A Novel Method to Metigate Demographic and Expert Bias in ICD Coding with Causal Inference

TL;DR

This paper introduces DECI, a causal inference-based method that reduces demographic and expert biases in ICD coding, improving accuracy and fairness in multi-label medical text classification.

Contribution

The paper presents a novel causality-based approach, DECI, that models three prediction pathways and uses counterfactual reasoning to mitigate biases in ICD coding.

Findings

DECI outperforms existing models in accuracy.

DECI effectively reduces demographic bias.

DECI minimizes bias from irrelevant expert information.

Abstract

ICD(International Classification of Diseases) coding involves assigning ICD codes to patients visit based on their medical notes. Considering ICD coding as a multi-label text classification task, researchers have developed sophisticated methods. Despite progress, these models often suffer from label imbalance and may develop spurious correlations with demographic factors. Additionally, while human coders assign ICD codes, the inclusion of irrelevant information from unrelated experts introduces biases. To combat these issues, we propose a novel method to mitigate Demographic and Expert biases in ICD coding through Causal Inference (DECI). We provide a novel causality-based interpretation in ICD Coding that models make predictions by three distinct pathways. And based counterfactual reasoning, DECI mitigate demographic and expert biases. Experimental results show that DECI outperforms state-of-the-art models, offering a significant advancement in accurate and unbiased ICD coding.