Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2410.14236 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914978171191296 |
|---|---|
| author | Zhang, Bin Wang, Junli |
| author_facet | Zhang, Bin Wang, Junli |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_14236 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Novel Method to Metigate Demographic and Expert Bias in ICD Coding with Causal Inference Zhang, Bin Wang, Junli Computation and Language 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. |
| title | A Novel Method to Metigate Demographic and Expert Bias in ICD Coding with Causal Inference |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.14236 |