使用自然语言处理技术从住院电子病历中提取健康的社会决定因素。

Extracting social determinants of health from inpatient electronic medical records using natural language processing.

作者信息

Martin Elliot A, D'Souza Adam G, Saini Vineet, Tang Karen, Quan Hude, Eastwood Cathy A

机构信息

Centre for Health Informatics, University of Calgary, Calgary, Canada; Health Research Methods and Analytics, Alberta Health Services, Calgary, Canada.

出版信息

J Epidemiol Popul Health. 2024 Dec;72(6):202791. doi: 10.1016/j.jeph.2024.202791. Epub 2024 Nov 14.

DOI:10.1016/j.jeph.2024.202791

PMID:39546940

Abstract

BACKGROUND

Social determinants of health (SDOH) have been shown to be important predictors of health outcomes. Here we developed methods to extract them from inpatient electronic medical record (EMR) data using techniques compatible with current EMR systems.

METHODS

Four social determinants were targeted: patient language barriers, employment status, education, and whether the patient lives alone. Inpatients aged 18 and older with records in the Calgary-wide EMR system were studied. Algorithms were developed on the January 2019 hospital admissions (n=8,999) and validated on the January 2018 hospital admissions (n=8,839). SDOH documented as structured data were compared against those extracted from unstructured free-text notes.

RESULTS

More than twice as many patients had a note documenting a language barrier in EMR data than in structured data; 12 % of patients indicated by EMR notes to be living alone had a partner noted in their structured marital status. The Positive Predictive Value (PPV) of the elements extracted from notes was high, at 99 % (95 % CI 94.0 %-100.0 %) for language barriers, 98 % (95 % CI 92.6 %-99.9 %) for living alone, 96 % (95 % CI 89.8 %-98.8 %) for unemployment, and 88 % (95 % CI 80.0 %-93.1 %) for retirement.

CONCLUSIONS

All SDOH elements were extracted with high PPV. SDOH documentation was largely missing in structured data and sometimes misleading.

摘要

背景

健康的社会决定因素（SDOH）已被证明是健康结果的重要预测指标。在此，我们开发了一些方法，使用与当前电子病历（EMR）系统兼容的技术，从住院电子病历数据中提取这些因素。

方法

针对四个社会决定因素：患者语言障碍、就业状况、教育程度以及患者是否独居。对卡尔加里地区电子病历系统中有记录的18岁及以上住院患者进行研究。算法基于2019年1月的住院患者（n = 8999）开发，并在2018年1月的住院患者（n = 8839）中进行验证。将记录为结构化数据的SDOH与从非结构化自由文本笔记中提取的SDOH进行比较。

结果

电子病历数据中记录有语言障碍的患者数量是结构化数据中的两倍多；电子病历笔记显示独居的患者中，有12%在其结构化婚姻状况中被记录为有伴侣。从笔记中提取的因素的阳性预测值（PPV）很高，语言障碍为99%（95%CI 94.0%-100.0%），独居为98%（95%CI 92.6%-99.9%），失业为96%（95%CI 89.8%-98.8%），退休为88%（95%CI 80.0%-93.1%）。