Revealing Treatment Non-Adherence Bias in Clinical Machine Learning Using Large Language Models

2025-02-26 · Zhongyuan Liang, Arvind Suresh, Irene Y. Chen

Machine learning systems trained on electronic health records (EHRs) increasingly guide treatment decisions, but their reliability depends on the critical assumption that patients follow the prescribed treatments recorded in EHRs. Using EHR data from 3,623 hypertension patients, we investigate how treatment non-adherence introduces implicit bias that can fundamentally distort both causal inference and predictive modeling. By extracting patient adherence information from clinical notes using a large language model (LLM), we identify 786 patients (21.7%) with medication non-adherence. We further uncover key demographic and clinical factors associated with non-adherence, as well as patient-reported reasons including side effects and difficulties obtaining refills. Our findings demonstrate that this implicit bias can not only reverse estimated treatment effects, but also degrade model performance by up to 5% while disproportionately affecting vulnerable populations by exacerbating disparities in decision outcomes and model error rates. This highlights the importance of accounting for treatment non-adherence in developing responsible and equitable clinical machine learning systems.

📄 PDF Abstract BibTeX arXiv:2502.19625

Code (0)

등록된 구현이 없습니다.

Tasks

Causal InferenceLanguage ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Causal inference Causal inference is the process of drawing a conclusion about a causal connection based on the conditions of the occurrence of an effect. The main difference between causal…

A Machine Learning Approach for Predicting Therapeutic Adherence to Osteoporosis Treatment

2022-03-01 · 2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE) 2022 3 · Ggaliwango Marvin, Md. Golam Rabiul Alam

Osteoporosis is a great disability burden with an expected cost increase of almost 50% by 2025. Due to its long term treatment, 50–70% of the patients withdraw from their osteoporosis medications within the first year of…

BIG-bench Machine Learning Management

A Decade-Scale Benchmark Evaluating LLMs' Clinical Practice Guidelines Detection and Adherence in Multi-turn Conversations

2026-03-26 · Andong Tan, Shuyu Dai, Jinglu Wang, Fengtao Zhou 외 arxiv

Clinical practice guidelines (CPGs) play a pivotal role in ensuring evidence-based decision-making and improving patient outcomes. While Large Language Models (LLMs) are increasingly deployed in healthcare scenarios, it …

Bias in Large Language Models Across Clinical Applications: A Systematic Review

2025-04-03 · Thanathip Suenghataiphorn, Narisara Tribuddharat, Pojsakorn Danpanichkul, Narathorn Kulthamrongsri

Background: Large language models (LLMs) are rapidly being integrated into healthcare, promising to enhance various clinical tasks. However, concerns exist regarding their potential for bias, which could compromise patie…

Image Generation

Developing an Artificial Intelligence Tool for Personalized Breast Cancer Treatment Plans based on the NCCN Guidelines

2025-01-06 · Abdul M. Mohammed, Iqtidar Mansoor, Sarah Blythe, Dennis Trujillo

Cancer treatments require personalized approaches based on a patient's clinical condition, medical history, and evidence-based guidelines. The National Comprehensive Cancer Network (NCCN) provides frequently updated, com…

Large Language Model RAG Retrieval-augmented Generation

Targeted learning of heterogeneous treatment effect curves for right censored or left truncated time-to-event data

2026-03-27 · Matthew Pryce, Karla Diaz-Ordaz, Ruth H. Keogh, Stijn Vansteelandt arxiv

In recent years, there has been growing interest in causal machine learning estimators for quantifying subject-specific effects of a binary treatment on time-to-event outcomes. Estimation approaches have been proposed wh…