Witting Celeste, Azizi Zahra, Gomez Sofia Elena, Zammit Alban, Sarraju Ashish, Ngo Summer, Hernandez-Boussard Tina, Rodriguez Fatima
Stanford University Division of Cardiovascular Medicine and Cardiovascular Institute, Department of Medicine, Stanford University, Center for Academic Medicine, Mail Code 5687, 453 Quarry Road, Palo Alto, Stanford, CA, USA.
Center for Digital Health, Stanford University, Stanford, CA, USA.
Am J Prev Cardiol. 2023 Apr 11;14:100496. doi: 10.1016/j.ajpc.2023.100496. eCollection 2023 Jun.
Statins are the cornerstone of treatment of patients with atherosclerotic cardiovascular disease (ASCVD). Despite this, multiple studies have shown that women with ASCVD are less likely to be prescribed statins than men. The objective of this study was to use Natural Language Processing (NLP) to elucidate factors contributing to this disparity.
Our cohort included adult patients with two or more encounters between 2014 and 2021 with an ASCVD diagnosis within a multisite electronic health record (EHR) in Northern California. After reviewing structured EHR prescription data, we used a benchmark deep learning NLP approach, Clinical Bidirectional Encoder Representations from Transformers (BERT), to identify and interpret discussions of statin prescriptions documented in clinical notes. Clinical BERT was evaluated against expert clinician review in 20% test sets.
There were 88,913 patients with ASCVD (mean age 67.8±13.1 years) and 35,901 (40.4%) were women. Women with ASCVD were less likely to be prescribed statins compared with men (56.6% vs 67.6%, <0.001), and, when prescribed, less likely to be prescribed guideline-directed high-intensity dosing (41.4% vs 49.8%, <0.001). These disparities were more pronounced among younger patients, patients with private insurance, and those for whom English is their preferred language. Among those not prescribed statins, women were less likely than men to have statins mentioned in their clinical notes (16.9% vs 19.1%, <0.001). Women were less likely than men to have statin use reported in clinical notes despite absence of recorded prescription (32.8% vs 42.6%, <0.001). Women were slightly more likely than men to have statin intolerance documented in structured data or clinical notes (6.0% vs 5.3%, =0.003).
Women with ASCVD were less likely to be prescribed guideline-directed statins compared with men. NLP identified additional sex-based statin disparities and reasons for statin non-prescription in clinical notes of patients with ASCVD.
他汀类药物是动脉粥样硬化性心血管疾病(ASCVD)患者治疗的基石。尽管如此,多项研究表明,患有ASCVD的女性比男性更不容易被处方他汀类药物。本研究的目的是使用自然语言处理(NLP)来阐明导致这种差异的因素。
我们的队列包括2014年至2021年间在北加利福尼亚州多地点电子健康记录(EHR)中被诊断为ASCVD且有两次或更多次就诊记录的成年患者。在审查结构化的EHR处方数据后,我们使用了一种基准深度学习NLP方法,即来自Transformer的临床双向编码器表示(BERT),来识别和解释临床记录中记录的他汀类药物处方的讨论。在20%的测试集中,将临床BERT与专家临床医生的审查结果进行了评估。
共有88,913例ASCVD患者(平均年龄67.8±13.1岁),其中35,901例(40.4%)为女性。与男性相比,患有ASCVD的女性被处方他汀类药物的可能性较小(56.6%对67.6%,P<0.001),并且在被处方时,被处方指南指导的高强度剂量的可能性也较小(41.4%对49.8%,P<0.001)。这些差异在年轻患者、有私人保险的患者以及以英语为首选语言的患者中更为明显。在未被处方他汀类药物的患者中,女性在临床记录中被提及使用他汀类药物的可能性低于男性(16.9%对19.1%,P<0.001)。尽管没有记录处方,但女性在临床记录中被报告使用他汀类药物的可能性低于男性(32.8%对42.6%,P<0.001)。在结构化数据或临床记录中,女性被记录有他汀类药物不耐受的可能性略高于男性(6.0%对5.3%,P=0.003)。
与男性相比,患有ASCVD的女性被处方指南指导的他汀类药物的可能性较小。NLP在ASCVD患者的临床记录中发现了基于性别的他汀类药物差异以及他汀类药物未处方的原因。