Global Interpretability via Automated Preprocessing: A Framework Inspired by Psychiatric Questionnaires

2026-02-26

AI Summary

Psychiatric questionnaire data are often context-sensitive and exhibit limited predictive power; while nonlinear models can achieve high accuracy, they typically lack global interpretability, undermining clinical trust. To address this, this work proposes the REFINE framework, which employs a two-stage modeling strategy: first, a nonlinear preprocessing module integrates redundant information and longitudinal follow-up data to stabilize item representations, and then a linear model maps these refined representations to future symptom severity. By confining nonlinearity to the preprocessing stage and preserving a linear prediction relationship, REFINE achieves both strong predictive performance and global interpretability through coefficient matrices. Evaluated on both psychiatric and non-psychiatric longitudinal prediction tasks, REFINE outperforms existing interpretable methods and provides clear attribution of prognostic factors.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Knowledge Representation and Reasoning: Preferences
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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: we restrict nonlinear capacity to a baseline preprocessing module that estimates stable item values, and then learn a linear mapping from these stabilized baseline items to future severity. We refer to this two-stage method as REFINE (Redundancy-Exploiting Follow-up-Informed Nonlinear Enhancement), which concentrates nonlinearity in preprocessing while keeping the prognostic relationship transparently linear and therefore globally interpretable through a coefficient matrix, rather than through post hoc local attributions. In experiments, REFINE outperforms other interpretable approaches while preserving clear global attribution of prognostic factors across psychiatric and non-psychiatric longitudinal prediction tasks.

Problem

• psychiatric questionnaires
• prognostic relationship
• interpretability
• context sensitivity
• symptom severity prediction

Innovation

• global interpretability
• preprocessing
• linear prognostic model
• psychiatric questionnaires
• REFINE