analiza aiqbench
This paper introduces REFINE, a novel machine learning framework that decouples nonlinear preprocessing from linear prediction to achieve global interpretability in psychiatric prognosis tasks. By leveraging future data to stabilize baseline measurements before fitting an interpretable model, the method recovers Bayes-optimal conditional means without sacrificing predictive flexibility or relying on post-hoc attribution techniques. The approach offers a robust solution for clinical AI where maintaining clear, globally understandable relationships between inputs and outcomes is critical for trust and adoption.
Global Interpretability via Automated Preprocessing: A Framework Inspired by Psychiatric Questionnaires
arXiv:2602.23459v2 Announce Type: replace Abstract: Psychiatric questionnaires are highly context sensitive and often only weakly predict subsequent symptom severity, which makes the prognostic relationship difficult to learn. Although flexible nonlinear models can improve predictive accuracy, their limited interpretability can erode clinical trust. In fields such as imaging and omics, investigators commonly address visit- and instrument-specific artifacts by extracting stable signal through preprocessing and then fitting an interpretable linear model. We adopt the same strategy for questionnaire data by decoupling preprocessing from prediction: REFINE (Redundancy-Exploiting Follow-up-Informed Nonlinear Enhancement) uses follow-up information to learn a nonlinear, item-aligned preprocessing of baseline measurements, and then maps these stabilized baseline items to future severity through a linear coefficient matrix. This construction constrains where nonlinearity enters rather than restricting the end-to-end predictive function class, allowing the prognostic relationship to remain globally interpretable through a single coefficient matrix rather than through post hoc local attributions. In the population, the resulting predictor recovers the Bayes-optimal conditional mean, so global linear interpretability does not require sacrificing nonlinear predictive flexibility. In experiments, REFINE outperforms other interpretable approaches while preserving clear global attribution of prognostic factors across psychiatric and non-psychiatric longitudinal prediction tasks.
Abstract:Psychiatric questionnaires are highly context sensitive and often only weakly predict subsequent symptom severity, which makes the prognostic relationship difficult to learn. Although flexible nonlinear models can improve predictive accuracy, their limited interpretability can erode clinical trust. In fields such as imaging and omics, investigators commonly address visit- and instrument-specific artifacts by extracting stable signal through preprocessing and then fitting an interpretable linear model. We adopt the same strategy for questionnaire data by decoupling preprocessing from prediction: REFINE (Redundancy-Exploiting Follow-up-Informed Nonlinear Enhancement) uses follow-up information to learn a nonlinear, item-aligned preprocessing of baseline measurements, and then maps these stabilized baseline items to future severity through a linear coefficient matrix. This construction constrains where nonlinearity enters rather than restricting the end-to-end predictive function class, allowing the prognostic relationship to remain globally interpretable through a single coefficient matrix rather than through post hoc local attributions. In the population, the resulting predictor recovers the Bayes-optimal conditional mean, so global linear interpretability does not require sacrificing nonlinear predictive flexibility. In experiments, REFINE outperforms other interpretable approaches while preserving clear global attribution of prognostic factors across psychiatric and non-psychiatric longitudinal prediction tasks.
Machine Learning (cs.LG); Quantitative Methods (q-bio.QM); Machine Learning (stat.ML)
arXiv:2602.23459 [cs.LG]
(or arXiv:2602.23459v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2602.23459 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 285 cuvinte
Subiecte conexe
Reducing medical claims review time with AI on AWS: The EXL Medical IDP solution
AWS · 21 sept. 2026
fSRD: Fuzzy Spectral Region Decomposition -- Automated Multi Operator Koopman Representations via an Adaptive Spectral Learning Architecture
arXiv · 21 iul. 2026
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · 18 sept. 2026
AI Transparency: Governance, Explainability, and Data Practices
Databricks · 20 iul. 2026