Cardiovascular diseases (CVDs) are the leading cause of mortality worldwide, with Latin America facing unique challenges due to socioeconomic disparities, limited healthcare resources, and fragmented medical infrastructures. Artificial Intelligence (AI) has emerged as a transformative technology in CVD management, offering potential solutions for early diagnosis, risk stratification, and treatment optimization. However, the adoption of AI in Latin America remains underexplored. This narrative review synthesizes the current state of AI applications in cardiovascular healthcare across the region, analyzing trending research, challenges, and opportunities based on 22 selected studies. The findings highlight a growing interest in AI-driven predictive models, clinical decision support systems, and remote monitoring technologies. Machine learning (ML) techniques have demonstrated promising results in improving CVD diagnosis and prognosis. However, significant barriers such as data scarcity, interoperability challenges, and regulatory limitations hinder widespread clinical implementation. Several studies utilized local datasets, while others relied on international repositories, raising concerns about model generalizability to Latin American populations. Despite these limitations, AI presents an opportunity to bridge healthcare gaps by enabling more efficient and accessible CVD management. This review underscores the need for region-specific AI research, enhanced data-sharing frameworks, and collaborative efforts among healthcare institutions, policymakers, and technology developers. By addressing these challenges, AI has the potential to substantially advance cardiovascular healthcare in Latin America, improving patient outcomes and reducing the burden of CVDs in resource-limited settings.Clinical Relevance— This review evaluates AI’s role in cardiovascular disease management in Latin America, identifying key techniques, ML implementations, challenges and opportunities.

Cardiovascular diseases are the leading cause of mortality worldwide. In 2021, an estimated 48 million individuals in Latin America were living with heart and circulatory diseases. In the context of liver transplantation, cardiometabolic risk factors play a crucial role not only during the procedure but also in the long-term post-transplantation period, significantly impacting patient survival and recovery. This study analyzes a cohort from the National Liver Transplantation Program of Uruguay, employing machine learning to predict the occurrence of post-transplant cardiometabolic diseases based on pre-transplant health indicators. Over a five-year period, multiple machine learning models were evaluated, with the Extra Trees algorithm achieving the highest predictive accuracy of 88% (AUC: 0.94). The findings highlight the potential of predictive analytics in improving early risk assessment and preventive strategies, ultimately enhancing the prediction of patient outcomes in liver transplantation.Clinical Relevance— This is the first national-level study validating machine learning algorithms for cardiometabolic risk prediction in liver transplantation patients within the National Liver Transplantation Program in Uruguay. By leveraging pretransplant clinical data, the proposed model provides a data-driven approach for early risk stratification, supporting clinicians in making informed decisions to mitigate post-transplant cardiometabolic complications.

Clinical Decision Support Systems (CDSS) based on machine learning offer a promising approach to improve decision-making in nephrology by enabling predictive insights from complex clinical data. In this work, we present a modular, web-based CDSS that automates the machine learning pipeline, including data ingestion, preprocessing, model training, feature selection, and evaluation. The system supports both categorical and continuous outcomes and dynamically adapts the workflow based on the input data structure and selected target variable. The platform was applied to a real-world dataset of 854 hemodialysis patients from Uruguay, with the objective of predicting treatment discontinuation outcomes—specifically distinguishing between patients who continued treatment and those who died. Following class balancing and variable selection, a total of 36 model configurations were evaluated using cross-validation. Performance was assessed using metrics like accuracy, F1 score, Area Under the Curve (AUC), confusion matrices, and ROC analysis. Models such as logistic regression and random forests demonstrated robust classification performance, with several configurations achieving AUC values above 0.72. Consistently selected predictive features included vascular access type, pre- and post-dialysis body weight, and specific clinical markers. The system also enabled interactive prediction on new input instances, ensuring reproducibility and transparency in the decision process. The results demonstrate the applicability of the proposed CDSS in nephrology, supporting early identification of high-risk patients and contributing to improved care planning in dialysis programs.

Liver transplantation is the ultimate therapeutic option for patients with end-stage liver disease. The clinical management of transplant patients significantly impacts their prognosis, with outcomes influenced by multiple interacting variables. Cardiovascular complications count as a leading cause of both short-term and long-term morbidity and mortality in liver transplant recipients. In this respect, accurate risk assessment and stratification are crucial for optimizing clinical outcomes. Modern artificial intelligence (AI) techniques have significant potential for early risk prediction, providing comprehensive risk assessments in both diagnosed cohorts and early clinical phase patients. This systematic review examines the state of the art in AI applications for predicting cardiovascular risks in liver transplantation, identifying current issues, challenges, and future research directions. We reviewed articles from digital repositories such as PubMed, IEEE Xplore, and ScienceDirect published between 2000 and 2023, using keywords including artificial intelligence, machine learning, cardiovascular, and liver transplantation. Our analysis revealed a diverse range of machine learning algorithms used in this domain. Despite the potential, only 12 papers met the criteria for adequate topic coverage, highlighting a scarcity of research at this intersection. Key challenges include integrating diverse datasets, isolating cardiovascular effects amid multifaceted influences, ensuring data quality and quantity, and the issues to extrapolate machine learning models to day-to-day clinical practice. Nevertheless, leveraging AI for risk prediction in liver transplantation could significantly enhance patient management and resource optimization, indicating a shift towards more personalized and effective medical practices.

Arterial stiffness serves as a marker of arterial damage in various diseases, including chronic kidney disease (CKD) and renal replacement therapies such as Hemodialysis (HD) and Peritoneal Dialysis (PD). This study measured pulse wave velocity (PWV) in a dialysis population, analyzing variables associated with cardiovascular risk. Notably, the study applied statistical analysis, integrating machine learning for developing prediction models, to potentially identify patients without significant clinical signs of cardiovascular disease but with silent structural or functional damage.

Artificial Intelligence (AI) and machine learning are the current forefront of computer science and technology. AI and related sub-disciplines, including machine learning, are essential technologies which have enabled the widespread use of smart technology, such as smart phones, smart home appliances and even electric toothbrushes. It is AI that allows the devices used day-to-day across people’s personal lives, working lives and in industry to better anticipate and respond to our needs. However, the use of AI technology comes with a range of ethical questions – including issues around privacy, security, reliability, copyright/plagiarism and whether AI is capable of independent, conscious thought. We have seen several issues related to racial and sexual bias in AI in the recent times, putting the reliability of AI in question. Many of these issues have been brought to the forefront of cultural awareness in late 2022, early 2023, with the rise of AI art programs (and the copyright issues arising from the deep-learning methods employed to train this AI), and the popularity of ChatGPT alongside its ability to be used to mimic human output, particularly in regard to academic work. In critical areas like healthcare, the errors of AI can be fatal. With the incorporation of AI in almost every sector of our everyday life, we need to keep asking ourselves— can we trust AI, and how much? This Editorial outlines the importance of openness and transparency in the development and applications of AI to allow all users to fully understand both the benefits and risks of this ubiquitous technology, and outlines how the Artificial Intelligence and Machine Learning Gateway on F1000Research meets these needs.

With the increasing impact of artificial intelligence in the domain of healthcare, unsupervised learning techniques have been in discussion for the detection of hidden patterns or relationships between different data features. The domain of mental health is no exception. This paper presents an unsupervised machine learning approach to analyze the presence of depression and anxiety. It presents unsupervised models to analyze depression based on depression-related data of a student cohort containing demographic and academic data along with depression information collected through the Beck Depression Inventory questionnaire, in addition to scores such as the PHQ (Patient Health Questionnaire) score, GAD (Generalized Anxiety Disorder) score, and Epworth score, which provide insights into the severity and impact of depressive symptoms, anxiety symptoms, and daytime sleepiness, respectively. The methodology involves data collection and preparation, feature selection, modeling, anomaly detection, and analysis of the relationships between different features.

Predictive modeling techniques using artificial intelligence have shown promising potential in detecting and predicting depression in recent times, adding newer perspectives to mental health assessment and treatment. This paper presents a predictive modeling approach to detect the presence of depression using machine learning techniques. It presents predictive models to detect depression based on depression-related data of a student cohort containing demographic and academic data along with depression information collected through the Beck Depression Inventory questionnaire, in addition to scores such as the PHQ (Patient Health Questionnaire) score, GAD (Generalized Anxiety Disorder) score, and Epworth score, which provide insights into the severity and impact of depressive symptoms, anxiety symptoms, and daytime sleepiness, respectively. The methodology involves data collection and preparation, feature selection, model selection, and model training using machine learning techniques. The results show the performance metrics of different predictive models on various dataset versions generated through preprocessing steps such as normalization, feature encoding, and selection. The best metrics are compared and evaluated, where the Linear Discriminant Analysis model performed best in terms of AUC, F1 score, and other metrics in this specific cohort. Considering the recent advancements of machine learning, incorporating predictive modeling would be important to designing clinical decision support systems, for a comprehensive prediction and analysis of depression in different cohorts, to act as an assistive tool for mental health professionals.

Research and innovation in the domain of technology have seen a strong transformation to transdisciplinary collaboration in recent years. Fields like Artificial Intelligence have amplified their scope, transcending through various disciplines of science and engineering. In the domain of healthcare in Latin America, digital transformation through data science has extended from the top to bottom, extending from digital administration and data-backed healthcare policies on one hand, smart eHealth devices and intelligent monitoring through Internet of Things and machine learning, on the other hand. The third sustainable development goal of the United Nations is "good health and well-being." In this aspect, Artificial Intelligence plays a strong role in predictive, preventive, participatory, and personalized healthcare. This chapter focuses on a holistic view of the digital transformation of healthcare in Latin America through Artificial Intelligence and transdisciplinary cooperation. It is based on the following aspects – strategic collaboration between the medical and engineering domains like physics, electronics, statistics, biology, and computer science for seamless transfer of technology, harnessing data science tools of machine learning for accurate predictions of diseases, thus exercising preventive healthcare, and integration of education, research, and innovation through international academic and scientific collaborations. This work illustrates the focal goal of providing healthcare services following best practices through digital data-powered transformations and transdisciplinary exchange around medicine and bioengineering in a Latin American perspective.

INTRODUCTION: Arterial wall viscosity is a source of energy dissipation that takes place during mechanical transduction. In our previous studies, a "global" damping effect in endurance training athletes was introduced, verifying that endurance-athletes dissipate greater pulsatile energy in the circulation compared with healthy untrained subjects. OBJECTIVE: To investigate the wall energy dissipation in the vascular bed for each beat and within the conceptual framework of ventricular-arterial coupling, in order to elucidate if different types of training could lead to differentiated levels of cardiovascular energy dissipation. MATERIALS AND METHODS: Data from subjects with different kinds of training (soccer players and ballet dancers) have been collected noninvasively and compared with a control group of untrained individuals to analyse the differentiating characteristics of the subjects, especially in terms of Stroke Work Dissipation (WDIS). RESULTS: In the endurance-trained individuals, an enhanced WDIS has been observed compared to the untrained individuals (p<0.05). However, non-significant differences were found regarding ballet-dancers group. CONCLUSION: Changes in wall energy dissipation are developed under high intensity endurance training routines.

Recent years have seen increasing use of artificial intelligence in the domain of healthcare and mental health is no exception. This study is focused on the particular aspect of depression, which affects a significant percentage of the population and is an important concern globally. This systematic review analyzes different methods based on artificial intelligence to diagnose depression, highlighting the global trends of this domain like the huge share of natural language processing algorithms and neural networks on one hand, and illustrating the key issues and future lines of research in applying artificial intelligence in the domain of mental health, on the other hand.

Cheiloscopy is a technique of forensic investigation with the purpose of identifying humans based on their lip prints. Analyzing the lip prints in detail, detailed characteristics could be deciphered, establishing a unique link with a specific person, thus helping in identification in persons using lip prints. Machine learning has significant applications in this forensic identification process with cheiloscopy, spanning from data collection to intelligent analysis. In this work, a design for a forensic decision support system has been proposed, aimed at identification of persons in terms of their biological sex based on cheiloscopy. In this respect, a generalized architecture for the implementation of cheiloscopy has been presented, along with the predictive modeling with lip prints using supervised algorithms, which has illustrated reasonable accuracy in identifying persons in terms of their biological sex.

In the field of agriculture, there are many individual micro businesses with low investment capacity and awareness of IT utilization, and it is difficult to obtain a return on investment. In recent years, edge computing and Artificial Intelligence (AI) technologies have attracted a lot of attention in the agricultural industry to cover the labor shortage. Also, safer vegetables are required by peoples due to COVID-19 epidemic and radioactive pollution. In this paper, we propose an agricultural support system called VegeCareAI for agricultural workers. The proposed system supports vegetable classification, plant disease classification and insect pest classification to improve the crops’ productively. The support system can show the growth condition of vegetables. When there are some problems, the VegeCareAI presents information on how to deal with diseases and insect pests. From the results, we found that our proposed VegeCareAI tool has advantage for supporting several crops. For vegetable classification, our training data for 300 epochs predicted six kinds of vegetables correctly. For plant disease classification, for 400 epochs the accuracy is more than 96% accuracy for both potato and corn leaves. For insect pest classification, the accuracy of corn insect pests is more than 73%, but the results of different life cycles showed low classification accuracy, which present a future challenge.

Liver transplantation is the last therapeutic option in patients with end-stage liver diseases. The adequate clinical management of transplant-patients impacts their vital prognosis and decisions on many occasions are made from the interaction of multiple variables involved in the process. This work is based on the National Liver Transplantation Program in Uruguay. We performed predictive analysis of cardiometabolic diseases on the transplanted cohort between 2014 and 2019, considering vascular age as a key factor. This aims at classification of the cohort based on the vascular age of the evaluated patients before transplantation for risk-profiling. Predicted high-risk group of the patients showed substantial deterioration of post-transplant health-conditions, including higher mortality rate. In our knowledge, this is the first study in Latin America incorporating vascular age toward predictive analysis of cardiometabolic risk factors in liver transplantations. Predictive risk-modeling using vascular age in a pre-transplantation scenario provides significant opportunity for early prediction of post-transplant risk factors, leading to efficient treatment with anticipation.

INTRODUCTION: Global education has seen a paradigm shift in the recent years; especially in life sciences, specializations have started sharing common space in applied research and development. Extending the transdisciplinary approach to undergraduate programs, a case study on the introductory course of Biological Engineering program at University of the Republic (Universidad de la República) Uruguay is presented. OBJECTIVES: The COVID-19 pandemic has led to shifting the biological engineering course to virtual modality, changing the pedagogical dynamics. This study aims at analyzing the adaptation to the new model of virtual learning. METHODS: Different course metrics over time has been analyzed along with surveys on students and professors of the course. RESULTS: Despite several new challenges posed by the virtual modality, the overall student-performance didn't decline. CONCLUSION: The biological engineering course presents interesting contents especially in its course design and student engagements, remodeled especially during its virtual mode.