Inmaculada Mora-Jiménez

Chromatin mobility in living interphase nuclei provides a dynamical readout of genome regulation. From time-resolved trajectories of chromatin granules in primary acute lymphoblastic leukemia (ALL) samples (one B-ALL, one T-ALL), leukemic cell lines (U266, Jurkat), and healthy donor T lymphocytes, we resolve rare but reproducible transitions between extreme mobility states. We quantify these events with Brownian-bridge ensembles, i.e., trajectories conditioned on crossings between low- and high-mobility quartiles. Despite their low frequency, crossings reveal strong polarity: activation ( Q1 → Q4 ) concentrates on a superlinear, ballistic-like ridge, whereas reconfinement ( Q4 → Q1 ) returns more slowly toward confinement. The scarcity of extreme events is comparable in magnitude to reported bursting fractions, motivating future joint live-imaging tests that directly link mobility bridges to transcriptional state. These asymmetric pathways yield a compact dynamical signature of disrupted confinement and lineage-dependent nuclear deregulation in ALL, and generate testable predictions for cohort-level validation.

Xylella fastidiosa (Xf) is a vascular plant pathogen that affects several crops by blocking xylem vessels, impairing water and nutrient flow, and ultimately leading a plant decline. Early detection is challenging due to symptom latency and overlap with abiotic stress. This study presents a methodological framework for temporal monitoring of Xf infection using leaf-level physiological and spectral traits. Data were collected from up to two selected branches of each of 96 almond trees across four dates in 2024. At each date, eight leaves per branch were measured and discarded after their analysis, enabling temporal monitoring at the branch level. Leaf samples were classified into four categories based on molecular tests, visual symptoms, and expert assessments, considering whether the corresponding branch was already infected or became symptomatic during the study period. Non-parametric tests identified informative variables for Xf -detection, including pigment and structure related indices (e.g. TCARI, MCARI) and physiological traits (e.g. stomatal conductance, fluorescence). A simple and interpretable data-driven predictive model, in this work a logistic regressor, was trained using the identified variables on leaf-level data from trees with contrasting health conditions (healthy vs. symptomatic). The model was evaluated for its ability to generalize over time. Models trained with data from the first two measurement dates showed the best generalization, achieving weighted accuracies between 60 % and 80 % even in later dates, and improved detection of symptomatic branches. Data from the second and third dates offered the best separation between health conditions, while the last date was less informative due to confounding stress factors. Despite limitations from sample size and class imbalance, the framework demonstrates potential for non-invasive disease monitoring in woody crops.

Electronic Health Records (EHRs) serve as a comprehensive repository of multimodal patient health data, combining static demographic attributes with dynamic, irregular Multivariate Time Series (MTS), characterized by varying lengths. While MTS provide critical insights for clinical predictions, their integration with static features enables a more nuanced understanding of patient health trajectories and enhances predictive accuracy. Deep Neural Networks (DNNs) have proven highly effective in capturing complex patterns in healthcare data, offering a framework for multimodal data fusion. However, their adoption in clinical practice is limited by a lack of interpretability, as transparency and explainability are essential for supporting informed medical decisions. This study presents interpretable multimodal DNN architectures for predicting and understanding the emergence of Multidrug Resistance (MDR) in Intensive Care Units (ICUs). The proposed models integrate static demographic data with temporal variables, providing a holistic view of baseline patient characteristics and health progression. To address predictive performance and interpretability challenges, we introduce a novel methodology combining feature selection techniques with attention mechanisms and post-hoc explainability tools. This approach not only reduces feature redundancy but also highlights key risk factors, thereby improving model accuracy and robustness. Experimental results demonstrate the effectiveness of the proposed framework, achieving a Receiver Operating Characteristic Area Under the Curve of 76.90 ± 3.10, a significant improvement over baseline models. Beyond MDR prediction, this methodology offers a scalable and interpretable framework for addressing various clinical challenges involving EHR data. By integrating predictive accuracy with explanatory insights-such as the identification of key risk factors-this work supports timely, evidence-based interventions to improve patient outcomes in ICU settings.

Background and Objectives: Multidrug Resistance (MDR) is a critical global health issue, causing increased hospital stays, healthcare costs, and mortality. This study proposes an interpretable Machine Learning (ML) framework for MDR prediction, aiming for both accurate inference and enhanced explainability. Methods: Patients are modeled as Multivariate Time Series (MTS), capturing clinical progression and patient-to-patient interactions. Similarity among patients is quantified using MTS-based methods: descriptive statistics, Dynamic Time Warping, and Time Cluster Kernel. These similarity measures serve as inputs for MDR classification via Logistic Regression, Random Forest, and Support Vector Machines, with dimensionality reduction and kernel transformations improving model performance. For explainability, patient similarity networks are constructed from these metrics. Spectral clustering and t-SNE are applied to identify MDR-related subgroups and visualize high-risk clusters, enabling insight into clinically relevant patterns. Results: The framework was validated on ICU Electronic Health Records from the University Hospital of Fuenlabrada, achieving an AUC of 81%. It outperforms baseline ML and deep learning models by leveraging graph-based patient similarity. The approach identifies key risk factors -- prolonged antibiotic use, invasive procedures, co-infections, and extended ICU stays -- and reveals clinically meaningful clusters. Code and results are available at \https://github.com/oscarescuderoarnanz/DM4MTS. Conclusions: Patient similarity representations combined with graph-based analysis provide accurate MDR prediction and interpretable insights. This method supports early detection, risk factor identification, and patient stratification, highlighting the potential of explainable ML in critical care.