Papers
Publications
Journal articles and conference papers of the group. Names of group members are shown in bold.
Selected publications
Google Scholar SoftwarePhysics-informed machine learning
-
Physics-Informed Neural Networks for Hidden Insulin Dynamics Estimation from Glucose Data
Artificial Intelligence in Medicine (AIME 2025), Springer, Part II, 283–287, 2025Code
Uses physics-informed neural networks to estimate insulin dynamics, which are not observed directly, from glucose data.
-
Modeling spatially dependent functional data via regression with differential regularization
Journal of Multivariate Analysis, 170, 275–295, 2019
Models spatially dependent functional data with a regression penalised by a differential operator, so that prior knowledge on the phenomenon enters the estimates.
-
Blood flow velocity field estimation via spatial regression with PDE penalization
Journal of the American Statistical Association, Theory and Methods, 110(511), 1057–1071, 2015Code
Extends spatial regression with differential regularisation to general partial differential equations and boundary conditions, which encode the physics of blood flow, to estimate velocity fields from sparse and noisy echo-colour Doppler data.
Causal AI and probabilistic graphical models
-
Data-Driven and Expert-Informed Causal Discovery for Type 2 Diabetes Risk in Primary Care
Medical Informatics Europe (MIE 2026), Studies in Health Technology and Informatics, 336, 298–302, 2026Code
Combines causal discovery from primary-care records with expert knowledge to build an interpretable causal model of type 2 diabetes risk.
-
Artificial Intelligence in Medicine (AIME 2025), Springer, Part I, 212–221, 2025Code
Couples a differential equation model of glucose regulation with a structural causal model to estimate, for an individual, the effect of a physical activity plan on the onset of type 2 diabetes.
-
A Bayesian hierarchical score for structure learning from related data sets
International Journal of Approximate Reasoning, 142, 248–265, 2022
Introduces a Bayesian hierarchical score to learn the structure of Bayesian networks jointly from related data sets, such as data collected in different hospitals.
Federated learning
-
FPLIER: Federated Pathway-Level Information Extractor
ACM Conference on Bioinformatics, Computational Biology and Health Informatics (ACM BCB 2026), 2026Code
Brings pathway-level information extraction to the federated setting, so that interpretable representations of transcriptomic data can be learned across institutions without sharing the data.
-
Flotta: a Secure and Flexible Spark-inspired Federated Learning Framework
IEEE International Conference on Federated Learning Technologies and Applications (FLTA 2024), 156–161, 2024PreprintCode
Presents FLOTTA, the open-source federated learning framework developed at IDSIA and used in multi-centre clinical projects.
All publications
2026
-
In silico methodologies in computational medicine: From complex disease modeling to virtual clinics
Biophysics Reviews, 7(3), 031304
-
FPLIER: Federated Pathway-Level Information Extractor
ACM Conference on Bioinformatics, Computational Biology and Health Informatics (ACM BCB 2026)Code
-
European Journal of Anaesthesiology, 43(6), 550–553
-
Data-Driven and Expert-Informed Causal Discovery for Type 2 Diabetes Risk in Primary Care
Medical Informatics Europe (MIE 2026), Studies in Health Technology and Informatics, 336, 298–302Code
-
A reduced model for the long-term effects of physical activity on type 2 diabetes
2025
-
Artificial Intelligence in Medicine (AIME 2025), Springer, Part I, 212–221Code
-
Physics-Informed Neural Networks for Hidden Insulin Dynamics Estimation from Glucose Data
Artificial Intelligence in Medicine (AIME 2025), Springer, Part II, 283–287Code
-
STAR Protocols, 6(1), 103670Code
-
A Preliminary Study on NLP-Based Personalized Support for Type 1 Diabetes Management
Second Workshop on Patient-Oriented Language Processing (CL4Health), Association for Computational Linguistics, 298–302
2024
-
A Computationally Efficient Deep Learning-Based Surrogate Model of Prediabetes Progression
IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2024), 6951–6958Code
-
Global Outlier Detection in a Federated Learning Setting with Isolation Forest
IEEE International Conference on Federated Learning Technologies and Applications (FLTA 2024), 251–258Preprint
-
Flotta: a Secure and Flexible Spark-inspired Federated Learning Framework
IEEE International Conference on Federated Learning Technologies and Applications (FLTA 2024), 156–161PreprintCode
-
iScience, 27(3), 109271
-
Psychiatry Research, 332, 115687
2022
-
Science Immunology, 7(74), eabn6563
-
International Journal of Environmental Research and Public Health, 19(6), 3220
-
A Bayesian hierarchical score for structure learning from related data sets
International Journal of Approximate Reasoning, 142, 248–265
-
Using mixed-effects models to learn Bayesian networks from related data sets
International Conference on Probabilistic Graphical Models (PGM 2022), PMLR, 186, 73–84
2021
-
Journal of Personalized Medicine, 11(12), 1377
-
Artificial intelligence in thyroid field. A comprehensive review
Cancers, 13(19), 4740
2020
-
Structure learning from related data sets with a hierarchical Bayesian score
International Conference on Probabilistic Graphical Models (PGM 2020), PMLR, 138, 5–16
2019
-
Efficient feature selection using shrinkage estimators
Machine Learning, 108(8–9), 1261–1286
-
Hierarchical estimation of parameters in Bayesian networks
Computational Statistics and Data Analysis, 137, 67–91Code
-
Modeling spatially dependent functional data via regression with differential regularization
Journal of Multivariate Analysis, 170, 275–295
2017
-
Profiling the location and extent of musicians' pain using digital pain drawings
Pain Practice, 18(1), 53–66
-
Hierarchical Multinomial-Dirichlet model for the estimation of conditional probability tables
IEEE International Conference on Data Mining (ICDM 2017)Code
-
Invariant NKT cells contribute to Chronic Lymphocytic Leukemia surveillance and prognosis
Blood, 129(26), 3440–3451
2016
-
Computational study of the fluid-dynamics in carotids before and after endarterectomy
Journal of Biomechanics, 49(1), 26–38
2015
-
Blood flow velocity field estimation via spatial regression with PDE penalization
Journal of the American Statistical Association, Theory and Methods, 110(511), 1057–1071Code
2014
-
Mixed finite elements for spatial regression with PDE penalization
SIAM/ASA Journal on Uncertainty Quantification, 2(1), 305–335
2013
-
Nonlinear nonparametric mixed-effects models for unsupervised classification
Computational Statistics, 28(4), 1549–1570Code
2011
Preprints
-
Learning Dynamical Systems from Multiple Sparse Datasets: A Hierarchical Bayesian Modeling Approach
arXiv:2606.24966 PreprintCode
-
The Causal Artificial Intelligence Clinician for early hemodynamic management of septic shock in ICU
medRxiv Under reviewCode
-
Towards the identification of ventilator-associated pneumonia by ventilator-acquired data using machine learning: a prospective cohort study
Manuscript Under review
-
AI-Powered 48-Month Mortality Prediction to Guide Shared Decision-Making in Mitral TEER. The MitraL-AI score: a Swiss, Italian and US collaboration
Manuscript Under review
No publications match the current selection.