A method for inferring medical diagnoses from patient similarities.

A method for inferring medical diagnoses from patient similarities.
复制标题

DOI:
10.1186/1741-7015-11-194
复制
发表时间:
2013-09-02
期刊:
影响因子:
9.3
通讯作者:
Sharan R
Sharan R
中科院分区:
医学1区
文献类型:
--
作者:
Gottlieb A;Stein GY;Ruppin E;Altman RB;Sharan R

文献摘要

参考文献

被引文献

相似文献

临床决策支持系统帮助医生解释复杂的患者数据。然而,它们通常以每个患者为基础进行操作,并且不利用电子健康记录(EHR)中广泛的潜在医学知识。大型电子健康记录系统的出现提供了将人口信息积极整合到这些工具中的机会。在这里,我们评估的能力,一个大型语料库的电子记录,以预测个人出院诊断。我们提出了一种方法,利用患者之间的相似性沿着多个维度来预测最终的出院诊断。使用人口统计学,初始血液和心电图测量,以及来自两家独立医院的住院患者的病史,我们在交叉验证中获得了高性能(曲线下面积>0.88),并正确预测了超过84%的受试患者的前十名预测中的至少一个诊断。重要的是,我们的方法为主要疾病类别提供了准确的预测(交叉验证精度>0.86),包括传染病和寄生虫病,内分泌和代谢疾病以及循环系统疾病。我们的表现适用于慢性和急性诊断。我们的研究结果表明,人们可以利用电子健康记录中嵌入的基于人群的信息来进行患者特定的预测任务。
Clinical decision support systems assist physicians in interpreting complex patient data. However, they typically operate on a per-patient basis and do not exploit the extensive latent medical knowledge in electronic health records (EHRs). The emergence of large EHR systems offers the opportunity to integrate population information actively into these tools. Here, we assess the ability of a large corpus of electronic records to predict individual discharge diagnoses. We present a method that exploits similarities between patients along multiple dimensions to predict the eventual discharge diagnoses. Using demographic, initial blood and electrocardiography measurements, as well as medical history of hospitalized patients from two independent hospitals, we obtained high performance in cross-validation (area under the curve >0.88) and correctly predicted at least one diagnosis among the top ten predictions for more than 84% of the patients tested. Importantly, our method provides accurate predictions (>0.86 precision in cross validation) for major disease categories, including infectious and parasitic diseases, endocrine and metabolic diseases and diseases of the circulatory systems. Our performance applies to both chronic and acute diagnoses. Our results suggest that one can harness the wealth of population-based information embedded in electronic health records for patient-specific predictive tasks.
DOI: 10.1097/mlr.0b013e3181de9e17
发表时间: 2010-06-01
期刊: MEDICAL CARE
影响因子: 3
作者:
Wu, Jionglin;Roy, Jason;Stewart, Walter F.
通讯作者: Stewart, Walter F.
DOI: 10.2307/2981737
发表时间: 1984-01-01
影响因子: 2
作者:
SPIEGELHALTER, DJ;KNILLJONES, RP
通讯作者: KNILLJONES, RP
DOI: 10.1136/bmj.38398.500764.8f
发表时间: 2005-04-02
影响因子: 105.7
作者:
Kawamoto, K;Houlihan, CA;Lobach, DF
通讯作者: Lobach, DF
DOI: 10.1136/hrt.2005.062018
发表时间: 2005-05-01
期刊: HEART
影响因子: 5.7
作者:
Dargie, H
通讯作者: Dargie, H
DOI: 10.1001/archinternmed.2010.527
发表时间: 2011-05-23
影响因子: --
作者:
Romano, Max J.;Stafford, Randall S.
通讯作者: Stafford, Randall S.