监督文本分类系统检测电子记录中的Fontan患者,精度高于ICD代码
Yuting Guo1, Mohammed A Al-Garadi2, Wendy M Book3,4
1Department of Biomedical Informatics, School of Medicine Emory University Atlanta GA.
Journal of the American Heart Association
|June 22, 2023
概括
自然语言处理模型从电子健康记录中准确地识别Fontan患者,优于传统的国际疾病分类 (ICD) 代码. 这一进步有助于创建更大的Fontan患者队伍进行研究.
科学领域:
- 医疗信息学 医疗信息学
- 计算生物学 计算生物学
- 临床数据分析 临床数据分析
背景情况:
- 芬坦手术与患者的显著发病率和死亡率有关.
- 使用国际疾病分类 (ICD) 代码识别Fontan患者是具有挑战性的,因为代码准确性的限制.
- 准确识别Fontan病例对于研究和临床管理至关重要.
研究的目的:
- 开发和比较基于自然语言处理 (NLP) 的机器学习模型,用于自动检测Fontan患者.
- 评估NLP模型的性能与传统的ICD代码基础分类相比.
- 增强创建大型的Fontan患者队伍进行研究.
主要方法:
- 使用了来自10,935名手动验证患者的自由文本临床笔记 (Fontan的7.1%).
- 在80%的数据上训练和优化机器学习模型,包括支持矢量机 (SVM) 和RoBERTa (基于变压器的语言模型).
- 为RoBERTa实施了一种新的滑动窗口策略,以管理文本长度限制,并使用F1分数对持有数据的模型进行评估.
主要成果:
- 支持矢量机器获得了最高的F1评分 (0.95),超过了RoBERTa (0.89) 和ICD代码分类 (0.81).
- 这两种NLP模型的准确性明显高于ICD基于代码的分类 (P<0.05).
- 移动窗口策略提高了RoBERTa的性能,但没有超过SVM;ICD代码产生了更多的错误阳性.
结论:
- 与ICD代码相比,NLP模型可以自动从临床笔记中识别Fontan患者,准确度更高.
- 这些发现凸显了NLP在改善Fontan相关研究的患者队列识别方面的潜力.
- 在NLP的进一步进展为更精确的临床数据分析提供了有希望的途径.
更多相关视频
13:44Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
42.9K
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.3K
相关概念视频
01:30Heart Failure IV: Classification and Diagnostic Evaluation
20
Heart failure can be classified in various ways, with the most common classifications based on physical activity limitations, disease progression, severity, and treatment strategies.The Functional Classification of Heart Failure divides patients into four categories based on physical activity limitation due to symptom burden.Class I: Patients in this class have cardiac disease but no physical activity limitations. Ordinary activities like walking, climbing stairs, or routine tasks do not cause...
20
01:17Classification of Illness
7.6K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
7.6K
01:26Classification of Systems-I
221
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
221
01:29Cardiomyopathy V: Interprofessional Care
18
Managing cardiomyopathy involves addressing underlying or precipitating causes, treating heart failure with medications, and implementing dietary changes and a balanced exercise and rest regimen.Lifestyle ModificationsCardiomyopathy patients should adopt a low-sodium diet to reduce fluid retention and manage heart failure. A personalized exercise and rest plan helps maintain physical fitness without overstraining the heart. Avoiding alcohol and tobacco is essential to prevent further damage to...
18