H2: A Dual Hybrid Semantic Data Lake Architecture for Medical Data Harmonization with Human-In-the-Loop verified, LLM Driven Metadata Annotation System

Medical data, by its nature, exhibit a high degree of heterogeneity on multiple levels ranging from (a) different modalities like images, text and time series, (b) diverse tabular schemata introduced by institutions and (c) completely unstructured textual information data provided by healthcare professionals. Data lakes are often used in medical data storage to consolidate all heterogeneous diverse data in a single, central location, where it can be saved "as is", without the need to impose a schema like a data warehouse does. Despite their flexibility, though, data lakes are notorious for the "data swamp" failure. Thus, providing a reliable data harmonization mechanism through metadata, without compromising integrity or flexibility, is a real challenge. To this end, knowledge graphs have attracted attention since they provide a dynamic way to depict relationships without a rigid schema-on-write approach. Additionally, another rigorous task relies on the interoperability of data: application of appropriate ML techniques on such a diverse nature of data is not an easy task, as a domain expert must decide the efficacy of a method to a specific data type or dataset. Metadata annotation can aid by tagging applicable operations, however this requires manual intervention, not to mention the plethora of existing datasets which lack such information. To tackle both challenges, in this paper, we propose a semantic data lake architecture that promotes data harmonization and incorporates a generative annotation process (i.e. LLMs) of non-labeled metadata collections to support the application of meaningful ML techniques. Building on top of this approach, we create a higher level of knowledge, identifying suitability of data with respect to applicable ML operations based on their data nature...

A Transportable Threshold-Based Framework for Interpretable Classification of Medical Data

Black-box models limit the adoption of artificial intelligence in medicine due to their lack of interpretability and reproducibility. We introduce a statistically grounded framework that provides fully interpretable, rule-based clinical classification using the Bernoulli Naïve Bayes (BNB) model. The method applies supervised $χ^2$-guided statistical binarization to continuous variables, identifying thresholds that maximize association with clinical outcomes within the training data. This transformation allows BNB to operate effectively on continuous medical data without sacrificing its inherent transparency. The approach was evaluated on three benchmark datasets, Pima Indians Diabetes, Wisconsin Breast Cancer, and Heart Failure Prediction, achieving area-under-the-curve (AUC) scores of 0.800 for the Pima analysis, 0.984 for Wisconsin Breast Cancer, and 0.919 for Heart Failure Prediction. In addition to discrimination, probabilistic reliability was assessed using leakage-safe cross-validated calibration analysis including Brier score, calibration intercept/slope, and post-hoc beta calibration, which improved probability calibration across datasets. These results suggest that a statistically interpretable framework can achieve performance comparable to more complex models while providing explicit, clinically meaningful decision rules and calibrated risk estimates. To illustrate this transparency concretely, a complete worked example demonstrates that model inference can be reproduced using only a reference table and basic arithmetic, without access to software or proprietary tools. This work offers a practical approach to supporting trustworthy and generalizable AI in real-world healthcare settings.

When, Where, and How: Adaptive Binning for Tabular Self-Supervised Learning

Medical tabular data are ubiquitous in clinical research, but deep learning for tables remains underexplored because reliable labels often require costly expert adjudication, even though structured clinical variables are routinely available in tabular form. Self-supervised learning can leverage these unlabeled tables, and recent binning-based pretexts offer a promising inductive bias, but existing objectives fix a single global quantile discretization and apply feature-agnostic supervision. We propose Adaptive Binning, a training-adaptive discretization pretext for tabular SSL that couples discretization to learning through a feature-wise coarse-to-fine curriculum. Motivated by the spectral bias of neural networks and the principles of curriculum learning, our method progressively refines discretization per feature upon plateau detection and selects representation-aware splits to jointly improve value-space concentration and representation-space coherence. A heterogeneity-aware objective unifies categorical reconstruction with ordinal supervision for numerical features, and experiments on public medical tabular datasets under unified evaluation protocols show consistent gains for linear probing and fine-tuning without dataset-specific discretization tuning. We further introduce a medical tabular SSL benchmark with standardized protocols to support reproducible progress in this underexplored domain. Our code is available at https://github.com/labhai/Adaptive-Binning.