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

Abstract

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.

Keywords: Electronic health records; Hypertrophic cardiomyopathy; Natural language processing; Sudden cardiac death.

Figure 1.

Study Design Study subjects were identified from 1,273 patients who participated in a dedicated HCM registry. Patients from the registry who did not have clinical narratives in electronic format were excluded (n = 277). From this cohort (n = 996) 200 subjects were randomly selected and allocated to training and test sets of 100 subjects each. HCM = hypertrophic cardiomyopathy.

Figure 2.

Extraction of Risk Factors in HCM by Automated Approaches Diverse automated technologies for risk factor extractions were used for each data type. FH-HCM = family history of hypertrophic cardiomyopathy; FH-SCD = family history sudden of cardiac death; HCM = hypertrophic cardiomyopathy; NLP = natural language processing.

Figure 3.

Information Extraction by Med Tagger - IE Med Tagger - IE processes clinical narratives containing unique identification numbers for each patient as input and generates risk factor status as output. The status of each risk factor is displayed as “Yes” (present) or “No” (absent). Sentences used for classification are displayed as evidence. Legend: IE = Information extraction.