Research projects
Projects
Our projects are carried out with clinical, industrial and academic partners and funded by Horizon Europe, Innosuisse, the Swiss National Science Foundation and direct research mandates.
Main projects
-
AI for materials characterisation
Physics-informed machine learning models for the prediction of the properties of industrial materials, in a research mandate with an international manufacturing company.
-
PRAESIIDIUM
Patient digital twins that combine differential equation models of glucose metabolism with clinical and wearable data, to predict individual risk and suggest personalised interventions.
-
SPEARHEAD
Machine learning models trained across Swiss hospitals without exchanging patient-level data, to support clinicians in the appropriate use of antibiotics for urinary tract infections.
-
Early identification of ventilator-associated pneumonia
A prospective cohort study and machine learning models that support the early diagnosis of ventilator-associated pneumonia, using data recorded continuously and automatically by mechanical ventilators.
-
K-CLIER
Transfer learning from single-cell atlases to bulk transcriptomic data, producing low-dimensional representations that can be interpreted in terms of kidney cell states.
Other projects
-
Counterfactual image editing
Generative models with a causal structure that predict how the radiological presentation of pulmonary oedema in intensive care patients would change under a different fluid therapy.
-
Emulation of clinical trials with real-world data
Target trial emulation on routinely collected intensive care data, to estimate the effect of prone positioning on mortality and how this effect varies across patients.
-
GUIDE
Interpretable, personalised insights on glucose management during physical activity for people with type 1 diabetes, combining machine learning with large language models.
-
MitraL-AI
A machine learning score that predicts all-cause mortality up to 48 months after transcatheter edge-to-edge repair of the mitral valve, to support shared decision-making between clinicians and patients.
No projects match the current selection.
Earlier projects
-
HEAVEN
Machine learning models to identify patients at high risk of difficult intubation.
-
Life-ON
Risk and diagnosis assessment strategies for perinatal depression.
-
SpineReg
Machine learning for patient stratification after lumbar spine surgery.
-
Client analytics and natural language processing
Direct mandates on churn analysis, client risk prediction, task-agnostic client representations and quality of client interactions through NLP.
-
ALBIS
Integrated system for the risk-based surveillance of the invasive mosquito Aedes albopictus in Switzerland.
-
Statistical learning and inference on big data with probabilistic graphical models
Hierarchical Bayesian estimation of the parameters of Bayesian networks.
-
Data mining for public statistics
Analysis of employment data for the official statistics of Canton Ticino.
-
Climate change impact on debris-flow hazard
Software for the prediction of debris-flow hazard in the Ticino region.