Chile’s public health system serves the vast majority of the population and performs well across several health indicators. At the same time, it faces major structural and operational challenges, including long waiting times, unequal access to specialist care, high patient no-show rates, increasing clinical complexity, missing interoperability, and the slow integration of advances in Genomics, biomedical imaging, Operations Research, Artificial Intelligence, and Digital Health technologies.
This research line aims to develop data-driven, interoperable, and AI-enabled healthcare systems through mathematical modeling, biomedical data science, medical informatics, and human-centered Artificial Intelligence. The focus is on developing scalable Digital Health solutions that improve healthcare delivery, clinical decision-making, resource allocation, and public health planning in Chile and beyond.
Research activities span multiple levels of the health ecosystem, from hospital processes and epidemic preparedness to precision medicine, biomedical imaging, and computational diagnostics. Special emphasis is placed on bridging the gap between methodological innovation and real-world implementation, ensuring that advanced analytical and computational methods can be effectively integrated into healthcare system infrastructures and workflows.
The group develops methods and technologies grounded in Operations Research, Machine Learning, AI, mathematical modeling, computational biology, and biomedical image analysis, while addressing challenges related to interoperability, data quality, interpretability, privacy, ethical use of AI, and the responsible handling of sensitive health information.
Through interdisciplinary collaboration with hospitals, public and private health institutions, academic and technology partners, and healthcare professionals, this research line seeks to contribute to the digital transformation of health systems and the development of precision, preventive, and personalized medicine.
Within this line, the following research areas are developed:
Health Management
This area focuses on improving access to and delivery of healthcare services within the public system through close collaboration with key stakeholders.
Current work includes optimizing surgical suite scheduling and clinical workflows through software tools based on operations research, Artificial Intelligence, and decision support systems. Other efforts aim to reduce patient no-show rates through predictive models applied to different medical specialties, procedures, and telemedicine services. Both contribute to the reduction of waiting lists.
In addition, the team develops predictive models based on Diagnosis-Related Groups (DRGs) and admission data to identify patients at risk of prolonged hospital stays, enabling earlier interventions and more efficient resource allocation.
Mathematical Epidemiology
This area focuses on the analysis, management, and development of epidemiological models to support public policy decisions during outbreaks and population health emergencies.
Our models incorporate health, social, demographic, and environmental factors to support short- and medium-term scenario analysis during epidemics, drawing on the recent COVID-19 pandemic as a reference. Future work aims to incorporate spatial components and to address emerging diseases such as measles.
The group also focuses on developing predictive systems that combine compartmental models with historical hospitalization data, enabling the anticipation of seasonal peaks in pediatric respiratory diseases, with potential extension to non-pediatric populations. The work also includes studies involving recent structural changes, such as shifts in hospitalization dynamics following the introduction of Nirsevimab immunization against Respiratory Syncytial Virus in Chile and the impact of this intervention.
Human Health Genomics
This research area focuses on advancing precision medicine through the integration of data, modeling, and Artificial Intelligence to better understand human diseases. It addresses key questions about how ancestry and biological variation determine disease risk and outcomes, and how complex biomedical data can be translated into actionable knowledge. A central component is the study of cancers prevalent in Chile (including gallbladder, colorectal, and breast cancers), with the goal of improving early detection, prognosis, and treatment decisions through the integration of molecular, clinical, and imaging information.
The area also develops data-driven tools that support clinical decision-making, including predictive models based on medical imaging and genomic data, as well as approaches for patient stratification and risk assessment. It also places strong emphasis on population genomics, contributing to better representation of Latin American populations in global genomic research. Altogether, human health genomics contributes both new biomedical knowledge and new mathematical and computational tools for understanding diseases, while addressing existing inequities in access to genomic medicine.
Biomedicine
In biomedicine, this area develops computational and AI-based methods for the analysis of biomedical data and images, digital pathology, and multimodal clinical data. Research focuses on the development of interpretable, human-centered AI systems for medical diagnosis, prognostic prediction, computational pathology, histological image analysis, and translational biomedical research. Current work includes AI-assisted analysis of histological and medical imaging data to identify clinically relevant biomarkers, predict survival outcomes, infer genomic alterations, and support precision medicine approaches.
Medical Informatics and Digital Health Systems
This area focuses on the design, integration, and evaluation of Digital Health infrastructures, interoperable clinical systems, and data-driven health ecosystems. Research includes clinical informatics, interoperability standards and terminologies, data integration, human-centered digital systems, and implementation strategies for AI-enabled technologies. The group works closely with academic, clinical, and public sector stakeholders to facilitate the responsible adoption of Digital Health innovations in real-world settings.