Comparison of the refractive prediction errors of artificial intelligence formula with 3 conventional formulas and 11 combination methods in cataract surgery on eyes with short axial length

ABSTRACT Purpose: To compare the refractive prediction error of Hill-radial basis function 3.0 with those of 3 conventional formulas and 11 combination methods in eyes with short axial lengths. Methods: The refractive prediction error was calculated using 4 formulas (Hoffer Q, SRK-T, Haigis, and Hill-RBF) and 11 combination methods (average of two or more methods). The absolute error was determined, and the proportion of eyes within 0.25-diopter (D) increments of absolute error was analyzed. Furthermore, the intraclass correlation coefficients of each method were computed to evaluate the agreement between target refractive error and postoperative spherical equivalent. Results: This study included 87 eyes. Based on the refractive prediction error findings, Hoffer Q formula exhibited the highest myopic errors, followed by SRK-T, Hill-RBF, and Haigis. Among all the methods, the Haigis and Hill-RBF combination yielded a mean refractive prediction error closest to zero. The SRK-T and Hill-RBF combination showed the lowest mean absolute error, whereas the Hoffer Q, SRK-T, and Haigis combination had the lowest median absolute error. Hill-radial basis function exhibited the highest intraclass correlation coefficient, whereas SRK-T showed the lowest. Haigis and Hill-RBF, as well as the combination of both, demonstrated the lowest proportion of refractive surprises (absolute error >1.00 D). Among the individual formulas, Hill-RBF had the highest success rate (absolute error ≤0.50 D). Moreover, among all the methods, the SRK-T and Hill-RBF combination exhibited the highest success rate. Conclusions: Hill-radial basis function showed accuracy comparable to or surpassing that of conventional formulas in eyes with short axial lengths. The use and integration of various formulas in cataract surgery for eyes with short axial lengths may help reduce the incidence of refractive surprises.

La inteligencia artificial en los procesos editoriales y la evaluación por pares / Artificial Intelligence in the Editorial Process and Peer Review

Resumen La narrativa mitológica de Epimeteo y Prometeo, retratada por Platón, sirve de introducción a la importancia de la inteligencia artificial (IA). El hombre se caracteriza en este mito, frente al resto de criaturas, por tener un don divino: la capacidad de crear herramientas. La IA representa un avance revolucionario al sustituir la labor intelectual humana, destacando su capacidad para generar nuevo conocimiento de forma autónoma. En el ámbito científico, la IA agiliza la revisión por pares y mejora la eficiencia en la evaluación de manuscritos, además de aportar elementos creativos, como la reescritura, traducción o creación de ilustraciones. Sin embargo, su implementación debe ser ética, limitada a un asistente y bajo la supervisión experta para evitar errores y abusos. La IA, una herramienta divina en evolución, requiere que cada uno de sus avances se estudie y aplique críticamente.

Abstract The mythological story of Epimetheus and Prometheus, as told by Plato, serves as an introduction to the meaning of artificial intelligence (AI). In this myth, man, unlike other creatures, is endowed with a divine gift: the ability to create tools. AI represents a revolutionary advance, replacing human intellectual labour and emphasising its ability to autonomously generate new knowledge. In the scientific field, AI is speeding up peer review processes and increasing the efficiency of manuscript evaluation, while also contributing creative elements such as rewriting, translating or creating illustrations. However, its use must be ethical, limited to an assisting role, and subject to expert oversight to prevent errors and misuse. AI, an evolving divine tool, requires critical study and application of each of its advances.

Assistentes Virtuais Inteligentes e saúde mental: debates regulatórios no Brasil / Intelligent Virtual Assistants and mental health: regulatory debates in Brazil / Asistentes Virtuales Inteligentes y salud mental: debates regulatorios en Brasil

A inserção dos Assistentes Virtuais Inteligentes na vida cotidiana representa um marco na história da comunicação entre humanos e máquinas. Devido às suas características interativas, estes estão sendo cada vez mais apropriados e desenvolvidos para fins de cuidado, especialmente no âmbito da saúde mental. Este artigo visa compreender se e como o debate regulatório brasileiro oferece instrumentos para lidar com os desafios e as preocupações desses sistemas de Inteligência Artificial em relação à saúde mental. A partir de uma análise documental, mapeamos exemplos de aplicação dos Assistentes Virtuais Inteligentes em saúde mental, a fim de identificar riscos a direitos dos usuários e avaliar, na legislação brasileira vigente e em discussão, se há proteção suficiente para lidar com eles. Por meio de uma abordagem crítica, salientamos a insuficiência da legislação brasileira atual e a necessidade de ampliação do debate sobre como equilibrar possíveis riscos e benefícios dessas tecnologias.

The integration of Intelligent Virtual Assistants into everyday life marks a milestone in the history of human-machine communication. Due to their interactive characteristics, they are increasingly being appropriated and developed for caregiving purposes, especially in the field of mental health. This article aims to understand whether and how the Brazilian regulatory debate provides tools to address the challenges and concerns of these Artificial Intelligence systems concerning mental health. Through a document analysis, we map examples of Intelligent Virtual Assistants's applications to mental health to identify risks to users' rights and evaluate whether the current and the proposed Brazilian legislation offer sufficient protection to address these risks. Through a critical approach, we highlight the inadequacy of current Brazilian legislation and the need to expand the debate on how to balance the potential risks and benefits of these technologies.

La inserción de los Asistentes Virtuales Inteligentes en la vida cotidiana representa un hito en la historia de la comunicación entre humanos y máquinas. Debido a sus características interactivas, cada vez son más apropiados y desarrollados para fines de cuidado. Este artículo tiene como objetivo comprender si y cómo el debate regulatorio brasileño ofrece instrumentos para abordar los desafíos y preocupaciones de estos sistemas de Inteligencia Artificial en relación con la salud mental. A partir de un análisis documental, mapeamos ejemplos de la aplicación de los Asistentes Virtuales Inteligentes a la salud mental, con el fin de identificar riesgos para los derechos de los usuarios y evaluar, en la legislación brasileña vigente y en discusión, si hay protección suficiente para abordarlos. Destacamos la insuficiencia de la legislación brasileña actual y la necesidad de ampliar el debate sobre cómo equilibrar los posibles riesgos y beneficios de estas tecnologías.

Artificial intelligence-driven patient monitoring for adverse event detection in clinical trials

Artificial intelligence (AI) keeps an eye on people in clinical studies to find out when bad things happen. This is a big way that AI is changing healthcare. It goes into a lot of detail about how AI has changed this field and stresses how important it is to use complicated formulas, always keep an eye on things, and follow the rules. These days, we have tools like deep learning frameworks, controlled and unsupervised learning models, and others that help us find bad things faster and more accurately. Tracking in real time is possible with early warning systems and constant data analysis. It helps make sure the experiment is done right and puts the safety of the people being tested first. AI-driven tracking systems can only work in an honest and reliable way if they follow the rules set by regulatory bodies such as the FDA and the EMA. The fact that AI has the ability to change the way medical research is done today, with benefits like making it faster and more accurate, makes its problems even more important. The report comes to the conclusion that more research, better teamwork, and a wider use of AI technologies are needed to make it more reliable to find bad events in clinical studies over time.

Potential of artificial intelligence to generate health research reports of decayed, missed and restored teeth / Potencial de la inteligencia artificial para generar informes de investigación sanitaria sobre dientes cariados, perdidos y restaurados

Abstract This study aims to indicate the potential of artificial intelligence (AI) in epidemiological reports of decayed, missed and restored teeth. As a proof of concept our study model used panoramic x-ray images and an AI algorithm for tooth numbering, detection of the caries and restorations with accuracy over 80% for such diagnostic tasks. The output came as the number of decayed, missed and restored teeth according to patient's age and the DMFT index (number of decayed, missing, and filled teeth) which varied from 3.6 (up to 20 years old) to 20.4 (+60 years old). Thus, it is suggested that AI is a promising method to automate health data collection through the analysis of x-rays.

Resumen Este estudio tiene como objetivo indicar el potencial de la inteligencia artificial (IA) en los informes epidemiológicos de dientes cariados, perdidos y restaurados. Como prueba de concepto, nuestro modelo de estudio utilizó imágenes panorámicas de rayos X y un algoritmo de inteligencia artificial para la numeración de dientes, la detección de caries y las restauraciones con una precisión superior al 80 % para dichas tareas de diagnóstico. El resultado fue el número de dientes cariados, perdidos y restaurados según la edad del paciente y el índice CPOD (número de dientes cariados, perdidos y obturados) que varió de 3,6 (hasta 20 años) a 20,4 (+60 años). Por tanto, se sugiere que la IA es un método prometedor para automatizar la recopilación de datos de salud mediante el análisis de rayos X.

Aplicaciones, oportunidades y desafíos de implementar la inteligencia artificial en medicina: una revisión narrativa de la literatura / Applications, opportunities and challenges of implementing artificial intelligence in medicine: a narrative literature review

La inteligencia artificial se está usando ampliamente en diversos campos de la medicina. El objetivo de esta revisión es describir las principales aplicaciones, oportunidades y desafíos de la inteligencia artificial en medicina brindando una perspectiva del contexto actual. Se realizó una revisión narrativa de la literatura, identificando la información más actualizada y relevante sobre el tema. Se consultaron las bases de datos electrónicas PubMed, Scopus y SciELO, desde enero de 2019 a marzo de 2024, tanto en inglés como en español. Se incluyeron revisiones sistemáticas y no sistemáticas de la literatura, scoping reviews, artículos originales y capítulos de libros. Se excluyeron artículos duplicados, trabajos científicos poco claros, aquellos de bajo rigor científico y literatura gris. La implementación de la inteligencia artificial en medicina ha traído consigo notables beneficios, que van desde el registro de información médica hasta el descubrimiento de nuevos fármacos. Ha generado una revolución en la forma tradicional de hacer medicina. Por otro lado, ha traído consigo desafíos en materia de precisión, confiabilidad, ética, privacidad, entre otros. Es crucial mantener un enfoque centrado en el paciente y garantizar que estas tecnologías se utilicen para mejorar los resultados en salud y promover la equidad en el acceso a la atención médica. La colaboración entre profesionales de la salud, investigadores, entidades reguladoras y desarrolladores de tecnología será fundamental para enfrentar estos desafíos y aprovechar todo el potencial de la inteligencia artificial.

Artificial intelligence is being widely used in various fields of medicine. The aim of this review is to describe the main applications, opportunities and challenges of AI in medicine by providing an overview of the current context. An overview of the literature was conducted, identifying the most up-to-date and relevant information on the topic. The electronic databases PubMed, Scopus and SciELO were consulted, from January 2019 to March 2024, in both English and Spanish. Systematic and non-systematic literature reviews, scoping reviews, original articles and book chapters were included. Duplicate articles, unclear scientific papers, those of low scientific rigour and grey literature were excluded. The implementation of artificial intelligence in medicine has brought remarkable benefits, ranging from the recording of medical information to the discovery of new drugs. It has generated a revolution in the traditional way of doing medicine. On the other hand, it has brought with it challenges in terms of accuracy, reliability, ethics, privacy, among others. It is crucial to maintain a patient-centred approach and ensure that these technologies are used to improve health outcomes and promote equity in access to care. Collaboration between healthcare professionals, researchers, regulators and technology developers will be critical to address these challenges and realise the full potential of artificial intelligence.

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.

O uso de sistemas de inteligência artificial para a personalização da experiência do paciente: a percepção de gestores de tecnologia e inovação de hospitais associados à ANAHP / The use of artificial intelligence systems for patient experience personalization: the perception of technology and innovation managers at hospitals associated with ANAHP

Objetivo: O presente trabalho explora a percepção de gestores das áreas de Tecnologia e Inovação de hospitais privados brasileiros acerca do uso da inteligência artificial (IA) na saúde, com foco específico na personalização da experiência do paciente nesses hospitais. Métodos: Este trabalho se caracteriza como uma pesquisa descritiva transversal quantitativa. Foi desenvolvido um questionário com 14 questões que foi distribuído a uma amostra de gestores de tecnologia e inovação em hospitais, com o apoio da Associação Nacional de Hospitais Privados (ANAHP). O questionário foi disponibilizado em versão online à base de 122 hospitais associados à ANAHP. Resultados: Foram obtidas 30 respostas completas (aproximadamente 25% da base total), conquistando percepções sobre as vantagens, desvantagens e desafios éticos e técnicos relacionados ao emprego da IA na área clínica, particularmente em ambientes hospitalares. As respostas coletadas ratificaram o otimismo e a reserva dos profissionais de tecnologia e inovação em hospitais privados quanto ao poder e aos impactos da IA na personalização da experiência do paciente, bem como indicaram a necessidade de treinamento adequado para os funcionários desses hospitais, a fim de maximizar os benefícios da IA como ferramenta de apoio à tomada de decisão. Conclusões: Este trabalho é uma fonte de consulta para instituições de saúde que considerem utilizar a IA na personalização da experiência do paciente e queiram estabelecer treinamentos de pessoal baseados nesses princípios. Desse modo, os resultados aqui obtidos oferecem orientações valiosas para a adoção plena de IA no setor de saúde.

Objective: This study explores the perception of managers in the Technology and Innovation areas of Brazilian private hospitals regarding the use of artificial intelligence (AI) in healthcare, specifically focusing on patient experience personalization in these hospitals. Methods: This study is characterized as a quantitative cross-sectional descriptive research. A questionnaire with 14 questions was developed and distributed to a sample of technology and innovation managers in hospitals, with the support of the National Association of Private Hospitals (NAPH). The questionnaire was made available online to a base of 122 hospitals associated with NAPH. Results: 30 complete responses were obtained (nearly 25% of the total base), capturing perceptions on the advantages, disadvantages, and ethical and technical challenges related to the use of AI in clinical settings, particularly in hospital environments. The collected responses affirmed the optimism and caution of technology and innovation professionals in private hospitals regarding the power and impacts of AI on patient experience personalization, and indicated the need for adequate training for employees in these hospitals to maximize the benefits of AI as a decision support tool. Conclusions: This study serves as a reference for healthcare institutions considering the use of AI in patient experience personalization and aiming to establish personnel training based on these principles. Thus, the results obtained here offer valuable guidance for the full adoption of AI in the healthcare sector.

Trends and patterns of orthognathic surgery in Saudi Arabia: a visualized bibliometric analysis of research output

This study conducted a bibliometric analysis of orthognathic surgery research from Saudi Arabia between 1994 and 2024 in the Web of Science database. The goal was to evaluate Saudi Arabia's influence in the field and implications worldwide. Relevant keywords were used without year restrictions to search for articles. Biblioshiny and VOS viewer were used to analyse and visualize the bibliometric data, including total citations, h-index, and number of papers. The results show that Saudi Arabia has significantly increased its orthognathic surgery research production over time, especially in 2021 and 2023. King Saud University and King Abdulaziz University emerged as the leading institutions in number of papers. The most cited work was an expert review on using artificial intelligence for orthodontic diagnosis and planning orthognathic surgeries. This represents meaningful progress in combining technology with orthognathic surgery. Alhammad, Alnofaie, and Al-Sebaei were identified as the most productive individual authors, each authoring around three papers. The bibliographic analysis highlights the need for increased cooperation between Saudi institutions to boost research outputs and advance the application of new technologies in orthognathic surgery. The study serves as a foundation for further developing orthognathic surgery research in Saudi Arabia, which remains one of the few developing nations showing promising potential for growth in this area.

Identification of Spices and their Adulterants by Integrating Machine Learning and Analytical Techniques: A Representative Study

This multidisciplinary research presents a comprehensive method to tackle the widespread problem of spice adulteration, which represents substantial risks to both public health and spices authenticity. A comprehensive approach is developed to authenticate spices with high accuracy and efficiency by combining old methods with contemporary approaches such as machine learning and artificial intelligence. This paper presents a specific case study where machine learning models, specifically using transfer learning with proven frameworks like MobileNetV2, were effectively employed. The models achieved an impressive accuracy of 98.67% in identifying Capsicum annum, a spice that is usually adulterated in the market. In addition, a wide range of traditional and advanced techniques, including qualitative testing, microscopy, colorimetry, density measurement, and spectroscopy, are reviewed closely. In addition, this article provides a detailed explanation of high-performance liquid chromatography based quantitation of capsaicin, which is the main active constituent for ascertaining the quality of C. annum. The present work defines a new interdisciplinary approach and also provides valuable information on evaluating the quality of spices and identifying adulterants using artificial intelligence. The outcomes presented here have the potential to completely transform the methods used to verify the authenticity of spices and herbal drugs, therefore ensuring the safety and health of consumers by confirming the quality.

Uso de aplicativo de inteligência artificial como fonte de informação para resolução de provas de Odontologia / Use of an artificial intelligence application as a source of information for solving Dentistry exams

Introdução: O ChatGPT® é uma ferramenta pública desenvolvida pela OpenAI que utiliza a tecnologia do modelo de linguagem GPT. Este chatbot é capaz de atender a variadas solicitações de texto. Objetivo: avaliar se o ChatGPT® é capaz de ser a única fonte de informação para resolução de provas de Odontologia. Material e métodos: consiste em um estudo transversal quantitativo analítico. Para a coleta de dados, foi elaborada uma prova fictícia constituída por questões do ENADE e de outros concursos públicos. Os participantes responderam a prova em dois momentos: T1, sem o ChatGPT® e, após 15 dias (T2), utilizando-o. A amostra foi de 30 discentes de graduação em Odontologia, divididos igualmente entre 3 grupos: 1º ao 4º semestre, 5º ao 6º semestre e 7º ao 10º semestre. Para análise de dados foram aplicadas análises estatísticas descritiva e inferencial, por meio do software SPSS, com os testes de Wilcoxon e de McNemar. Resultados: revelaram uma eficácia notável do ChatGPT® na resolução de questões discursivas, com 83,3% de taxa de acerto, enquanto os discentes deram mais respostas incorretas ou incompletas. Porém, foram observadas limitações da base de dados do ChatGPT® quanto às questões objetivas. É crucial ressaltar que, apesar de resultados promissores, a aplicação do Chat levanta questões éticas e pedagógicas. Assim, a introdução do ChatGPT® na educação preocupa quanto à validade e equidade nas avaliações, destacando a importância de encontrar equilíbrio entre a inovação tecnológica e a preservação da integridade acadêmica

Introduction: ChatGPT® is a public tool developed by OpenAI that employs the language model technology of GPT. This chatbot is capable of addressing various text-based requests. Objective: To assess whether ChatGPT® can be the sole source of information for resolving Dentistry exams. Materials and Methods: This is an analytical quantitative cross-sectional study. For data collection, a fictitious exam was created, consisting of questions from the National Student Performance Exam (ENADE) and other public competitions. Participants answered the exam at two different times: T1, without ChatGPT®, and, after 15 days (T2), using it. The sample included 30 undergraduate Dentistry students, equally divided into three groups: 1st to 4th semester, 5th to 6th semester, and 7th to 10th semester. Descriptive and inferential statistical analyses were applied using SPSS software, including the Wilcoxon and McNemar tests. Results: They revealed a notable effectiveness of ChatGPT® in resolving essay questions, with an 83.3% accuracy rate, while students provided more incorrect or incomplete answers. However, limitations of the ChatGPT® database were observed regarding objective questions. It is crucial to emphasize that, despite promising results, the application of Chat raises ethical and pedagogical questions. Therefore, the introduction of ChatGPT® in education raises concerns about the validity and fairness of assessments, underscoring the importance of finding a balance between technological innovation and the preservation of academic integrity

El principio ético de la intervención humana en la responsabilidad civil

Una de las mayores complejidades que se presentan respecto de la responsabilidad civil por daños causados por sistemas de inteligencia artificial viene dada por la dificultad de atribuir la conducta que causa daño a un sujeto particular. Frente a ello, este artículo expone la importancia del principio ético de la intervención humana para la responsabilidad civil, cuya función consiste en constituir la guía para la interpretación y aplicación de sus reglas en los casos en los que, como resultado de una acción u omisión emanada de una decisión, recomendación o predicción realizada por un sistema de inteligencia artificial, se causen daños a las personas.

One of the main challenges associated with regard to civil liability for damages resulting from artificial intelligence systems is the difficulty of attributing the behavior that led to harm to a specific individual. The aim of this article is to highlight the significance of the ethical principle of human intervention for civil liability. This principle serves as a guide for interpreting and applying rules when artificial intelligence systems cause harm to individuals due to actions, decisions, recommendations or predictions.

Uma das maiores complexidades que se apresentam a respeito da responsabilidade civil por danos causados por sistemas de inteligência artificial vem dada pela dificuldade de atribuir a conduta que causa dano a um sujeito particular. Frente a isso, este artigo expõe a importância do princípio ético da intervenção humana para a responsabilidade civil, cuja função consiste em constituir uma orientação para a interpretação e aplicação de suas regras nos casos em que, como resultado de uma ação ou omissão emanada de uma decisão, recomendação ou previsão realizada por um sistema de inteligência artificial, se cause danos às pessoas.

Automatic Auditing System for Endoscopic Exploration of the Stomach with Artificial Intelligence-Gastro UNAL: Gastroendoscopy UNit for Automatic Labeling / Sistema de auditoría automática para la exploración endoscópica del estómago con Inteligencia Artificial - Gastro UNAL: Gastroendoscopy UNit for Automatic Labeling

Abstract Introduction: Upper endoscopy is the standard method for diagnosing early-stage gastric cancer. However, according to estimates, up to 20% of tumors are not detected, and their accuracy may be affected by the variability in their performance. In Colombia, most diagnoses take place in advanced stages, which aggravates the problem. Protocols have been proposed to ensure the complete observation of areas prone to premalignant lesions to address variability. Objective: To build and validate an automatic audit system for endoscopies using artificial intelligence techniques. Methodology: In this study, 96 patients from a teaching hospital underwent video-documented endoscopies, spanning 22 stations rearranged to minimize overlaps and improve the identification of 13 key gastric regions. An advanced convolutional network was used to process the images, extracting visual characteristics, which facilitated the training of artificial intelligence in the classification of these areas. Results: the model, called Gastro UNAL, was trained and validated with images of 67 patients (70% of cases) and tested with 29 different patients (30% of cases), which reached an average sensitivity of 85,5% and a specificity of 98,8% in detecting the 13 gastric regions. Conclusions: The effectiveness of the model suggests its potential to ensure the quality and accuracy of endoscopies. This approach could confirm the regions evaluated, alerting less experienced or trained endoscopists about blind spots in the examinations, thus, increasing the quality of these procedures.

Resumen Introducción: La endoscopia digestiva alta es el método estándar para diagnosticar el cáncer gástrico en etapas tempranas. Sin embargo, su precisión puede verse afectada por la variabilidad en su realización, y se estiman hasta 20% de tumores no detectados. En Colombia, la mayoría de los diagnósticos se realizan en etapas avanzadas, lo que agrava el problema. Para abordar la variabilidad, se han propuesto protocolos con el fin de asegurar la observación completa de áreas propensas a lesiones premalignas. Objetivo: Construir y validar un sistema de auditoría automática para endoscopias usando técnicas de inteligencia artificial. Metodología: En este estudio, 96 pacientes de un hospital universitario se sometieron a endoscopias documentadas en video, abarcando 22 estaciones reorganizadas para minimizar solapamientos y mejorar la identificación de 13 regiones gástricas clave. Se utilizó una red convolucional avanzada para procesar las imágenes, extrayendo características visuales, lo que facilitó el entrenamiento de la inteligencia artificial en la clasificación de estas áreas. Resultados: El modelo, llamado Gastro UNAL, fue entrenado y validado con imágenes de 67 pacientes (70% de los casos) y probado con 29 pacientes distintos (30% de los casos), con lo que alcanzó una sensibilidad promedio del 85,5% y una especificidad del 98,8% en la detección de las 13 regiones gástricas. Conclusiones: La eficacia del modelo sugiere su potencial para asegurar la calidad y precisión de las endoscopias. Este enfoque podría confirmar las regiones evaluadas, alertando puntos ciegos en la exploración a los endoscopistas con menos experiencia o en entrenamiento, de tal forma que se aumente la calidad de estos procedimientos.

La era de la inteligencia artificial y su impacto en el aprendizaje de habilidades quirúrgicas de grado y posgrado: ¿El futuro de la cirugía? / The age of artificial intelligence and its impact on learning surgical skills: is it the future of surgery?

RESUMEN Los cambios en la educación desafían a los profesores sobre cómo enseñar de la mejor manera y mejorar el desempeño de sus estudiantes. En el caso de la cirugía es necesario adquirir habilidades manuales que reflejen el pensamiento crítico y la capacidad de tomar decisiones en situaciones complejas, de manera rápida y eficaz. Así, la inteligencia artificial (IA) es una nueva herramienta que puede mejorar el desempeño de los estudiantes de grado y posgrado, así como repercutir en mejores desenlaces clínicos. El papel que debe desempeñar la enseñanza tradicional y el futuro de la enseñanza quirúrgica son cuestiones para resolver.

ABSTRACT Educational changes present a challenge for teachers in terms of how to effectively teach and enhance student performance. Surgery demands manual dexterity that reflects critical thinking and the ability to make efficient decisions quickly in complex situations. Artificial Intelligence (AI) is a tool that can enhance the performance of both undergraduate and graduate students and improve clinical outcomes. The role of traditional teaching and the future of surgical education need to be addressed.

Normas sociales, publicidad y consumo alimentario en escolares: modelado mediante lógica difusa tipo 2 / Social norms, advertising and food consumption in schoolchildren: modeling using fuzzy logic

Resumen: México ocupa el primer lugar en obesidad infantil en el mundo, por lo que resulta importante identificar variables asociadas al consumo alimentario. El objetivo del presente trabajo fue establecer si la forma en que el consumo de alimentos se modifica en función de las normas sociales alimentarias y la publicidad alimentaria que recibe la población infantil escolar. Se diseñó un estudio multivariado predictivo utilizando sistemas de lógica difusa tipo dos de intervalo (IT2 FLS), y comparando su ajuste con modelos convencionales, como la regresión lineal múltiple (RLM). Se trabajó con las respuestas emitidas por 196 niños en un estudio previo y almacenadas en una base de datos, seleccionando solo las que correspondieron a las variables de interés para el estudio. Las normas sociales a evitar, el número de comidas y la compra de alimentos por la publicidad alimentaria permitieron predecir el consumo alimentario de los niños mediante IT2 FLS. En RLM las horas de comidas tuvo mayor capacidad predictiva que el número de comidas. El IT2 FLS proporcionó un mayor coeficiente de determinación (R2 = 0.649), que el de la RLM (R2 = 0.370). El consumo alimentario, al ser un fenómeno multicausal y complejo, puede ser mejor predicho al utilizar métodos de análisis que manejen de forma más flexible la incertidumbre, como lo hace la IT2 FLS.

Abstract: Mexico ranks first in childhood obesity in the world, so it is important to identify variables associated with food consumption. The objective of this work was to establish whether the way in which food consumption is modified depending on social food norms and food advertising received by school children. A predictive multivariate study was designed using interval type two fuzzy logic systems (IT2 FLS), and comparing its fit with conventional models, such as multiple linear regression (RLM). We worked with the responses issued by 196 children in a previous study and stored in a database, selecting only those that corresponded to the variables of interest for the study. The social norms to avoid, the number of meals and the purchase of food through food advertising made it possible to predict children's food consumption through IT2 FLS. In RLM, mealtimes had a greater predictive capacity than the number of meals. The IT2 FLS provided a higher coefficient of determination (R2 = 0.649) than that of the RLM (R2 = 0.370). Food consumption, being a multicausal and complex phenomenon, can be better predicted by using analysis methods that manage uncertainty more flexibly, as the IT2 FLS does.

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.

Accuracy and validity of common dental terms using chat GPT model: a cross-sectional study

Background: Chat generative pre-trained transformer, an artificial intelligence chatbot can generate text-based content for information purpose. This study aims to find the accuracy and reliability of the chat GPT generated definitions for 30 common dental terms. Methods: A 15 current dental teaching staffs grading from Professors and Readers of various specialities participated in this study. They graded the chat GPT generated terms on a 5-point Likert scale (1- Strongly disagree, 2- Disagree, 3- Neutral, 4- Agree, 5- Strongly disagree). Scores were obtained and descriptive statistics was done and compared using Mann-Whitney U test. Results: Among 30 dental terms, 13 terms which were generated from the chat GPT model were found to be more appropriate when compared to text book definition. On comparison of reviewers’ perceptions for accuracy of definitions generated from chat GPT compared with text book definitions in which among the 30 dental terms, 9 terms were found to be statistically significant (p<0.05*). Conclusions: Chat GPT is a potential tool for answering knowledge based questions with equal vigor in the field of dentistry. Moreover, the accuracy of Chat GPT to solve questions in dentistry has a relational level of accuracy.

Evaluación de signos vitales mediante una aplicación móvil en pacientes con insuficiencia cardiaca: ¿una oportunidad para la titulación remota? / Evaluation of vital signs through a mobile application in patients with heart failure: a opportunity for remote titration?

Resumen Antecedentes: Las consultas virtuales aumentaron exponencialmente, pero presentan como limitación la imposibilidad de valorar los signos vitales (SV), siendo especialmente útiles en los pacientes con insuficiencia cardiaca (IC) para titular medicación que modifica pronóstico. Este problema podría potencialmente solucionarse mediante una herramienta que pueda medir la presión arterial (PA) y frecuencia cardiaca (FC) de manera precisa, accesible y remota. Los teléfonos móviles equipados con tecnología de imágenes ópticas transdérmicas podrían cumplir con estos requisitos. Objetivo: Evaluar la precisión de una app basada en imagen óptica transdérmica para estimar SV en relación con la valoración clínica en pacientes con IC. Métodos: Estudio de cohorte prospectivo, se incluyeron pacientes evaluados en una unidad ambulatoria de IC de febrero a abril del 2022. Se valoró simultáneamente la PA y FC mediante la app y el examen clínico (PA con un esfigmomanómetro automatizado y FC por palpación braquial). Se realizaron tres mediciones por app y clínica en cada paciente, por dos médicos independientes, encontrándose ciegos a los resultados. Resultados: Se incluyeron 30 pacientes, con 540 mediciones de TA y de FC. Edad media de 66 (± 13) años, el 53.3% de sexo masculino. La fracción de eyección del ventrículo izquierdo media fue de 37 ± 15, con hospitalizaciones previas por IC el 63.3%, en CF II-III el 63.4%. La diferencia media entre la medición de la app y su medición de referencia clínica fue de 3.6 ± 0.5 mmHg para PA sistólica (PAS), 0.9 ± -0.2 mmHg para PA diastólica (PAD) y 0.2 ± 0.4 lpm para FC. Cuando se promedian las diferencias medias emparejadas para cada paciente, la media entre los 30 pacientes es de 2 ± 6 mmHg para PAS, -0.14 ± 4.6 mmHg para PAD y 0.23 ± 4 lpm para FC. Conclusión: La estimación de PA y FC por una app con tecnología de imagen óptica transdérmica fue comparable a la medición no invasiva en pacientes con IC, y cumple los criterios de precisión de la medición de PA en este estudio preliminar. La utilización de esta nueva tecnología de imagen óptica transdérmica brinda datos prometedores, que deberán ser corroborados en cohortes de mayor tamaño.

Abstract Background: Virtual consultations have increased exponentially, but a limitation is the inability to assess vital signs (VS). This is particularly useful in patients with heart failure (HF) for titrating prognosis-modifying medication. This issue could potentially be addressed by a tool capable of measuring blood pressure (BP) and heart rate (HR) accurately, remotely, and conveniently. Mobile phones equipped with transdermal optical imaging technology could meet these requirements. Objective: To evaluate the accuracy of a transdermal optical imaging-based app for estimating VS compared to clinical assessment in patients with HF. Methods: A prospective cohort study included patients evaluated in an HF outpatient unit between February and April 2022. BP and HR were simultaneously assessed using the app and clinical examination (BP with an automated sphygmomanometer and HR by brachial palpation). Three measurements were taken by both the app and clinic for each patient, by two independent blinded physicians. Results: Thirty patients were included, with 540 measurements of BP and HR. The mean age was 66 (± 13) years, 53.3% were male. The mean left ventricular ejection fraction was 37 ± 15, with 63.3% having previous hospitalizations for HF, and 63.4% in NYHA class II-III. The mean difference between the app measurement and its clinical reference measurement was 3.6 ± 0.5 mmHg for systolic BP (SBP), 0.9 ± -0.2 mmHg for diastolic BP (DBP), and 0.2 ± 0.4 bpm for HR. When averaging the paired mean differences for each patient, the mean across the 30 patients was 2 ± 6 mmHg for SBP, -0.14 ± 4.6 mmHg for DBP, and 0.23 ± 4 bpm for HR. Conclusion: The estimation of BP and HR by an app with transdermal optical imaging technology was comparable to non-invasive measurement in patients with HF and met the precision criteria for BP measurement in this preliminary study. The use of this new transdermal optical imaging technology provides promising data, which should be corroborated in larger cohorts.

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.