Joaquim Arlandis

The rapid adoption of complex Artificial Intelligence (AI) and Machine Learning (ML) models has led to their characterization as black boxes due to the difficulty of explaining their internal decision-making processes. This lack of transparency hinders users' ability to understand, validate and trust model behavior, particularly in high-risk applications. Although explainable AI (XAI) has made significant progress, there remains a need for versatile and effective techniques to address increasingly complex models. This work introduces Multivariate Conditional Expectation (MUCE), a model-agnostic method for local explainability designed to capture prediction changes from feature interactions. MUCE extends Individual Conditional Expectation (ICE) by exploring a multivariate grid of values in the neighborhood of a given observation at inference time, providing graphical explanations that illustrate the local evolution of model predictions. In addition, two quantitative indices, stability and uncertainty, summarize local behavior and assess model reliability. Uncertainty is further decomposed into uncertainty+ and uncertainty- to capture asymmetric effects that global measures may overlook. The proposed method is validated using XGBoost models trained on three datasets: two synthetic (2D and 3D) to evaluate behavior near decision boundaries, and one transformed real-world dataset to test adaptability to heterogeneous feature types. Results show that MUCE effectively captures complex local model behavior, while the stability and uncertainty indices provide meaningful insight into prediction confidence. MUCE, together with the ICE modification and the proposed indices, offers a practical contribution to local explainability, enabling both graphical and quantitative insights that enhance the interpretability of predictive models and support more trustworthy and transparent decision-making.

Type 2 diabetes (T2D) is becoming one of the leading health problems in Western societies, diminishing quality of life and consuming a significant share of healthcare resources. This study presents machine learning models for T2D diagnosis and prognosis, developed using heterogeneous data from a Spanish population dataset (Di@bet.es study). The models were trained exclusively on individuals classified as controls and undiagnosed diabetics, ensuring that the results are not influenced by treatment effects or behavioral changes due to disease awareness. Two data domains are considered: environmental (patient lifestyle questionnaires and measurements) and clinical (biochemical and anthropometric measurements). The preprocessing pipeline consists of four key steps: geospatial data extraction, feature engineering, missing data imputation, and quasi-constancy filtering. Two working scenarios (Environmental and Healthcare) are defined based on the features used, and applied to two targets (diagnosis and prognosis), resulting in four distinct models. The feature subsets that best predict the target have been identified based on permutation importance and sequential backward selection, reducing the number of features and, consequently, the cost of predictions. In the Environmental scenario, models achieved an AUROC of 0.86 for diagnosis and 0.82 for prognosis. The Healthcare scenario performed better, with an AUROC of 0.96 for diagnosis and 0.88 for prognosis. A partial dependence analysis of the most relevant features is also presented. An online demo page showcasing the Environmental and Healthcare T2D prognosis models is available upon request. Graphic

SEQENS is an ensemble method aimed at feature identification that has demonstrated strong performance in identifying relevant genes in high‐dimensional spaces, across different synthetic tasks. In this paper, we first introduce the differences between feature importance , feature selection (FS) and feature identification concepts. Following this, we present a framework based on SEQENS covering the following contributions: (1) computing the hypergeometric p‐ value of the features of a SEQENS output ranking in order to be able to establish a threshold between relevant and non‐relevant features; (2) extending SEQENS by introducing the use of preselected features as hypotheses of relevance in the sequential FS, which may help to attract other features that might exhibit weak correlation with the target on their own, but gain relevance when combined with the preselected ones and; (3) designing an automated process based on a 2D‐cascade of SEQENS ensembles to obtain a purged feature set , or PFS, that is, having as many relevant features, and as few non‐relevant, as possible. The framework presented, named pc–SEQENS, integrates the former techniques so that the PFS is used as a hypothesis of relevance in a SEQENS ensemble. Performance is analysed in a gene expression identification task using the E‐MTAB‐3732 public database and synthetic targets. pc–SEQENS is compared to other state‐of‐the‐art methods, including SEQENS to check the effect of using hypotheses of relevance. On average, the proposed framework identifies better the relevant genes, especially in unfavourable sample‐to‐dimension rates, and exhibits a stronger stability.

This research aims to evaluate the Type 2 Diabetes (T2D) diagnosis and prognosis power from heterogeneous environmental, lifestyle and biochemistry data. Model estimation has previously addressed three main actions as: 1) Missingvalue imputation using specific univariant and multivariant imputers accommodated to each particular feature; 2) Quasi-constancy detection in variables; 3) Constructing geographical pollution and rent data from municipality information. Next, different T2D diagnosis and prognosis models are fitted and evaluated, showing increasing performance as more specific features become available while the prediction cost rises as a consequence of requiring more specific data. Finally, four models are obtained: two of them for T2D diagnosis and the other two for T2D prognosis respectively, with performances ranging from 73.3 to 95.41 AUC-ROC. One pair of diagnosis and prognosis models were thought for a global testing that can be done in general locations by only asking general lifestyle-related questions. On the other hand, the other pair, which achieves higher performances, is thought to be applied in a clinical environment where it is easy to obtain more specific biochemistry measures.

In this paper, a generic Symbol Input Correction Method for Human-Machine Interfaces, especially useful for embedded devices where the input subsystem is often size-constrained, combining a Language Model, the Input Hypothesis information and an Error Model is proposed. The approach can be seen as a flexible and efficient way to perform Stochastic Error-Correcting Language Modeling. We use Weighted Finite-State Transducers (WFSTs) to represent the Language Model, the complete set of symbol-input Hypotheses interpreted as a sequence of vectors of symbol probabilities, and an Error Model. This approach is different to other methods since it does not involve an explicit parsing process and also because it combines the practical advantages of a de-coupled (input-system + post-processor) model with the error-recovery power of a integrated approach where the capture and the interpretation are performed in the same element (e.g. in a HMM). The symbol-input subsystem can be a physical, "soft" (touch screen-based) or reduced (as in a mobile phone) keyboard, a speech or gesture-based recognizer, an Off-line or On-line OCR system or any other Human-Machine Interface consisting of a sequence of symbols conveying information belonging to a language where the segmentation of the input is known (although some segmentation errors can be recovered by the Error Model).