相关实验视频

Updated: Aug 10, 2026

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis

Published on: September 26, 2018

使用自然语言处理在住院患者电子病历数据中的脑血管疾病病例识别

Jie Pan^1,2, Zilong Zhang³, Steven Ray Peters⁴

¹Centre for Health Informatics, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada. jie.pan@ucalgary.ca.

Brain informatics

|September 2, 2023

概括

这项研究开发了一种自然语言处理 (NLP) 算法,用于在电子病历 (EMR) 中检测脑血管疾病 (CeVD). 与用于自动化CeVD识别的ICD代码相比,NLP模型显示出更高的性能.

科学领域:

医疗信息学医疗信息学
自然语言处理自然语言处理.
医疗保健服务研究医疗服务研究

背景情况:

从电子病历 (EMR) 中自动检测脑血管疾病 (CeVD) 对监测和患者护理至关重要.
目前使用编码器抽象的方法面临延迟和代码不足的问题.
这项研究旨在创建一种自然语言处理 (NLP) 方法,使用EMR临床笔记来检测CeVD.

研究的目的:

开发和评估一种基于NLP的算法,用于在住院电子病历 (EMR) 中检测脑血管疾病 (CeVD).
将NLP模型的性能与CeVD识别的传统ICD-10-CA代码进行比较.

主要方法:

使用临床概念提取和机器学习 (随机森林,XGBoost) 对住院患者的EMR数据进行训练的NLP预测模型.
验证模型性能与图表审查作为参考标准.
将NLP模型性能与国际疾病分类 (ICD-10-CA) 代码进行比较,使用灵敏度,特异性,PPV和NPV.

主要成果:

使用统一医疗语言系统概念和TF-IDF的XGBoost模型在CeVD检测方面取得了卓越的性能.
对于CeVD识别的关键临床文件包括护理转移报告,出院摘要,护理笔记和住院患者咨询.
在敏感度 (70.0%对25.0%) 和积极预测值 (87.8%对82.6%) 方面,NLP模型显著超过了ICD代码.

结论:

开发的NLP算法在从EMR中检测脑血管疾病 (CeVD) 方面明显优于ICD代码.
NLP模型提供了一个有希望的自动化工具来识别CeVD病例,支持未来的监测和纵向研究.

关键词:

脑血管疾病是脑血管疾病.疾病识别疾病识别电子健康记录是电子健康记录.机器学习是机器学习.自然语言处理自然语言处理.

更多相关视频

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

Evaluation of the Cognitive Performance of Hypertensive Patients with Silent Cerebrovascular Lesions

Evaluation of the Cognitive Performance of Hypertensive Patients with Silent Cerebrovascular Lesions

Published on: April 23, 2021

相关概念视频

Hemorrhagic Stroke l: Introduction

Hemorrhagic Stroke l: Introduction

A hemorrhagic stroke is an acute neurological event that occurs when a weakened cerebral blood vessel ruptures, allowing blood to accumulate within or around the brain. The sudden release of blood forms a focal hematoma that increases intracranial pressure, displaces neural tissue, and can obstruct cerebrospinal fluid pathways. These effects may be compounded by intraventricular extension of the hemorrhage, cerebral edema, or compression of adjacent structures, all of which contribute to...

Dementia l: Introduction

Dementia l: Introduction

Dementia is an acquired, progressive syndrome characterized by a decline in multiple cognitive domains severe enough to impair daily functioning and reduce independence. Although memory loss is a central feature, the diagnosis requires additional deficits involving language, executive function, visuospatial skills, judgment, calculation, or abstract reasoning. These cognitive impairments reflect underlying neurodegenerative or vascular processes that gradually disrupt neuronal networks...