Background: Coronary artery calcium (CAC) can be identified on non-gated chest CTs, but this finding is not consistently incorporated into care. A deep learning algorithm enables opportunistic CAC screening of non-gated chest CTs. Our objective was to evaluate the impact of notifying clinicians and patients of incidental CAC on statin initiation. Methods: NOTIFY-1 was a randomized quality improvement project in the Stanford healthcare system. Patients without known atherosclerotic cardiovascular disease (ASCVD) or prior statin prescription were screened for CAC on a prior non-gated chest CT from 2014-2019 using a validated deep learning algorithm with radiologist confirmation. Patients with incidental CAC were randomized to notification of the primary care clinician and patient versus usual care. Notification included a patient-specific image of CAC and guideline recommendations regarding statin use. The primary outcome was statin prescription within 6 months. Results: Among 2,113 patients who met initial clinical inclusion criteria, CAC was identified by the algorithm in 424 patients. After additional exclusions following chart review, a radiologist confirmed CAC among 173 of 194 patients (89.2%) who were randomized to notification or usual care. At 6 months, the statin prescription rate was 51.2% (44/86) in the notification arm versus 6.9% (6/87) with usual care (p<0.001). There was also more coronary artery disease testing in the notification arm (15.1% [13/86] vs. 2.3% [2/87], p=0.008). Conclusions: Opportunistic CAC screening of prior non-gated chest CTs followed by clinician and patient notification led to a significant increase in statin prescriptions. Further research is needed to determine whether this approach can reduce ASCVD events.
Background Statins conclusively decrease mortality in atherosclerotic cardiovascular disease (ASCVD), the leading cause of death worldwide, and are strongly recommended by guidelines. However, real-world statin utilization and persistence are low, resulting in excess mortality. Identifying reasons for statin nonuse at scale across health systems is crucial to developing targeted interventions to improve statin use. Methods We developed and validated deep learning-based natural language processing (NLP) approaches (Clinical Bidirectional Encoder Representations from Transformers [BERT]) to classify statin nonuse and reasons for statin nonuse using unstructured electronic health records (EHRs) from a diverse healthcare system. Results We present data from a cohort of 56,530 ASCVD patients, among whom 21,508 (38%) lack guideline-directed statin prescriptions and statins listed as allergies in structured EHR portions. Of these 21,508 patients without prescriptions, only 3,929 (18%) have any discussion of statin use or nonuse in EHR documentation. The NLP classifiers identify statin nonuse with an area under the curve (AUC) of 0.94 (95% CI 0.93–0.96) and reasons for nonuse with a weighted-average AUC of 0.88 (95% CI 0.86–0.91) when evaluated against manual expert chart review in a held-out test set. Clinical BERT identifies key patient-level reasons (side-effects, patient preference) and clinician-level reasons (guideline-discordant practices) for statin nonuse, including differences by type of ASCVD and patient race/ethnicity. Conclusions Our deep learning NLP classifiers can identify crucial gaps in statin nonuse and reasons for nonuse in high-risk populations to support education, clinical decision support, and potential pathways for health systems to address ASCVD treatment gaps.
Background Coronary artery calcium (CAC) scans can help reclassify risk and guide patient‐clinician shared treatment decisions for cardiovascular disease prevention. Patients increasingly access online patient educational materials (OPEMs) to guide medical decision‐making. The American Medical Association (AMA) recommends that OPEMs should be written below a 6th‐grade reading level. This study estimated the readability of commonly accessed OPEMs on CAC scans. Methods and Results The terms “coronary artery calcium scan,” “heart scan,” and “CAC score” were queried using an online search engine to identify the top 50 commonly accessed websites based on order of search results on December 17, 2019. Grade‐level readability was calculated using generalized estimating equations, with observations nested within readability metrics from each website. Results were compared with AMA‐recommended readability parameters. Overall grade‐level readability among all search terms was 10.9 (95% CI, 9.3–12.5). Average grade‐level readability of OPEMs for the search terms “coronary artery calcium scan,” “heart scan,” and “CAC score,” was 10.7 (95% CI, 9.0–12.5), 10.5 (95% CI, 8.9–12.1), and 11.9 (95% CI, 10.3–13.5), respectively. Professional society and news/media/blog websites had the highest average reading grade level of 12.6, while health system websites had the lowest average reading grade level of 10.0. Less than half of the unique websites (45.3%) included explanatory images or videos. Conclusions Current OPEMs on CAC scans are written at a higher reading level than recommended for the general public. This may lead to patient misunderstanding, which could exacerbate disparities in cardiovascular health among groups with lower health literacy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.