arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.04008cs.CY
收藏

算法偏见、通用模型与临床医学

Algorithmic Bias, Generalist Models,and Clinical Medicine

Geoff Keeling

AI总结:

本文针对临床机器学习从窄域模型转向通用模型的趋势,分析了通用模型新型算法偏见与传统临床模型偏见的差异及成因,并提出了偏见缓解的实用建议。

摘要:

临床机器学习的技术格局正在发生变化,动摇了关于算法偏见的性质与成因的普遍假设。一方面,临床机器学习的主流范式是窄域的:模型在生物医学数据集上训练,用于诊断、治疗建议等特定临床任务。另一方面,新兴范式是通用型的:Google的BERT、PaLM等通用语言模型,正越来越多地通过提示工程或在生物医学数据集上微调,适配临床应用场景。这类下一代模型中,许多相比既往临床模型实现了显著的性能提升,但同时也引入了新型算法偏见,且让算法偏见与训练数据偏见之间的解释关系变得更为复杂。本文阐明了通用模型的偏见与既往临床模型的偏见在哪些方面存在差异、差异如何产生,并提出了算法偏见缓解的实用建议。

英文摘要:

The technical landscape of clinical machine learning is shifting in ways that destabilize pervasive assumptions about the nature and causes of algorithmic bias. On one hand, the dominant paradigm in clinical machine learning is narrow in the sense that models are trained on biomedical datasets for particular clinical tasks such as diagnosis and treatment recommendation. On the other hand, the emerging paradigm is generalist in the sense that general-purpose language models such as Google's BERT and PaLM are increasingly being adapted for clinical use cases via prompting or fine-tuning on biomedical datasets. Many of these next-generation models provide substantial performance gains over prior clinical models, but at the same time introduce novel kinds of algorithmic bias and complicate the explanatory relationship between algorithmic biases and biases in training data. This paper articulates how and in what respects biases in generalist models differ from biases in prior clinical models, and draws out practical recommendations for algorithmic bias mitigation.

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。

↑