https://hdl.handle.net/2072/452965 2026-04-18T09:50:00Z https://hdl.handle.net/10256/27424 Managing Blood Glucose in Premature Neonates via Parenteral Nutrition: In-silico Evaluation Bertachi, Arthur Hirata; Marchiori, Hadija; Dalla Man, Chiara; Vehí, Josep Prometeus (Preterm Brain-Oxygenation and Metabolic EU-Sensing: Feed the Brain) develops innovative technology for personalized nutrition in premature neonates. Central to this is the Nutritional Clinical Advisor, an adaptive algorithm providing optimal parenteral nutrition plans to enhance brain oxygenation. This study tests a closed-loop PID controller for regulating glucose levels in virtual neonates born preterm, offering insights into its effectiveness and guiding future NCA development to support neonatal care; The authors would like to express their gratitude to all the physicians involved in the Prometeus project for their valuable discussions and insights during its development 2025-05-01T00:00:00Z https://hdl.handle.net/10256/27420 CTBN-PH: A continuous-time Bayesian network for individualised diagnostic risk prediction Hernández Guillamet, Guillem; López Seguí, Francesc; Vidal-Alaball, Josep; López Ibáñez, Beatriz Continuous-time Bayesian networks (CTBNs) are powerful tools for modelling and predicting complex disease trajectories in continuous-time scenarios. However, their application is often limited by a lack of individualisation in the results, if the covariates significantly influence a patient's diagnostic transitions. To address these challenges, we introduce the CTBN-PH model, which integrates CTBN models with Cox proportional hazards (Cox-PH) models. The proposed model combines the dynamic and probabilistic capabilities of CTBNs with the robust, covariate-driven risk estimation of Cox-PH models. By leveraging causal topologies learned from healthcare trajectories, the method dynamically adjusts transition intensities based on covariate effects, enabling efficient parameter learning in extensive databases. We validated the model using a dataset of over 2.1 million patients and found that it learned complex causal structures associated with multi-morbid conditions such as diabetes and hypertension. Performance comparisons with non-individualised and non-causally inferred networks highlight the model's effectiveness. Our model achieved an integrated Brier score (IBS) of 0.153 for predicting the onset of a single diagnosis over 25 years and an IBS of 0.04 for forecasting the inertia of the entire system over four years. Additionally, we explore the model's utility in simulating patient trajectories that are tailored to specific covariate-defined populations; This study was conducted with the support of the Secretary of Universities and Research of the Department of Business and Knowledge at the Generalitat de Catalunya 2021 SGR 01125, and funded by the Industrial Doctorate Plan 2021 DI 106 provided by the Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR), Spain. Open Access funding provided thanks to the CRUE-CSIC agreement with Elsevier. 2025-10-01T00:00:00Z https://hdl.handle.net/10256/27320 CCLR-DL: A novel statistics and deep learning hybrid method for feature selection and forecasting healthcare demand Hernández Guillamet, Guillem; López Seguí, Francesc; Vidal-Alaball, Josep; López Ibáñez, Beatriz Background and Objective: Hybrid forecasting methods aim to overcome the limitations of classical statistical approaches and deep learning models. While statistical methods provide interpretability, they often lack predictive power. Conversely, deep learning models achieve high accuracy but act as “black boxes.” This study introduces the Comprehensive Cross-Correlation and Lagged Linear Regression Deep Learning (CCLR-DL) framework, combining statistical and deep learning techniques to enhance both forecasting accuracy and interpretability. Unlike existing hybrid methods that combine statistical filtering with deep learning, CCLR-DL integrates causal statistical selection with neural forecasting, producing interpretable predictors and consistently achieving higher accuracy than models without feature selection or other standard baselines. Methods: The CCLR-DL framework integrates cross-correlation analysis, lagged multiple linear regression, and Granger causality testing with advanced deep learning architectures. This dual-phase approach first identifies causally significant predictors and then fits them into a deep learning model for multivariate time series forecasting. The framework was validated using a real-world dataset of clinical visits and diagnoses from 6.3 million individuals collected over 10 years. Results: In the evaluated setting, the CCLR-DL framework outperformed baseline models, achieving an average Root Mean Square Error (RMSE) improvement of 19.8% over univariate models, 60.1% over no feature selection, and 51.9% over random selection. The causality phase ensured that all selected predictors demonstrated a significant Granger-causal (GC) relationship. Simpler recurrent architectures, particularly bidirectional Long Short-Term Memory units (BiLSTM), yielded the most accurate forecasts by effectively capturing nonlinear temporal dependencies. Conclusions: By addressing the challenges of both prediction accuracy and model transparency, the CCLR-DL framework offers a new approach for high-dimensional, multivariate time series forecasting. In healthcare settings, it may enable decision-makers to anticipate demand shifts with greater reliability, allowing earlier staff scheduling, more efficient resource allocation, and reduced waiting times. In our evaluation, it consistently outperformed baseline strategies, delivering measurable improvements that translate into thousands of patient visits being forecasted more accurately across large populations; This work was conducted with the support of the Secretary of Universities and Research of the Department of Business and Knowledge at the Generalitat de Catalunya 2021 SGR 01125, and founded by the Industrial Doctorate Plan 2021 DI 106, provided by the Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR). Open Access funding provided thanks to the CRUE-CSIC agreement with Elsevier 2025-12-01T00:00:00Z https://hdl.handle.net/10256/26702 Methodological Advances in temperature dynamics modeling for energy-efficient indoor air management systems Iglesias i Cels, Ferran; Massana i Raurich, Joaquim; Burgas Nadal, Llorenç; Planellas Fargas, Narcís; Colomer Llinàs, Joan Heating, ventilation, and air conditioning (HVAC) systems account for up to 40% of the total energy consumption in buildings. Improving the modeling of HVAC components is necessary to optimize energy efficiency, maintain indoor thermal comfort, and reduce their carbon footprint. This work addresses the lack of a general methodology for data preprocessing by introducing a novel approach for feature extraction and feature selection based on physical equations and expert knowledge that can be applied to any data-driven model. The proposed framework enables the forecasting of indoor temperatures and the energy consumption of individual HVAC components. The methodology is validated with real-world data from a system involving a fan coil unit and a thermal inertia deposit powered by geothermal energy, achieving a coefficient of determination (R2) of 0.98 and mean absolute percentage error (MAPE) of 0.44%; This project was undertaken by the eXiT research group (SITES group, Ref. 2021 SGR 01125) under a grant from the Generalitat de Catalunya. The research received funding from the European Union NextGenerationEU/PRTR under OptiREC project grant agreement TED2021-131365B-C41 and the GERIO project under grant agreement PID2022-142221OB-I00; from the (Departament de Recerca i Universitats, del Departament d’Acció Climàtica, Alimentació i Agenda Rural i del Fons Climàtic de la Generalitat de Catalunya) under CLIMA project grant agreement No 2023 CLIMA 00090; and the ACCIO of Generalitat de Catalunya under AI ENERGY project grant agreement nuclis T083-24 2025-04-13T00:00:00Z