AI for Healthcare

The research theme on AI and healthcare aims at applying some of the IIIA AI techniques to the field of healthcare. Specifically, it is focused on the design of novel algorithms to provide solutions able to incorporate advanced Descriptive, Diagnostic, Predictive, and Prescriptive capabilities to Clinical Decision Support Systems (CDSS). 

The current trend of moving towards a more Personalized, Preventive, and Participatory medicine, known as 3P Medicine, is changing the healthcare paradigm. Digital technologies are playing an important role in this 3P paradigm generating a volume and variety of information never seen before. Artificial Intelligence is contributing by providing tools for the management and exploitation of this huge amount of data.

The prescription of highly personalized treatments increases the complexity of the knowedge and decisions to be considered. Artificial Intelligence and Machine Learning aims at developing innnovative decision support systems to speed up the discovery and consolidation of new evidence.  

Time Series Analysis

Many information sources in healthcare have a temporal dimension. The explosion of biometrical sensors and wearables is an example of its relevance and an also of its noisy nature. Providing robust and efficient algorithms to deal with this amount of data is a challenging problem we are currently focused on.

Deep Learning

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics.

Case-Based Reasoning

CBR systems are capable of solving new problems using domain knowledge and the experience acquired in solving precedent problems (cases). CBR is a powerful methodology that allows incremental prototyping and short design cycles. Our group is an international referent on CBR with high impact contributions both in research and in applications.

Probabilistic Graphical Models

Probabilistic graphical models are a powerful framework for representing complex domains using probability distributions, with numerous applications in machine learning, computer vision, natural language processing and computational biology. Graphical models bring together graph theory and probability theory, and provide a flexible framework for modeling large collections of random variables with complex interactions

Causal Reasoning

Distinguishing between co-occurence and causality is one of the main challenges in healthcare. Determining causal relationships and designing robust causal models from data usually requires of the combination of multiple and heterogeneous data sources. Our research has been exploited into technology transfer projects.

Semi-Supervised Learning

One of the main characteristics of healthcare datasets is that they are usually partially annotated. Annotating and curating information is one of the key issues to obtain high quality datasets. This task requires a titanic effort and easily it becomes unaffordable. Semi-supervised techniques focus on minimizing the amount of labeled information, i.e. expert resources, while maximizing the models generated.

Trust, and Accountability

The adoption of complex AI/ML algorithms to take critical decisions collides with the requirement to understand ​Why these systems are recommending their decisions, which is their robustness, and the ethical consequences of these decisions. These systems will not succeed in healthcase if they do not incorporate explainability capabilities.

Josep Lluís Arcos
Scientific Researcher
Phone Ext. 227

Eva Armengol
Tenured Scientist
Phone Ext. 226

Jesus Cerquides
Scientific Researcher
Phone Ext. 228

Núria Correa
Industrial PhD Student
Phone Ext. 234

Lissette Lemus del Cueto
Contract Engineer
Phone Ext. 259

Kian Seif
PhD Student

Borja Velasco
PhD Student

Jennifer Grau-Sánchez,  Emma Segura,  David Sanchez-Pinsach,  Preeti Raghavan,  Thomas F. Münte,  Anna Marie Palumbo,  Alan Turry,  Esther Duarte,  Särkämö Särkämö,  Jesus Cerquides,  Josep Lluis Arcos,  & Antoni Rodriguez-Fornells (2021). Enriched Music-supported Therapy for chronic stroke patients: a study protocol of a randomised controlled trial. BMC Neurology, 21. [BibTeX]
Oguz Mulayim,  & Josep Lluis Arcos (2020). Fast anytime retrieval with confidence in large-scale temporal case bases. Knowledge-Based Systems, 206, 106374. [BibTeX]
David Sanchez-Pinsach,  Oguz Mulayim,  Jennifer Grau-Sánchez,  Emma Segura,  Berta Juan-Corbella,  Josep Lluis Arcos,  Jesus Cerquides,  Monique Messaggi-Sartor,  Esther Duarte,  & Antoni Rodriguez-Fornells (2019). Design of an AI Platform to Support Home-Based Self-Training Music Interventions for Chronic Stroke Patients. Jordi Sabater-Mir, Vicenç Torra, Isabel Aguilo, & Manuel González-Hidalgo (Eds.), Frontiers in Artificial Intelligence and Applications (pp 170--175). IOS Press. [BibTeX]
Oguz Mulayim,  & Josep Lluis Arcos (2018). Perks of Being Lazy: Boosting Retrieval Performance. Twenty-Sixth International Conference on Case-Based Reasoning . [BibTeX]
E. Ros-Cucurull,  A. Xicola,  R.F. Palma-Álvarez,  Arturo Ribes,  L. Grau-López,  Lissette Lemus,  Josep Lluis Arcos,  & C. Roncero (2017). Electrodermal activity monitoring on inpatient detoxification unit. 30th ECNP Congress . [BibTeX]
Martin Nettling,  Henrik Treutler,  Jesús Cerquides,  & Ivo Grosse (2017). Unrealistic phylogenetic trees may improve phylogenetic footprinting. Bioinformatics. [BibTeX]
David Sanchez-Pinsach,  Josep Lluis Arcos,  Sara Laxe,  Montserrat Bernabeu,  & Josep Maria Tormos (2017). Using community detection techniques to disc over non-explicit relationships in neurorehabilitation treatments. 20th International Conference of the Catalan Association for Artificial Intelligence (pp. 26-35). IOS Press. [BibTeX]
Martin Nettling,  Hendrik Treutler,  Jesús Cerquides,  & Ivo Grosse (2016). Detecting and correcting the binding-affinity bias in ChIP-seq data using inter-species information. BMC Genomics, 17, 347. [BibTeX]
Joan Serrà,  Josep Lluis Arcos,  Alejandro Garcia-Rudolph,  Alberto García-Molina,  Teresa Roig,  & Josep Maria Tormos (2013). Cognitive prognosis of acquired brain injury patients using machine learning techniques. Int. Conf. on Advanced Cognitive Technologies and Applications (COGNITIVE) (pp. 108-113). IARIA. [BibTeX]  [PDF]
Josep Blat,  Josep Lluis Arcos,  & Sergio Sayago (2012). WorthPlay: juegos digitales para un envejecimiento saludable. LYCHNOS, 8. [BibTeX]
Eva Armengol (2011). Classification of Melanomas in situ using Knowledge Discovery with Explained CBR. Artificial Intelligence in Medicine, 51, 12. [BibTeX]  [PDF]
Eva Armengol,  Pilar Dellunde,  & Carlo Ratto (2011). Lazy Learning Methods for Quality of Life Assessment in people with intellectual disabilities. CCIA-2011 (pp. 41-50). IOS Press. [BibTeX]
Eva Armengol (2009). Using explanations for determining carcinogenecity in chemical compounds. International Journal on Engineering Applications of Artificial Intelligence, 22, 8. [BibTeX]
Albert Fornells,  Eva Armengol,  Elisabet Golobardes,  Susana Puig,  & Josep Malvehy (2008). Experiences using clustering and generizations for knowledge discovery in melanomas domain. P. Perner (Eds.), Lecture Notes in Computer Science . Springer. [BibTeX]
A. Palaudàries,  Eva Armengol,  & Enric Plaza (2001). Individual prognosis of diabetes long-term risks: A CBR approach. Methods of Information in Medicine, 40, 46-51. [BibTeX]
Eva Armengol,  A. Palaudàries,  & Enric Plaza (2000). Raonament basat en Casos per Pronosticar Riscos a Llarg Termini en Pacients amb Diabetis Mellitus. Proceedings of the (pp. 209-218). [BibTeX]