aiqbench analysis
This paper introduces BFHD, a novel framework for harmonizing heterogeneous clinical assessment systems by treating measurement translation as a bidirectional recoverability problem. The method explicitly decomposes data into translatable and non-translatable components using feature-wise output gating to ensure stability across different centers and time periods. By moving beyond simple total-score linking, this approach addresses critical challenges in integrating diverse medical datasets for robust AI-driven clinical analysis.
BFHD: Bidirectional Feature Harmonization Decomposition for Heterogeneous Clinical Assessments
arXiv:2610.19352v1 Announce Type: new Abstract: Clinical assessments are often collected using heterogeneous assessment systems across centers and time, leading to records that mix different but related sets of measurements. This motivates harmonization beyond total-score linking. We formulate clinical harmonization at the measurement level as a bidirectional recoverability problem: given paired observations from two assessment systems, the goal is to identify which measurements can be reliably translated in both directions within an application-defined tolerance, while separating non-translatable components. We propose Bidirectional Feature Harmonization Decomposition (BFHD), a feasibility-driven framework that enforces bidirectionally coupled translation and uses feature-wise output gating to produce an explicit decomposition in the original measurement space. Experiments on synthetic data and real clinical assessment pairs show that BFHD achieves broader feasible harmonization coverage and improved subset stability compared to baselines.
Abstract:Clinical assessments are often collected using heterogeneous assessment systems across centers and time, leading to records that mix different but related sets of measurements. This motivates harmonization beyond total-score linking. We formulate clinical harmonization at the measurement level as a bidirectional recoverability problem: given paired observations from two assessment systems, the goal is to identify which measurements can be reliably translated in both directions within an application-defined tolerance, while separating non-translatable components. We propose Bidirectional Feature Harmonization Decomposition (BFHD), a feasibility-driven framework that enforces bidirectionally coupled translation and uses feature-wise output gating to produce an explicit decomposition in the original measurement space. Experiments on synthetic data and real clinical assessment pairs show that BFHD achieves broader feasible harmonization coverage and improved subset stability compared to baselines.
17 pages, 2 figures, 9 tables. Extended version of the paper published in IJCAI-ECAI 2026, including additional supplementary material in the appendices
Machine Learning (cs.LG)
arXiv:2610.19352 [cs.LG]
(or arXiv:2610.19352v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.19352 arXiv-issued DOI via DataCite (pending registration)
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-26), pp. 7046-7054, 2026
https://doi.org/10.24963/ijcai.2026/784 DOI(s) linking to related resources
Full text under the publisher's open licence · 186 words
Related coverage
Synergistic Vision-Language Reinforcement Enables Scalable On-Demand Analysis across Diverse Clinical Tasks
arXiv · Sep 11, 2026
Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
arXiv · Aug 25, 2026
GeoNIRS: Geometry-Aware Pretraining for Heterogeneous fNIRS Representation Learning
arXiv · Oct 14, 2026
LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys
arXiv · Sep 16, 2026