientes, que constituíram as variáveis. Para a organização dos dados e a realização das análises, utilizou-se a plataforma de ciência de dados Dataiku ® . A análise dos dados ocorreu de forma exploratória, descritiva e preditiva. Estudo aprovado pelo Comitê de Ética e Pesquisa da instituição campo do estudo. Resultados: o uso de inteligência artificial possibilitou o desenvolvimento do modelo classificador de avaliação da carga de trabalho de enfermagem, identificando as variáveis que mais contribuíram para a sua predição. O algoritmo classificou corretamente 72% das variáveis e a área sob a curva Receiver Operating Characteristic foi de 82%. Conclusão: houve o desenvolvimento de um modelo preditivo, demonstrando que é possível treinar algoritmos com dados do prontuário eletrônico do paciente para predizer a carga de trabalho de enfermagem e que as ferramentas da inteligência artificial podem ser efetivas para a automatização desta atividade.