机器学习模型和人类专业知识对护理干预分类的比较分析
Jerome Niyirora1,2, Lynne Longtin1, Cynthia Grabski1,2
1College of Health Sciences, SUNY Polytechnic Institute, Utica, NY 13502, United States.
机器学习模型显示了分类护理干预的潜力,但不能完全取代人类的专业知识. 复杂的,取决于上下文的临床文档需要进一步开发.
科学领域:
- 临床信息学 临床信息学
- 医疗保健中的人工智能
- 护理文档护理文档
背景情况:
- 护理笔记的自动分类对于标准化数据和基准测试至关重要.
- 护理干预分类 (NIC) 系统为护理护理提供了一个标准化的框架.
研究的目的:
- 将机器学习 (ML) 模型与人类专家的性能进行比较,将护理笔记映射到NIC系统中.
- 识别ML模型在临床文档分类中出色的领域,以及在临床文档分类中落后的领域.
主要方法:
- 开发和评估了四种ML模型:TF-IDF,UMLS语义映射,GPT-4o mini和生物临床BERT.
- 使用了一组数据集,该数据集是未识别的家庭医疗保健护理笔记.
- 使用协议统计,精度,回忆,F1分数和科恩的卡帕评估绩效,将ML模型与专家护士分类进行比较.
主要成果:
- 人类专家证明了比ML模型更高的同意和F1分数.
- 在机器学习模型中,GPT-4o mini实现了最佳性能,但仍然落后于人类专家.
- 机器学习模型在常见的,明确定义的干预措施 (例如药物管理) 上表现良好,但在细微的,取决于上下文的干预措施 (例如信息管理) 上表现不佳.
结论:
- 当前的ML模型可以帮助,但不能完全取代复杂的护理干预分类的人类判断.
- 改进的ML方法是必要的,以准确地捕捉临床术语和特定背景文档的细微差别.
更多相关视频
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
相关概念视频
Nursing Interventions II: Selecting and Classifying the Nursing Interventions
Current Trends in Nursing II
Nursing Evaluation
Documentation of Nursing Diagnosis
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...
Data Validation
Nursing assessment guides are generally based on holistic models rather than medical...
Nursing Process for Patient and Caregiver Teaching I: Assessment and Diagnosis
It is critical to determine the patient's learning needs during the assessment. Determination of learning needs compounds data...
