No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discovery

TL;DR

This paper introduces II-KEA, a framework that combines causal discovery, personalized knowledge, and large language models to make healthcare predictions more interpretable and interactive for clinicians.

Contribution

It presents a novel knowledge-enhanced agent-driven causal discovery framework that improves interpretability and interactivity in healthcare prediction models.

Findings

Demonstrates superior performance on MIMIC-III and MIMIC-IV datasets.

Enhances interpretability through explicit causal reasoning.

Enables clinician interaction via customizable knowledge bases.

Abstract

Deep learning models trained on extensive Electronic Health Records (EHR) data have achieved high accuracy in diagnosis prediction, offering the potential to assist clinicians in decision-making and treatment planning. However, these models lack two crucial features that clinicians highly value: interpretability and interactivity. The ``black-box'' nature of these models makes it difficult for clinicians to understand the reasoning behind predictions, limiting their ability to make informed decisions. Additionally, the absence of interactive mechanisms prevents clinicians from incorporating their own knowledge and experience into the decision-making process. To address these limitations, we propose II-KEA, a knowledge-enhanced agent-driven causal discovery framework that integrates personalized knowledge databases and agentic LLMs. II-KEA enhances interpretability through explicit reasoning and causal analysis, while also improving interactivity by allowing clinicians to inject their knowledge and experience through customized knowledge bases and prompts. II-KEA is evaluated on both MIMIC-III and MIMIC-IV, demonstrating superior performance along with enhanced interpretability and interactivity, as evidenced by its strong results from extensive case studies.