The architecture of a tissue-engineering scaffold affects how cells attach, migrate, and remodel newly formed tissue. At present, many scaffolds are still developed through repeated adjustment of a few structural variables, making it difficult to balance porosity with mechanical strength or degradation with the pace of tissue formation. Generative artificial intelligence may help shift scaffold development toward a target-driven process. Given a desired biological or mechanical outcome, a model could identify structures that are likely to achieve it. This possibility depends on training data that connect scaffold features with biological responses. In this review, we consider the use of generative methods together with bioinformatics for scaffold design. We describe potentially useful data sources, including micro-computed tomography (CT) images, mechanical measurements, single-cell RNA sequencing, and degradation data. We also examine generative adversarial networks, variational autoencoders, diffusion models, and evolutionary algorithms. Rather than treating these approaches as interchangeable, we discuss the design tasks for which their strengths differ. Examples from cardiac, bone, cartilage, and related applications show how tissue context shapes data requirements and model selection. We close by considering data comparability, validation across length scales, and the practical challenges of clinical use. These issues will determine whether generative tools can support more tailored scaffold design.

The trustworthiness of medical AI systems is often undermined by their potential to violate established clinical principles, a critical issue in self-supervised learning (SSL) frameworks where explicit domain knowledge is typically disregarded. To address this trust deficit, we propose the Logic-Constrained Joint Embedding Predictive Architecture (LC-JEPA). LC-JEPA is a novel framework that bridges neural and symbolic learning by seamlessly integrating predefined medical rules into the SSL process via differentiable logic programming. It utilizes a dedicated Differentiable Constraint Satisfaction Layer (D-CSL) to formally encode clinical constraints, enabling end-to-end joint optimization of both predictive accuracy and logical consistency. We introduce the Constraint Satisfaction Rate (CSR) as a specialized metric to quantify adherence to medical knowledge. Comprehensive evaluation on the MIT-BIH Arrhythmia Database demonstrates that LC-JEPA achieves high accuracy (97.5%) while significantly improving domain adherence (CSR of 93.9%), substantially outperforming unconstrained baselines (e.g., Vanilla JEPA’s 86.4% CSR). Extensive sensitivity analysis confirms that the logic constraint is essential: removing it causes accuracy to drop from 97.5% to 32.1%, while the specific constraint weight λ ∈ [0.1,2.0] has minimal impact on performance. By successfully uniting representation learning with symbolic reasoning, LC-JEPA provides a robust and generalizable solution for building safer, more reliable, and clinically deployable trustworthy AI systems for ECG arrhythmia analysis.

Accurate and interpretable blood glucose prediction is critical for optimizing insulin therapy and preventing adverse events in type 1 diabetes (T1D) management. However, existing deep learning models often lack transparency, limiting their clinical adoption. We introduce a novel neural-symbolic framework that integrates Fourier neural operators (FNOs) with clinical rules to predict 30-minute-ahead blood glucose levels with high accuracy and interpretability. FNOs capture periodic glucose patterns, such as circadian rhythms and meal responses, while differentiable clinical rules encode medical knowledge, providing actionable insights like hypoglycemia risk alerts. Evaluated on the OhioT1DM dataset, our model achieves a mean absolute error (MAE) of 10.2 mg/dL, meeting ISO 15197:2013 standards, and 99.8% Clarke Error Grid A+B coverage, ensuring clinical safety. Leave-one-subject-out cross-validation across 12 subjects demonstrates robust generalization (MAE = 8.85 ± 1.33 mg/dL), addressing concerns about sample size limitations. The model exhibits strong robustness to continuous glucose monitoring (CGM) measurement noise (maintaining ISO compliance at 10% noise) and missing data (5.4% performance degradation at 40% data loss). By generating interpretable outputs, such as trend analyses and risk warnings, our framework supports clinical decision-making, enhances patient trust, and facilitates personalized diabetes care. This work advances medical informatics by combining data-driven and knowledge-driven methods, offering a scalable solution for real-time glucose monitoring and insulin dosing in T1D.