Advances in Electronic Phenotyping: From Rule-Based Definitions to Machine Learning Models
Advances in Electronic Phenotyping: From Rule-Based Definitions to Machine Learning Models
复制标题
DOI：
10.1146/annurev-biodatasci-080917-013315
复制
发表时间：
2018-01-01
期刊：
影响因子：
--
通讯作者：
Shah, Nigam H.
中科院分区：
文献类型：
--
作者：
Banda, Juan M.;Seneviratne, Martin;Shah, Nigam H.
随着电子健康记录（EHR）的广泛采用，大型结构化和非结构化患者数据库可用于进行观察性研究。发现具有特定条件或结果的患者，即表型分析，是使用这些新的EHR数据时遇到的最基本的研究问题之一。表型分析构成了转化研究、比较有效性研究、临床决策支持和使用常规收集的EHR数据进行人群健康分析的基础。我们回顾了电子表型的演变，从早期的基于规则的方法到最前沿的监督和无监督机器学习模型。我们的目标是涵盖最有影响力的论文在相称的细节，重点是方法和实施。最后，对未来的研究方向进行了展望。
With the widespread adoption of electronic health records (EHRs), large repositories of structured and unstructured patient data are becoming available to conduct observational studies. Finding patients with specific conditions or outcomes, known as phenotyping, is one of the most fundamental research problems encountered when using these new EHR data. Phenotyping forms the basis of translational research, comparative effectiveness studies, clinical decision support, and population health analyses using routinely collected EHR data. We review the evolution of electronic phenotyping, from the early rule-based methods to the cutting edge of supervised and unsupervised machine learning models. We aim to cover the most influential papers in commensurate detail, with a focus on both methodology and implementation. Finally, future research directions are explored.