Identification of recurrent atrial fibrillation using natural language processing applied to electronic health records.
Identification of recurrent atrial fibrillation using natural language processing applied to electronic health records.
复制标题
使用应用于电子健康记录的自然语言处理来识别复发性房颤。
DOI：
10.1093/ehjqcco/qcad021
复制
发表时间：
2024
期刊：
影响因子：
--
通讯作者：
An,Jaejin
中科院分区：
文献类型：
--
作者：
Zheng,Chengyi;Lee,Ming-Sum;Bansal,Nisha;Go,AlanS;Chen,Cheng;Harrison,TeresaN;Fan,Dongjie;Allen,Amanda;Garcia,Elisha;Lidgard,Ben;Singer,Daniel;An,Jaejin
本研究旨在开发和应用自然语言处理（NLP）算法，利用电子健康记录（EHRs）识别心律控制治疗开始后复发性心房颤动（AF）发作。方法和结果我们纳入了在两个美国综合医疗保健系统内开始心律控制治疗（消融、心律转复或抗心律失常药物）的新发房颤成人。基于代码的算法识别潜在的房颤复发使用诊断和程序代码。开发并验证了一种自动NLP算法，可从心电图、心脏监护报告和临床记录中捕获房颤复发。与医生判定的参考标准病例相比，NLP算法在两个地点的f分、敏感性和特异性均在0.90以上。我们将NLP和基于代码的算法应用于开始节律控制治疗后12个月内发生AF的患者（n= 22970）。应用NLP算法，1、2部位AF复发患者的比例分别为消融60.7%、69.9%，复律64.5%、73.7%，抗心律失常药物49.6%、55.5%。相比之下，在第1和第2部位发生AF复发的患者中，消融组分别为20.2%和23.7%，心律转复组分别为25.6%和28.4%，抗心律失常药物组分别为20.0%和27.5%。与单独基于代码的方法相比，本研究的高性能自动NLP方法识别出更多的复发性房颤患者。NLP算法可以有效评估房颤治疗在大量人群中的治疗效果，并有助于制定量身定制的干预措施。
AimsThis study aimed to develop and apply natural language processing (NLP) algorithms to identify recurrent atrial fibrillation (AF) episodes following rhythm control therapy initiation using electronic health records (EHRs).Methods and resultsWe included adults with new-onset AF who initiated rhythm control therapies (ablation, cardioversion, or antiarrhythmic medication) within two US integrated healthcare delivery systems. A code-based algorithm identified potential AF recurrence using diagnosis and procedure codes. An automated NLP algorithm was developed and validated to capture AF recurrence from electrocardiograms, cardiac monitor reports, and clinical notes. Compared with the reference standard cases confirmed by physicians’ adjudication, theF-scores, sensitivity, and specificity were all above 0.90 for the NLP algorithms at both sites. We applied the NLP and code-based algorithms to patients with incident AF (n= 22 970) during the 12 months after initiating rhythm control therapy. Applying the NLP algorithms, the percentages of patients with AF recurrence for sites 1 and 2 were 60.7% and 69.9% (ablation), 64.5% and 73.7% (cardioversion), and 49.6% and 55.5% (antiarrhythmic medication), respectively. In comparison, the percentages of patients with code-identified AF recurrence for sites 1 and 2 were 20.2% and 23.7% for ablation, 25.6% and 28.4% for cardioversion, and 20.0% and 27.5% for antiarrhythmic medication, respectively.ConclusionWhen compared with a code-based approach alone, this study's high-performing automated NLP method identified significantly more patients with recurrent AF. The NLP algorithms could enable efficient evaluation of treatment effectiveness of AF therapies in large populations and help develop tailored interventions.