Pedro A. Moreno-Sánchez

Pedro A. Moreno-Sánchez, Javier Del Ser, Mark van Gils et al.

Artificial Intelligence (AI) holds great promise for transforming healthcare, particularly in disease diagnosis, prognosis, and patient care. The increasing availability of digital medical data, such as images, omics, biosignals, and electronic health records, combined with advances in computing, has enabled AI models to approach expert-level performance. However, widespread clinical adoption remains limited, primarily due to challenges beyond technical performance, including ethical concerns, regulatory barriers, and lack of trust. To address these issues, AI systems must align with the principles of Trustworthy AI (TAI), which emphasize human agency and oversight, algorithmic robustness, privacy and data governance, transparency, bias and discrimination avoidance, and accountability. Yet, the complexity of healthcare processes (e.g., screening, diagnosis, prognosis, and treatment) and the diversity of stakeholders (clinicians, patients, providers, regulators) complicate the integration of TAI principles. To bridge the gap between TAI theory and practical implementation, this paper proposes a design framework to support developers in embedding TAI principles into medical AI systems. Thus, for each stakeholder identified across various healthcare processes, we propose a disease-agnostic collection of requirements that medical AI systems should incorporate to adhere to the principles of TAI. Additionally, we examine the challenges and tradeoffs that may arise when applying these principles in practice. To ground the discussion, we focus on cardiovascular diseases, a field marked by both high prevalence and active AI innovation, and demonstrate how TAI principles have been applied and where key obstacles persist.

Leire Benito-Del-Valle, Pedro A. Moreno-Sánchez, Itziar Egusquiza et al.

The MIDOG 2025 challenge extends prior work on mitotic figure detection by introducing a new Track 2 on atypical mitosis classification. This task aims to distinguish normal from atypical mitotic figures in histopathology images, a clinically relevant but highly imbalanced and cross-domain problem. We investigated two complementary backbones: (i) ConvNeXt-Small, pretrained on ImageNet, and (ii) a histopathology-specific ViT from Lunit trained via self-supervision. To address the strong prevalence imbalance (9408 normal vs. 1741 atypical), we synthesized additional atypical examples to approximate class balance and compared models trained with real-only vs. real+synthetic data. Using five-fold cross-validation, both backbones reached strong performance (mean AUROC approximately 95 percent), with ConvNeXt achieving slightly higher peaks while Lunit exhibited greater fold-to-fold stability. Synthetic balancing, however, did not lead to consistent improvements. On the organizers' preliminary hidden test set, explicitly designed as an out-of-distribution debug subset, ConvNeXt attained the highest AUROC (95.4 percent), whereas Lunit remained competitive on balanced accuracy. These findings suggest that both ImageNet and domain-pretrained backbones are viable for atypical mitosis classification, with domain-pretraining conferring robustness and ImageNet pretraining reaching higher peaks, while naive synthetic balancing has limited benefit. Full hidden test set results will be reported upon challenge completion.

Pedro A. Moreno-Sanchez

Cardiovascular diseases and their associated disorder of heart failure are one of the major death causes globally, being a priority for doctors to detect and predict its onset and medical consequences. Artificial Intelligence (AI) allows doctors to discover clinical indicators and enhance their diagnosis and treatments. Specifically, explainable AI offers tools to improve the clinical prediction models that experience poor interpretability of their results. This work presents an explainability analysis and evaluation of a prediction model for heart failure survival by using a dataset that comprises 299 patients who suffered heart failure. The model employs a data workflow pipeline able to select the best ensemble tree algorithm as well as the best feature selection technique. Moreover, different post-hoc techniques have been used for the explainability analysis of the model. The paper's main contribution is an explainability-driven approach to select the best prediction model for HF survival based on an accuracy-explainability balance. Therefore, the most balanced explainable prediction model implements an Extra Trees classifier over 5 selected features (follow-up time, serum creatinine, ejection fraction, age and diabetes) out of 12, achieving a balanced-accuracy of 85.1% and 79.5% with cross-validation and new unseen data respectively. The follow-up time is the most influencing feature followed by serum-creatinine and ejection-fraction. The explainable prediction model for HF survival presented in this paper would improve a further adoption of clinical prediction models by providing doctors with intuitions to better understand the reasoning of, usually, black-box AI clinical solutions, and make more reasonable and data-driven decisions.

Pedro A. Moreno-Sanchez

Chronic Kidney Disease (CKD), where delayed recognition implies premature mortality, is currently experiencing a globally increasing incidence and high cost to health systems. Data mining allows discovering subtle patterns in CKD indicators to contribute to an early diagnosis. This work presents the development and evaluation of an explainable prediction model that would support clinicians in the early diagnosis of CKD patients. The model development is based on a data management pipeline that detects the best combination of ensemble trees algorithms and features selected concerning classification performance. Furthermore, the main contribution of the paper involves an explainability-driven approach that allows selecting the best predictive model maintaining a balance between accuracy and explainability. Therefore, the most balanced explainable predictive model implements an extreme gradient boosting classifier over 3 features (packed cell value, specific gravity, and hypertension), achieving an accuracy of 99.2% and 97.5% with cross-validation technique and with new unseen data respectively. In addition, an analysis of the model's explainability shows that the packed cell value is the most relevant feature that influences the prediction results of the model, followed by specific gravity and hypertension. This small number of feature selected results in a reduced cost of the early diagnosis of CKD implying a promising solution for developing countries.