Polycystic ovary syndrome (PCOS) is a heterogeneous endocrine disorder associated with reproductive dysfunction and increased cardiometabolic risk. Convent

Aims: To systematically evaluate how artificial intelligence and machine-learning (AI/ML) methods are applied to cardiac biomarkers after myocardial infarction (MI), identify recurring methodological limitations, and operationalize a leakage-aware modelling workflow in a proof-of-concept post-MI dataset using a controlled proxy classification task. Methods and results: A PRISMA 2020-compliant systematic review of studies published between 2015 and 2025 identified 120 eligible studies from 1,389 records. Most studies used multimodal inputs combining biomarkers with clinical or functional variables (109/120, 90.8%) and focused on prediction or prognostic modelling (89/120, 74.2%). Logistic or regularized regression (76/120, 63.3%) and Random Forest (69/120, 57.5%) were the most frequently used approaches. Internal validation predominated, whereas independent external validation was reported in only 44/120 studies (36.7%). Area under the receiver operating characteristic curve (ROC-AUC) was reported in 114/120 studies (95.0%), while calibration analyses and decision-curve analysis remained limited. Formal explainability methods were used inconsistently, and public code availability was uncommon. To translate these observations into a practical framework, we implemented a leakage-aware machine-learning workflow in a proof-of-concept dataset of 152 patients with MI and 117 variables. The analytical task was defined as a binary classification problem (STEMI vs NSTEMI), used intentionally as a methodological proxy rather than a clinically relevant prognostic endpoint. Three predefined feature-set variants were benchmarked using nested cross-validation. The FULL variant achieved near-perfect discrimination [ROC-AUC 0.9988 (95% CI 0.9925-1.000)], the CLINICAL variant showed modest performance [0.6025 (0.4463-0.7450)], and the BIOMARKERS variant yielded strong discrimination with low dimensionality [0.9300 (0.8537-0.9863)]. Permutation-based falsification testing reduced performance towards chance level, supporting the procedural integrity of the workflow. Conclusions: AI/ML research on cardiac biomarkers after MI is expanding rapidly but remains limited by heterogeneous methodology, insufficient external validation, incomplete interpretability, and weak reproducibility practices. A leakage-aware framework integrating explicit feature governance, nested validation, calibration assessment, robustness analyses, and falsification testing may improve the credibility and translational relevance of biomarker-based cardiovascular AI studies. However, the proof-of-concept case study is intended as a methodological demonstration and does not represent prognostic modelling of post-MI outcomes. Translational Perspective: AI models using cardiac biomarkers after MI often report strong discrimination, but their clinical value is undermined by limited external validation, incomplete calibration assessment, and poor transparency. Our systematic review identifies these recurrent weaknesses, while the proof-of-concept case study demonstrates how a leakage-aware workflow can distinguish clinically plausible signals from structurally inflated performance under controlled analytical conditions. The use of a proxy classification task highlights methodological behavior rather than clinical prognosis, underscoring the need for future studies to validate such frameworks on clinically meaningful post-MI outcomes. Integrating explicit feature governance, nested validation, calibration, decision-analytic assessment, and falsification testing may help move biomarker-based cardiovascular AI from promising retrospective performance towards more reproducible and clinically trustworthy prediction models.

Pain assessment remains one of the most significant challenges in equine clinical practice and welfare monitoring. Despite advances in behavioural pain scales, facial expression scoring, gait analysis and physiological monitoring, current approaches remain fragmented and largely dependent on subjective interpretation — a limitation that is particularly relevant in horses, where pain expression is often subtle, context-dependent and shaped by species-specific behavioural adaptations. We argue that equine pain should be conceptualised as a multidimensional neurobehavioural state emerging from interactions among nociceptive processing, affective responses, autonomic regulation, motor adaptations and environmental context. Rather than evaluating clinical signs, facial expression, behaviour, movement and autonomic physiology independently, future research should integrate them into multimodal biomarkers capable of objectively characterising pain states. To this end, we introduce the Equine Multimodal Pain Biomarker (EMPB): an integrated biological signature derived from behavioural, physiological and neurophysiological domains that reflects the presence, severity or progression of pain in horses. Within this framework, artificial intelligence is viewed not as a replacement for clinical expertise but as a tool for combining heterogeneous data streams into biologically meaningful, clinically actionable representations of pain. Finally, we propose a five-phase roadmap for the development, validation and clinical translation of objective pain biomarkers in horses. The EMPB framework provides a foundation for future research aimed at improving pain assessment, supporting veterinary decision-making and advancing equine welfare.

Background: Unsupervised machine learning has become a cornerstone of computational phenotyping across clinical medicine, genomics, imaging, and multi-omics research. However, phenotype discovery relies on a sequence of analytical decisions – including missing-data handling, preprocessing, dimensionality reduction, clustering methodology, and stochastic initialization – that are rarely evaluated collectively. Although clustering stability has been extensively investigated, the robustness of complete analytical workflows remains largely unexplored. Results: We developed an Analytical Perturbation Framework that systematically quantifies the robustness of phenotype discovery by perturbing complete unsupervised learning workflows rather than individual clustering algorithms. Using a real-world cohort of 1,286 women with polycystic ovary syndrome (PCOS), we generated 116 valid analytical pipelines comprising alternative preprocessing strategies, missing-data handling methods, dimensionality reduction approaches, clustering algorithms, and random initializations. Agreement between independently generated phenotype solutions was consistently low (median Adjusted Rand Index = 0.079), indicating substantial sensitivity of phenotype discovery to routine analytical decisions. Variance decomposition identified preprocessing as the largest contributor to phenotype instability (22.8%), followed by clustering methodology (14.6%), whereas stochastic initialization explained only 3.1% of the observed variability. At the patient level, most individuals exhibited reproducible phenotype assignments (median Patient Robustness Score = 0.719), although a substantial subgroup showed markedly lower assignment stability. Feature perturbation analyses identified follicle-stimulating hormone, anti-thyroglobulin antibodies, anti-thyroid peroxidase antibodies, total testosterone, luteinizing hormone, and androstenedione as the strongest contributors to computational robustness, rather than biological importance. Finally, phenotype solutions demonstrating greater computational robustness also exhibited greater biological coherence during independent validation. Availability and implementation: The analytical framework and reproducible implementation will be made publicly available through a version-controlled repository upon publication. Contact: natalia.piorkowska@pwr.edu.pl