Objectives: Artificial intelligence (AI) applications utilizing electronic health records (EHRs) have gained popularity, but they also introduce various types of bias. This study aims to systematically review the literature that address bias in AI research utilizing EHR data. Methods: A systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guideline. We retrieved articles published between January 1, 2010, and October 31, 2022, from PubMed, Web of Science, and the Institute of Electrical and Electronics Engineers. We defined six major types of bias and summarized the existing approaches in bias handling. Results: Out of the 252 retrieved articles, 20 met the inclusion criteria for the final review. Five out of six bias were covered in this review: eight studies analyzed selection bias; six on implicit bias; five on confounding bias; four on measurement bias; two on algorithmic bias. For bias handling approaches, ten studies identified bias during model development, while seventeen presented methods to mitigate the bias. Discussion: Bias may infiltrate the AI application development process at various stages. Although this review discusses methods for addressing bias at different development stages, there is room for implementing additional effective approaches. Conclusion: Despite growing attention to bias in healthcare AI, research using EHR data on this topic is still limited. Detecting and mitigating AI bias with EHR data continues to pose challenges. Further research is needed to raise a standardized method that is generalizable and interpretable to detect, mitigate and evaluate bias in medical AI.

翻译：目的：利用电子健康记录（EHR）的人工智能（AI）应用日益普及，但同时也引入了多种类型的偏见。本研究旨在系统性综述利用EHR数据的AI研究中处理偏见的文献。方法：按照《系统综述和荟萃分析优先报告条目》（PRISMA）指南进行系统性综述。我们从PubMed、Web of Science和电气电子工程师学会检索了2010年1月1日至2022年10月31日期间发表的文章。我们定义了六种主要偏见类型，并总结了现有的偏见处理方法。结果：在检索到的252篇文章中，20篇符合纳入标准进入最终综述。本研究覆盖了六种偏见中的五种：八项研究分析了选择偏见；六项研究涉及隐性偏见；五项研究涉及混杂偏见；四项研究涉及测量偏见；两项研究涉及算法偏见。在偏见处理方法方面，十项研究在模型开发过程中识别了偏见，而十七项研究提出了缓解偏见的方法。讨论：偏见可能在AI应用开发过程的不同阶段渗透。虽然本综述讨论了不同开发阶段处理偏见的方法，但仍需实施更多有效方法。结论：尽管医疗AI中的偏见日益受到关注，但利用EHR数据进行相关研究仍有限。使用EHR数据检测和缓解AI偏见仍然面临挑战。需要进一步研究，以提出一种标准化、可推广且可解释的方法，用于检测、缓解和评估医疗AI中的偏见。