Natural language processing (NLP) is a set of automated methods to organise and evaluate the information contained in unstructured clinical notes, which are a rich source of real-world data from ...clinical care that may be used to improve outcomes and understanding of disease in cardiology. The purpose of this systematic review is to provide an understanding of NLP, review how it has been used to date within cardiology and illustrate the opportunities that this approach provides for both research and clinical care. We systematically searched six scholarly databases (ACM Digital Library, Arxiv, Embase, IEEE Explore, PubMed and Scopus) for studies published in 2015-2020 describing the development or application of NLP methods for clinical text focused on cardiac disease. Studies not published in English, lacking a description of NLP methods, non-cardiac focused and duplicates were excluded. Two independent reviewers extracted general study information, clinical details and NLP details and appraised quality using a checklist of quality indicators for NLP studies. We identified 37 studies developing and applying NLP in heart failure, imaging, coronary artery disease, electrophysiology, general cardiology and valvular heart disease. Most studies used NLP to identify patients with a specific diagnosis and extract disease severity using rule-based NLP methods. Some used NLP algorithms to predict clinical outcomes. A major limitation is the inability to aggregate findings across studies due to vastly different NLP methods, evaluation and reporting. This review reveals numerous opportunities for future NLP work in cardiology with more diverse patient samples, cardiac diseases, datasets, methods and applications.
Abstract only
Introduction:
Atrial fibrillation (AF) symptom relief is a primary indication for catheter ablation, but the impact of ablation on AF symptoms is not well characterized. The objective ...of this study was to describe AF symptom documentation in electronic health records (EHRs) pre- and post-ablation and identify correlates of post-ablation symptoms.
Methods:
We evaluated EHRs of AF patients (n=1293) in a large, urban health system from 2010-2020 who underwent ablation and had at least one encounter note within 30 days of the ablation. We extracted structured data about patient demographics, medications, diagnoses, and encounters, and symptom data from unstructured clinical notes using natural language processing. We used Cochran’s Q tests with post-hoc McNemar’s tests to determine whether the prevalence of symptoms differed significantly pre- and 3, 6, 9, and 12 months post-ablation. We used bivariate logistic regression models to estimate the unadjusted odds of symptom prevalence by personal or clinical characteristics at 6 and 12 months post-ablation.
Results:
Compared to pre-ablation, the prevalence of any AF symptom decreased but anxiety and weakness increased post-ablation (Table 1). The unadjusted odds of any symptoms 12 months post-ablation were associated with Black/African-American (odds ratio OR=0.35; 95% confidence interval CI=0.14-0.92) or another race (OR=0.39, 95% CI=0.16-0.95) versus Asian race, Hispanic/Latino ethnicity (OR=2.40, 95% CI=1.28-4.39) versus non-Hispanic/Latino, antiarrhythmic medication (OR=0.62, 95% CI=0.46-0.80) versus no medication, smoking history (OR=0.70, 95% CI=0.53-0.94) versus no history, and heart failure (OR=0.73, 95% CI=0.55-0.97) versus no heart failure.
Conclusion:
Symptom patterns post-ablation are heterogeneous. Findings warrant confirmation with larger, more representative datasets, which may be informative for patients whose primary goal for undergoing an ablation is symptom relief.
Non-valvular atrial fibrillation (NVAF) is the most common cause of cardioembolic stroke. The left atrial appendage (LAA) is the major source of cardiac emboli in patients with NVAF. Anticoagulation ...(AC) is the standard of care for stroke prevention in atrial fibrillation (AF), but many patients are intolerant of AC. Surgical exclusion of the LAA may result in incomplete closure and is associated with an increased risk of embolism. We report a case of a woman in her 50s with a history of persistent AF, mitral valve prolapse s/p repair with surgical LAA exclusion, and multifocal haemorrhagic stroke presented for elective LAA closure who underwent a Watchman placement successfully. This case demonstrates that a percutaneous approach for occlusion of the LAA when surgical exclusion was incomplete may be feasible with appropriate planning. Clinical outcome data for this patient group are needed.
Coronavirus disease 2019 (COVID-19) is a growing pandemic that confers augmented risk for right ventricular (RV) dysfunction and dilation; the prognostic utility of adverse RV remodeling in COVID-19 ...patients is uncertain.
The purpose of this study was to test whether adverse RV remodeling (dysfunction/dilation) predicts COVID-19 prognosis independent of clinical and biomarker risk stratification.
Consecutive COVID-19 inpatients undergoing clinical transthoracic echocardiography at 3 New York City hospitals were studied; images were analyzed by a central core laboratory blinded to clinical and biomarker data.
In total, 510 patients (age 64 ± 14 years, 66% men) were studied; RV dilation and dysfunction were present in 35% and 15%, respectively. RV dysfunction increased stepwise in relation to RV chamber size (p = 0.007). During inpatient follow-up (median 20 days), 77% of patients had a study-related endpoint (death 32%, discharge 45%). RV dysfunction (hazard ratio HR: 2.57; 95% confidence interval CI: 1.49 to 4.43; p = 0.001) and dilation (HR: 1.43; 95% CI: 1.05 to 1.96; p = 0.02) each independently conferred mortality risk. Patients without adverse RV remodeling were more likely to survive to hospital discharge (HR: 1.39; 95% CI: 1.01 to 1.90; p = 0.041). RV indices provided additional risk stratification beyond biomarker strata; risk for death was greatest among patients with adverse RV remodeling and positive biomarkers and was lesser among patients with isolated biomarker elevations (p ≤ 0.001). In multivariate analysis, adverse RV remodeling conferred a >2-fold increase in mortality risk, which remained significant (p < 0.01) when controlling for age and biomarker elevations; the predictive value of adverse RV remodeling was similar irrespective of whether analyses were performed using troponin, D-dimer, or ferritin.
Adverse RV remodeling predicts mortality in COVID-19 independent of standard clinical and biomarker-based assessment.