top of page
En el laboratorio


Here we publish interesting links, articles, studies, projects, and content for researchers in the field.

Our Research Goals:


         Develop an AI-based Decision Support System (AI-DSS) for Pancreatic Ductal Adenocarcinoma (PDAC) to assist healthcare professionals in making better treatment decisions.

​      Enhance data collection and analysis capabilities through user-friendly mobile applications for PDAC patients, caregivers, and clinicians.

        Design a wearable device to monitor and manage pain in real-time for PDAC patients.

        Develop a monitoring tool for assessing sarcopenia in PDAC patients to aid in early detection and intervention.

        Create a comprehensive dashboard for clinicians, patients, and caregivers, providing valuable information for improved disease management and treatment choices.

        Build estimation models for neuropathic pain and sarcopenia to aid in accurate assessment and personalized care for PDAC patients.

        Create an early cachexia estimation model to identify and intervene in cachexia cases at an early stage, improving patient outcomes.

        Investigate and develop multi-modal interventions to enhance the quality of life (QoL) for PDAC patients, focusing on diverse aspects such as pain management, nutrition, and physical activity.

       Develop guidelines for supportive and palliative care specific to PDAC, providing evidence-based recommendations for healthcare professionals and improving patient outcomes.

       Develop causal models for assessing the effectiveness of pain management strategies and nutritional/physical activity interventions, aiding in evidence-based decision-making and improving patient care.

Relevant Research, Publications & Studies:

  • 🔗KITTU - AI-supported Clinical Decision In Urologic OncologyKITTU aims to develop an AI system in urology that assists physicians and patients in decision-making by providing comprehensive options. It relieves the burden on individuals involved and optimizes therapy decisions, contributing to healthcare optimization. Integration into the digitalization of the healthcare system involves interdisciplinary collaboration. The goal is to improve evidence-based treatment recommendations in oncology, reducing side effects and enhancing quality of life. KITTU plans to expand beyond urology, making a significant impact on cancer care.

  • 🔗EORTC clinical research on the Gastrointestinal tractEORTC's GI clinical research explores genetic, epigenetic, and immunologic factors in gastrointestinal tumors. Their trials bridge preclinical and clinical stages, investigating new aspects of tumor biology using advanced technology. With a patient-centered approach, their mission is to develop innovative therapeutic strategies through multidisciplinary studies. They collaborate with diverse cancer research networks, enrich their expert team, and empower future leaders in GI cancer research.

Our Solution...

Captura de pantalla 2023-06-29 114352.png

In the Relevium project, we utilize a range of sensor data, such as heart rate variability, electrodermal activity, and pain sensation, collected through sensors and an app. These data serve as valuable input for both developing medical models and designing effective interventions.


By analyzing the data, we derive causal models that enable us to predict disease progression and identify potential improvements that can be achieved through lifestyle changes. This data-driven approach helps us understand the underlying factors influencing health outcomes.

When planning interventions for patients, we employ Explainable Artificial Intelligence (AI) techniques to analyze the current health data in accordance with these models. This allows us to provide transparent and understandable insights into the analysis results. Our focus is on ensuring the ethical use of these results for intervention planning.

Equipped with these explainable analysis outcomes, healthcare professionals can make informed decisions when creating personalized lifestyle interventions for patients. We prioritize the comprehensibility of the analysis results, enabling professionals to effectively communicate and collaborate with patients in their treatment journey.

Through the combination of causal medical models and Explainable AI, the Relevium project aims to provide actionable insights for intervention planning, empowering patients and healthcare professionals to make informed decisions and improve patient outcomes.

bottom of page