Provider Survey on Automated Clinical Decision Support System for Cardiovascular Risk Assessment.

Despite progress made in establishing primary and secondary preventive strategies for cardiovascular diseases, there are significant gaps between guideline recommended strategies and implementation of recommendations in practice. A clinical decision support (CDS) system entitled CV Risk Profile was developed at Mayo Clinic Rochester as a targeted solution for this gap in preventive cardiovascular care. The system remained in use for 10 years until it became non-functional in 2018 during transition to a new electronic health record (EHR). This study investigated provider opinions regarding the cardiovascular disease CDS system while it was still in operation, to determine if there exists a provider reported need for a similar system to be developed for use within the new EHR.

Automated extraction of sudden cardiac death risk factors in hypertrophic cardiomyopathy patients by natural language processing.

BACKGROUND: The management of hypertrophic cardiomyopathy (HCM) patients requires the knowledge of risk factors associated with sudden cardiac death (SCD). SCD risk factors such as syncope and family history of SCD (FH-SCD) as well as family history of HCM (FH-HCM) are documented in electronic health records (EHRs) as clinical narratives. Automated extraction of risk factors from clinical narratives by natural language processing (NLP) may expedite management workflow of HCM patients. The aim of this study was to develop and deploy NLP algorithms for automated extraction of syncope, FH-SCD, and FH-HCM from clinical narratives. METHODS AND RESULTS: We randomly selected 200 patients from the Mayo HCM registry for development (n = 100) and testing (n = 100) of NLP algorithms for extraction of syncope, FH-SCD as well as FH-HCM from clinical narratives of EHRs. The clinical reference standard was manually abstracted by 2 independent annotators. Performance of NLP algorithms was compared to aggregation and summarization of data entries in the HCM registry for syncope, FH-SCD, and FH-HCM. We also compared the NLP algorithms with billing codes for syncope as well as responses to patient survey questions for FH-SCD and FH-HCM. These analyses demonstrated NLP had superior sensitivity (0.96 vs 0.39, p < 0.001) and comparable specificity (0.90 vs 0.92, p = 0.74) and PPV (0.90 vs 0.83, p = 0.37) compared to billing codes for syncope. For FH-SCD, NLP outperformed survey responses for all parameters (sensitivity: 0.91 vs 0.59, p = 0.002; specificity: 0.98 vs 0.50, p < 0.001; PPV: 0.97 vs 0.38, p < 0.001). NLP also achieved superior sensitivity (0.95 vs 0.24, p < 0.001) with comparable specificity (0.95 vs 1.0, p-value not calculable) and positive predictive value (PPV) (0.92 vs 1.0, p = 0.09) compared to survey responses for FH-HCM. CONCLUSIONS: Automated extraction of syncope, FH-SCD and FH-HCM using NLP is feasible and has promise to increase efficiency of workflow for providers managing HCM patients.

Provider Survey on Automated Clinical Decision Support for Cardiovascular Risk Assessment.

OBJECTIVE: To investigate provider opinions regarding a clinical decision support (CDS) system for cardiovascular risk assessment and for the creation of a replacement system. METHODS: From March to April 2018, an invitation letter with a link to a self-administered web-based survey was sent via e-mail to 279 providers with primary appointment in the Department of Cardiovascular Medicine, Mayo Clinic, Rochester. The e-mail was sent to providers on March 8, 2018 and the survey closed on April 16, 2018. RESULTS: One hundred providers responded to the survey yielding an overall response rate of 35.8%. Of these, 52 (52%) indicated they had used the cardiovascular (CV) risk profile CDS system and were classified as users and prompted to continue the survey. Among users, 42 (80.8%) indicated use of the CDS was either important (25; 48.1%) or very important (17; 32.7%) in their clinical practice; 45 (86.5%) responded that the system was very easy (17; 32.7%) or easy (28; 53.8%) to use. In addition, 48 (96.0%) users indicated that the CV risk profile supported their thought process at the point-of-care; 47 (97.9%) users indicated similar functionalities should be implemented into the new electronic health record system and 41 (85.4%) users reported new functionalities should also be incorporated. CONCLUSIONS: For most users, the CDS system was easy to use and supported clinical thought process at the point-of-care. Users also felt their practice was supported and should continue to be supported by CDS systems providing individualized patient information at the point-of-care.