Prostate cancer (PC) mortality in Latin America is reported to be twice as high as in developed countries. Combination therapies, such as androgen deprivation therapy (ADT) combined with new hormonal therapies (NHT), are known to improve survival, but their effectiveness in Latin American populations remains understudied. This knowledge limitation can be addressed using artificial intelligence (AI). In this study, an AI and Natural Language Processing (NLP) tool was developed by the Hospital Italiano de Buenos Aires's (HIBA) healthcare AI program in collaboration with the oncology department, to extract, encode, and analyze electronic health record (EHR) data. The data were collected from patients diagnosed with metastatic castration-sensitive prostate cancer (mCSPC) at HIBA, from 2010 to 2020, with a focus on first-line treatment patterns. Performance metrics, including precision, recall, and F1 score, were evaluated for several key variables. For "prostate cancer diagnosis," recall was 0.95, and for "metastasis development detection," recall was 0.91. Regarding "initiation of first-line treatment," precision, recall, and F1 score were 0.94, 0.97, and 0.95, respectively. However, metrics for more complex variables, such as "castration resistance detection," were lower (precision 0.87, recall 0.46, F1 score 0.60). The tool demonstrated adequate recall for metastatic disease diagnosis, although further refinements are needed to enhance performance.

The analysis of large EHR data volumes in adult emergency departments contributes to physician burnout due to time-consuming manual information extraction. To address this, Hospital Italiano de Buenos Aires conducted a pilot study integrating TanaGPT, a generative AI assistant, into emergency consultations. This mixed-methods study assessed usability, adoption, and user perceptions through observations, a UMUX-Lite survey, and interviews. Results show that TanaGPT improved real-time access to patient information, streamlining workflows and reducing EHR navigation time. While improvements in response speed and workflow integration are needed, participants found the tool useful and easy to use, highlighting its potential for broader implementation in time-sensitive clinical settings.

En las últimas décadas, diversas causas convergieron en la generación de un sistema de salud cada vez más ineficaz. Consecuentemente cada vez es mayor la insatisfacción de los pacientes, de los prestadores de salud y de los financiadores de esta. Por ello, es imperioso dejar de insistir en un sistema que día a día tiene más exigencias pero no resuelve los problemas de fondo, e intentar rediseñar el sistema de salud actual. En este texto nos concentraremos en analizar los problemas de cobertura insuficiente o incompleta y los de malos resultados de calidad de los sistemas de salud. Un nuevo paradigma de atención que el Plan de Salud del Hospital Italiano ha adoptado contempla seis pilares para el cambio: 1) Actividades para el automanejo y autocuidado del paciente y su entorno. 2) Sistemas de toma de decisiones, guías clínicas y opiniones de expertos. 3) Recursos comunitarios. 4) Sistemas de información clínica y para el seguimiento de cohortes de enfermos. 5) Cambios organizacionales y rediseño de los sistemas prestacionales. 6) Cambios culturales y financiamiento del sistema de salud. Nuestra experiencia ha demostrado que dicho cambio de paradigma es mejor no solo desde el punto de vista teórico sino también desde nuestra práctica habitual y nuestra investigación clínica y epidemiológica. Se basa en construir verdaderos equipos en la atención ambulatoria (compuesto por médicos de cabecera, especialistas, enfermeros, asistentes sociales, monitores, educadores y coordinadores del programa). También se basa en la activación de los pacientes para que participen del cuidado, y en la utilización de herramientas informáticas modernas para el cuidado habitual y el seguimiento de los casos de mayor riesgo o mala evolución, en especial para aquellos que no consultan adecuadamente al sistema de salud a fin de ofrecerles el cuidado de sus necesidades y no solo de lo que demandan

Emergency Departments (ED) face the growing challenge of providing high-quality, timely patient care. Effective management and performance improvement require the identification of multiple variables and measurements. Quality dashboards are tools that provide timely information to support decision-making. This study aims to describe the design, development, and implementation of an ED quality dashboard, with indicators defined by an interdisciplinary team. A user-centered design for data visualization was performed, and a web-based BI analytical tool was used. Implemented in 2014, the system features a main page displaying a list of various indicators, including process, quality, and safety. Clicking on each indicator reveals detailed graphs and filters. The dashboard provides valuable performance insights and has been instrumental in identifying issues, such as undertriage, along with corresponding solution strategies.

“Usability”, “Human computer interaction”, “Human computer Interface “, “ Cyberpsychology “, are the names ofa group of emerging disciplines seeking to analyze, for purposes ranging from research in cognitive science to the implementation of technological developments, how software developments impact on the daily life of human beings, not onlyas direct users, but also to what extent human beings are immersed in a computerized world. The common background includes human beings and computers, and the psychology of their interaction. It is clear that computers are ubiquitous in every human activity and that clearly affect their behavior from the more obvious aspects, such as the sensory and motor interaction, to much more complex aspects related with cognition, social changes, and ultimately on cultural issues. The objective of this monograph is to make a brief description of the interaction between humans and computers.

This paper presents our methodology for designing, testing, and evaluating a co-pilot tailored for healthcare professionals working in Spanish-speaking contexts. The co-pilot facilitates efficient access to textual information from clinical notes and structured data within Electronic Health Records (EHRs). Its primary objective is to save professionals' time while ensuring accurate information retrieval. The system leverages a Retrieval-Augmented Generation (RAG) architecture powered by state-of-the-art Large Language Models (LLMs). Our evaluation, conducted on a dataset of 3,500 yes/no questions, achieved an F1 score of 0.82, demonstrating its effectiveness in the target domain.

This study explores the development, implementation and preliminary results of an alert integrated into a EHR to de-implement unnecessary colonoscopies for patients aged 75 and older. From August 20 to November 29, 2024, the CDSS generated 567 alerts across 244 physicians and 499 patients. 91.8% of alerts were overridden and 7% were accepted. CDSS alerts to promote evidence-based care and reduce unnecessary procedures among older adults. Future work will focus on enhancing alert specificity and expanding de-implementation strategies to other practices.

Abstract BackgroundInclusive digital health, primary health care (PHC), and resilient health systems (RHS) are vital for equitable health systems in Latin America and the Caribbean (LAC). This paper defines operationally inclusive digital health in the LAC context, analyzes how inclusive digital health principles are integrated into LAC health policies, and offers recommendations for policy, implementation, investment, and evaluation. Methods We conducted a narrative literature review of global studies on digital health advancements for PHC, RHS, and inclusion from 2010 to 2024. Also, we examined the national digital health policies of 26 LAC countries to assess the integration of inclusive digital health into digital health strategies, electronic health records, and telemedicine. FindingsThe LAC region requires a shared language and cohesive strategies to translate inclusive digital health, PHC, and RHS into actionable frameworks: 1. Prioritize populations for tailored interventions. 2. Implement digital solutions for equitable access. 3. Strengthen PHC and resilience through digital technologies. FundingThis study did not receive financial support

Cybersecurity in healthcare is a growing concern as institutions face increasing cyber threats. This study describes a cybersecurity awareness program on healthcare workers at Hospital Italiano de Buenos Aires (HIBA), using simulation-based training and periodic communication initiatives. The program's outcomes showed improvements in staff knowledge and engagement, reinforcing the importance of continuous education. These initiatives emphasize that fostering a robust cybersecurity culture is crucial for mitigating risks and protecting patient data in the healthcare sector.

The Health Informatics Master's Program at Hospital Italiano de Buenos Aires (EMIS-HIBA), launched in 2017, addresses the growing need for skilled professionals in health informatics. This study describes the program, characterizes its student population, and evaluates its alignment with current standards. Key findings reveal gender disparities, with lower female enrollment, and a strong national footprint, with most students from Argentina. The transition to a fully online format in 2023 enhancing accessibility and addressed the need for flexible learning, although retention and graduation rates remain areas for improvement. The curriculum aligns closely with IMIA recommendations but underscores the importance of balancing technical and clinical content. These findings inform strategic program improvements, including continuous curriculum updates, increased female participation, and expanded international outreach. This analysis contributes to understanding the challenges and opportunities in health informatics education and highlights the value of adaptable educational models in fostering a skilled digital health workforce.

The adequate management of patients' genomic information is essential for any health institution pursuing the Precision Medicine model. Here we approach a bioinformatic architecture that allows the Institution to store its whole genetic test data in a scalable database, and also the integration of that genetic data with the Electronic Health Record through a Clinical Decision Support System. The system complements patient care by suggesting referral to genetic counseling for patients who are potentially at risk of hereditary breast/ovarian cancer, and allowing for proper follow-up of patients with pathogenic variants in BRCA1 or BRCA2 genes. The implemented solution uses the FHIR standard and genetic nomenclatures from the Human Genome Variation Society and the HUGO Gene Nomenclature Committee. The architecture is flexible enough to allow any other health institution to integrate -to their information ecosystem- the whole solution or some of the modules according to its degree of digitization progress.

This work aims to assess standard evaluation practices used by the research community for evaluating medical imaging classifiers, with a specific focus on the implications of class imbalance. The analysis is performed on chest X-rays as a case study and encompasses a comprehensive model performance definition, considering both discriminative capabilities and model calibration. We conduct a concise literature review to examine prevailing scientific practices used when evaluating X-ray classifiers. Then, we perform a systematic experiment on two major chest X-ray datasets to showcase a didactic example of the behavior of several performance metrics under different class ratios and highlight how widely adopted metrics can conceal performance in the minority class. Our literature study confirms that: (1) even when dealing with highly imbalanced datasets, the community tends to use metrics that are dominated by the majority class; and (2) it is still uncommon to include calibration studies for chest X-ray classifiers, albeit its importance in the context of healthcare. Moreover, our systematic experiments confirm that current evaluation practices may not reflect model performance in real clinical scenarios and suggest complementary metrics to better reflect the performance of the system in such scenarios. Our analysis underscores the need for enhanced evaluation practices, particularly in the context of class-imbalanced chest X-ray classifiers. We recommend the inclusion of complementary metrics such as the area under the precision-recall curve (AUC-PR), adjusted AUC-PR, and balanced Brier score, to offer a more accurate depiction of system performance in real clinical scenarios, considering metrics that reflect both, discrimination and calibration performance. This study underscores the critical need for refined evaluation metrics in medical imaging classifiers, emphasizing that prevalent metrics may mask poor performance in minority classes, potentially impacting clinical diagnoses and healthcare outcomes.

Dermatology is one of the medical fields outside the radiology service that uses image acquisition and analysis in its daily medical practice, mostly through digital dermoscopy imaging modality. The acquisition, transfer, and storage of dermatology images has become an important issue to resolve. We aimed to describe our experience in integrating dermoscopic images into PACS using DICOM as a guide for the health informatics and dermatology community. During 2022 we integrated the video dermoscopy equipment through a strategic plan with an 8-step procedure. We used the DICOM standard with Modality Worklist and Storage commitment. Three systems were involved (video dermoscopy software, the EHR, and PACS). We identified critical steps and faced many challenges, such as the lack of a final model of DICOM standard for dermatology images.

Drug information tools help avoid medication errors, a common cause of avoidable harm in health care systems. We sought to describe the design, development process and architecture of an electronic drug information tool, as well as its overall use by health professionals. We developed a tool that can be accessed by all health professionals in a tertiary level university hospital. The functionalities of eDrugs are organized into two main parts: Drug Summary sheet, and Prescription Simulator. Most users accessed eDrugs to use the Drug summary sheet. Clinical information and antimicrobial drugs were the most accessed drug information and drug group. The analysis of log data provides insights into the information priorities of health professionals.

From our roles within international public health organizations, we have collectively witnessed the global challenges presented by outdated health information systems, platforms, and applications. The COVID-19 pandemic has clearly exposed the limitations of our current paper-based vaccine certification methods and highlighted the deficiencies of outdated technological platforms that lack interoperability standards, a situation that underscores the critical need for a digital transformation in how we manage and verify immunization records. Digital vaccination certificates are understood to be secure, electronically stored, and easily accessible records that provide verifiable proof of a person's immunization status. The Pan American Health Organization (PAHO) envisions leveraging digital technologies to strengthen health systems, enhance data-driven decision- making, and improve health outcomes. The organization's vision emphasizes the integration of innovative technologies to build resilient and responsive health systems capable of addressing modern public health challenges. In an era of unprecedented technological advancement, our continued reliance on paper-based vaccine certificates is not just anachronistic-it is a significant liability for global public health that impacts the efficiency and effectiveness of our health systems on multiple fronts, limiting our ability to respond to public health crises effectively. With the strategic guidance from its Member States, PAHO has agreed to move toward the digital transformation of the health sector across the entire continent with an initiative that aims to improve health outcomes, ensure equitable access to health services, and enhance the overall efficiency of health systems in the Americas. The roadmap for this digital transformation outlines strategic actions and goals to achieve a connected, efficient, and resilient health sector.

Creating notes in the EHR is one of the most problematic aspects for health professionals. The main challenges are the time spent on this task and the quality of the records. Automatic speech recognition technologies aim to facilitate clinical documentation for users, optimizing their workflow. In our hospital, we internally developed an automatic speech recognition system (ASR) to record progress notes in a mobile EHR. The objective of this article is to describe the pilot study carried out to evaluate the implementation of ASR to record progress notes in a mobile EHR application. As a result, the specialty that used ASR the most was Home Medicine. The lack of access to a computer at the time of care and the need to perform short and fast evolutions were the main reasons for users to use the system.