ShifaMind: A Multiplicative Concept Bottleneck for Interpretable ICD-10 Coding

TL;DR

ShifaMind introduces a multiplicative concept bottleneck architecture for interpretable ICD-10 coding, balancing accuracy and transparency in clinical text classification.

Contribution

It proposes a novel multiplicative bottleneck design that improves predictive performance and interpretability over traditional concept bottleneck models.

Findings

Achieves competitive F1, AUC, and ranking metrics on MIMIC-IV ICD-10 coding.

Outperforms five baseline ICD-coding models in predictive and interpretability metrics.

Provides concept-mediated explanations with substantial performance gains.

Abstract

Automated ICD-10 coding from clinical discharge summaries requires models that are both accurate on long-tailed multi-label classification tasks and interpretable to clinicians. Concept Bottleneck Models (CBMs) offer a principled framework for interpretability by routing predictions through human-interpretable concepts, but this transparency often comes at a cost: compressing rich clinical text representations into a narrow concept layer can restrict gradient flow and limit predictive capacity. We present ShifaMind, a concept-grounded architecture built around a Multiplicative Concept Bottleneck (MCB), which changes the form, rather than the width, of the bottleneck. Instead of projecting through a narrow concept layer, ShifaMind uses a learned multiplicative gate over a concept-grounded representation while retaining a scalar concept interface for inspection. On MIMIC-IV top-50 ICD-10 coding, ShifaMind achieves performance competitive with LAAT, the strongest baseline, across F1, AUC, and ranking metrics, while outperforming five additional ICD-coding baselines and providing concept-mediated explanations. Its substantial gains over a capacity-matched Vanilla CBM in both predictive performance and interpretability-oriented metrics highlight the importance of the bottleneck design.