连接电子健康记录用于多发性硬化症研究:确定性,概率和机器学习连接方法的比较研究
Ohoud Almadani1, Yasser Albogami2, Adel Alrwisan1
1Saudi Food and Drug Authority, 4904 northern ring branch rd, 13513, Hittin Dist, Unit number : 1, Riyadh, 13513, Saudi Arabia, 966 555300732.
JMIR medical informatics
|February 4, 2026
概括
概率链接有效地将多发性硬化症 (MS) 研究的非识别患者数据连接起来,在没有唯一标识符的情况下平衡准确性和效率. 这种方法增强了数据集成,用于现实世界的证据生成.
科学领域:
- 医疗信息学 医疗信息学
- 药学流行病学 药学流行病学
- 数据科学数据科学数据科学
背景情况:
- 电子健康记录 (EHR) 对药物流行病学研究至关重要.
- 由于缺乏独特的患者标识符,在各机构之间将非识别的EHR数据联系起来具有挑战性.
- 沙特现实世界证据网络 (SRWEN) 需要强大的数据链接技术.
研究的目的:
- 评估和比较确定性,概率和机器学习 (ML) 数据链接方法.
- 评估SRWEN和国家卫队卫生事务部EHR系统中未识别的多发性硬化症 (MS) 患者数据的链接性能.
- 确定最有效的链接策略,以在MS研究中产生真实世界的证据.
主要方法:
- 在实际数据链接之前,采用了基于模拟的验证框架.
- 确定性链接使用了预定义的规则.
- 可能性链接使用了基于相似度得分的匹配.
- 机器学习方法包括神经网络,物流回归和随机森林模型,采用基于相似性得分和分类方法.
- 使用混矩阵评估性能,重点关注灵敏度,正预测值,F1得分和计算效率.
主要成果:
- 确定性链接实现了高的模拟F1得分 (97.2%),但显示了可变的现实世界匹配率 (46.6%-86.6%),具有高计算效率 (<1秒/规则).
- 概率链接显示出强大的模拟性能 (F1得分为93.9%),现实世界的匹配率更高 (65.5%-95.4%) 和中等的处理时间 (0.1-5秒/规则).
- 机器学习模型获得了最高的F1分数 (高达99.8%),但计算密集,根据具体的ML方法,具有高度可变的真实世界匹配率.
结论:
- 概率链接为链接无标识数据提供了更高的能力,可以恢复确定性方法错过的匹配.
- 这种方法对于缺乏唯一标识符的现实场景来说是灵活和高效的,平衡回忆和精度.
- 可能性链接有助于更好地整合多样化的数据源,显著有利于多发性硬化症 (MS) 研究.
相关概念视频
00:49Ligand Binding and Linkage
5.6K
Allosteric proteins have more than one ligand binding site; the binding of a ligand to any of these sites influences the binding of ligands to the other sites. When a protein is allosteric, its binding sites are called coupled or linked. In the case of enzymes, the site that binds to the substrate is known as the active site and the other site is known as the regulatory site. When a ligand binds to the regulatory site, this leads to conformational changes in the protein that can influence...
5.6K
00:49Ligand Binding and Linkage
4.1K
4.1K
01:01Phosphodiester Linkages
111.3K
Overview
Phosphodiester bond forms when a phosphoric acid molecule (H3PO4) links with two hydroxyl groups (–OH) of two other molecules, forming two ester bonds. Two water molecules are released in this process. The phosphodiester bond is commonly found in nucleic acids (DNA and RNA) and plays a critical role in their structure and function.
Phosphodiester Bonds Link Nucleotides Together
DNA and RNA are polynucleotides or long chains of nucleotides that are linked together. A nucleotide is...
Phosphodiester bond forms when a phosphoric acid molecule (H3PO4) links with two hydroxyl groups (–OH) of two other molecules, forming two ester bonds. Two water molecules are released in this process. The phosphodiester bond is commonly found in nucleic acids (DNA and RNA) and plays a critical role in their structure and function.
Phosphodiester Bonds Link Nucleotides Together
DNA and RNA are polynucleotides or long chains of nucleotides that are linked together. A nucleotide is...
111.3K
01:11Purpose of Health Records I
1.8K
The vital purpose of health records is to provide a complete and accurate account of a patient's medical history, including communication, diagnostic and therapeutic orders, care planning, research, and quality review.
Here's a breakdown of how health records serve these purposes:
Here's a breakdown of how health records serve these purposes:
1.8K
01:19Purpose of Health Records II
1.4K
Health records serve various essential purposes in the healthcare system. Here are some key purposes:
1.4K
02:04Covalently Linked Protein Regulators
9.6K
Proteins can undergo many types of post-translational modifications, often in response to changes in their environment. These modifications play an important role in the function and stability of these proteins. Covalently linked molecules include functional groups, such as methyl, acetyl, and phosphate groups, and also small proteins, such as ubiquitin. There are around 200 different types of covalent regulators that have been identified.
These groups modify specific amino acids in a protein....
These groups modify specific amino acids in a protein....
9.6K