针对来源混杂的后门调整用于多机构临床文本的鲁棒文本分类
Backdoor Adjustment of Confounding by Provenance for Robust Text Classification of Multi-institutional Clinical Notes
AI总结：
针对多机构临床数据整合带来的来源混杂偏差问题，本研究在药物滥用标注的多站点临床文本数据集上，验证了后门调整可有效缓解分布偏移、提升文本分类鲁棒性。
摘要：
自然语言处理（NLP）方法已被广泛应用于临床任务。机器学习和深度学习方法已被用于提升临床NLP的性能。然而，这些方法需要足够大的数据集进行训练，且已被证明训练后的模型在不同站点间的迁移效果不佳。这些问题推动了不同机构间的数据收集与整合，以构建准确且可迁移的模型。但这可能引入一种被称为“来源混杂”的偏差。当部署时的源特定数据分布存在差异时，这可能会损害模型性能。为解决该问题，我们在一个标注了药物滥用提及的多站点临床文本数据集上，评估了后门调整在文本分类中的效用。我们使用一个专为衡量对分布偏移的鲁棒性而设计的评估框架，来评估后门调整的效用。我们的结果表明，后门调整能够有效缓解混杂偏移。
英文摘要：
Natural Language Processing (NLP) methods have been broadly applied to clinical tasks. Machine learning and deep learning approaches have been used to improve the performance of clinical NLP. However, these approaches require sufficiently large datasets for training, and trained models have been shown to transfer poorly across sites. These issues have led to the promotion of data collection and integration across different institutions for accurate and portable models. However, this can introduce a form of bias called confounding by provenance. When source-specific data distributions differ at deployment, this may harm model performance. To address this issue, we evaluate the utility of backdoor adjustment for text classification in a multi-site dataset of clinical notes annotated for mentions of substance abuse. Using an evaluation framework devised to measure robustness to distributional shifts, we assess the utility of backdoor adjustment. Our results indicate that backdoor adjustment can effectively mitigate for confounding shift.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
