Leveraging structured and unstructured electronic health record data to detect reasons for suboptimal statin therapy use in patients with atherosclerotic cardiovascular disease.
Leveraging structured and unstructured electronic health record data to detect reasons for suboptimal statin therapy use in patients with atherosclerotic cardiovascular disease.
复制标题
DOI：
10.1016/j.ajpc.2021.100300
复制
发表时间：
2022-03
影响因子：
4.1
通讯作者：
Virani SS
中科院分区：
文献类型：
--
作者：
Gobbel GT;Matheny ME;Reeves RR;Akeroyd JM;Turchin A;Ballantyne CM;Petersen LA;Virani SS
确定非结构化医学文本的自然语言处理（NLP）是否可以提高因他汀类药物相关副作用（SASEs）等原因未使用高强度他汀类药物治疗（HIST）的ASCVD患者的识别。审稿人在从VA医疗保健系统中随机选择的1152名ASCVD治疗但未接受HIST的患者的记录中注释了不开HIST的原因。开发人员使用审稿人注释来训练Canary NLP工具来检测和提取包含一个或多个这些原因的注释。使用负预测值（NPV）、敏感性、特异性和曲线下面积（AUC）来评估在使用结构化数据、nlp提取的非结构化数据或两种数据源组合时检测包含原因的文档的准确性。47%的病历中至少有一个不开HIST处方的记录原因。最常见的原因是SASEs（41%）和一般不耐受（20%）。当识别包含任何未使用HIST的记录原因时，与单独使用结构化数据相比，添加nlp提取的非结构化数据显着（p<0.05）提高了灵敏度（0.69（95%置信区间[CI] 0.60-0.76）至0.89 (95% CI 0.81-0.93)）， NPV （0.90 （95% CI 0.87 - 0.93）至0.96 (95% CI 0.93 - 0.98)）和AUC（0.84（95%置信区间[CI] 0.81-0.88）至0.91 (95% CI 0.90 - 0.93)）。从非结构化文本中提取数据的NLP可以提高对患者不使用HIST的原因的识别，而不仅仅是结构化数据。通过非结构化自由文本的NLP提供的额外信息应该有助于定制和实施系统级干预措施，以提高ASCVD患者HIST的使用。
To determine whether natural language processing (NLP) of unstructured medical text can improve identification of ASCVD patients not using high-intensity statin therapy (HIST) due to statin-associated side effects (SASEs) and other reasons. Reviewers annotated reasons for not prescribing HIST in notes of 1152 randomly selected patients from across the VA healthcare system treated for ASCVD but not receiving HIST. Developers used reviewer annotations to train the Canary NLP tool to detect and extract notes containing one or more of these reasons. Negative predictive value (NPV), sensitivity, specificity and Area Under the Curve (AUC) were used to assess accuracy at detecting documents containing reasons when using structured data, NLP-extracted unstructured data, or both data sources combined. At least one documented reason for not prescribing HIST occurred in 47% of notes. The most frequent reasons were SASEs (41%) and general intolerance (20%). When identifying notes containing any documented reason for not using HIST, adding NLP-extracted, unstructured data significantly (p<0.05) increased sensitivity (0.69 (95% confidence interval [CI] 0.60–0.76) to 0.89 (95% CI 0.81–0.93)), NPV (0.90 (95% CI 0.87 to 0.93) to 0.96 (95% CI 0.93–0.98)), and AUC (0.84 (95% confidence interval [CI] 0.81–0.88) to 0.91 (95% CI 0.90–0.93)) compared to structured data alone. NLP extraction of data from unstructured text can improve identification of reasons for patients not being on HIST over structured data alone. The additional information provided through NLP of unstructured free text should help in tailoring and implementing system-level interventions to improve HIST use in patients with ASCVD.
登录
查看更多内容
影响因子：
4.4
作者：
Virani, Salim S.;Akeroyd, Julia M.;Petersen, Laura A.
通讯作者：
Petersen, Laura A.
影响因子：
13.8
作者：
Mahtta, Dhruv;Ramsey, David J.;Virani, Salim S.
通讯作者：
Virani, Salim S.
影响因子：
24
作者：
Rodriguez, Fatima;Maron, David J.;Heidenreich, Paul A.
通讯作者：
Heidenreich, Paul A.
影响因子：
3.4
作者：
Mahtta, Dhruv;Ahmed, Sarah T.;Virani, Salim S.
通讯作者：
Virani, Salim S.
影响因子：
158.5
作者：
Cannon, CP;Braunwald, E;Skene, AM
通讯作者：
Skene, AM