CHiRPE: A Step Towards Real-World Clinical NLP with Clinician-Oriented Model Explanations

2026-01-26

AI Summary

This study addresses the limited clinical interpretability of existing NLP tools, which often fail to align with physicians’ reasoning logic. Leveraging 944 semi-structured clinical interview transcripts, the authors develop an end-to-end NLP pipeline that integrates symptom-domain mapping, LLM-based summarization, and BERT classifiers to achieve high-accuracy prediction of psychosis risk—exceeding 90% accuracy across three BERT variants. To enhance clinical utility, the work introduces a novel physician-in-the-loop, concept-guided SHAP explanation framework, presented through a hybrid graph-text summary format. This approach significantly improves interpretability from a clinical perspective. In evaluations by 28 clinical experts, the proposed explanation format was strongly preferred over existing baseline methods, demonstrating its practical relevance and usability in real-world clinical settings.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

The medical adoption of NLP tools requires interpretability by end users, yet traditional explainable AI (XAI) methods are misaligned with clinical reasoning and lack clinician input. We introduce CHiRPE (Clinical High-Risk Prediction with Explainability), an NLP pipeline that takes transcribed semi-structured clinical interviews to: (i) predict psychosis risk; and (ii) generate novel SHAP explanation formats co-developed with clinicians. Trained on 944 semi-structured interview transcripts across 24 international clinics of the AMP-SCZ study, the CHiRPE pipeline integrates symptom-domain mapping, LLM summarisation, and BERT classification. CHiRPE achieved over 90% accuracy across three BERT variants and outperformed baseline models. Explanation formats were evaluated by 28 clinical experts who indicated a strong preference for our novel concept-guided explanations, especially hybrid graph-and-text summary formats. CHiRPE demonstrates that clinically-guided model development produces both accurate and interpretable results. Our next step is focused on real-world testing across our 24 international sites.

Problem

• Clinical NLP
• Explainable AI
• Model Interpretability
• Psychosis Risk Prediction
• Clinician-Oriented Explanations

Innovation

• clinician-oriented explainability
• concept-guided explanations
• hybrid graph-and-text summary
• symptom-domain mapping
• clinical NLP