Machine Learning Assessment of Left Ventricular Diastolic Function Based on Electrocardiographic Features

BACKGROUND

Left ventricular (LV) diastolic dysfunction is recognized as playing a major role in the pathophysiology of heart failure; however, clinical tools for identifying diastolic dysfunction before echocardiography remain imprecise.

OBJECTIVES

This study sought to develop machine-learning models that quantitatively estimate myocardial relaxation using clinical and electrocardiography (ECG) variables as a first step in the detection of LV diastolic dysfunction.

METHODS

A multicenter prospective study was conducted at 4 institutions in North America enrolling a total of 1,202 subjects. Patients from 3 institutions (n = 814) formed an internal cohort and were randomly divided into training and internal test sets (80:20). Machine-learning models were developed using signal-processed ECG, traditional ECG, and clinical features and were tested using the test set. Data from the fourth institution was reserved as an external test set (n = 388) to evaluate the model generalizability.

RESULTS

Despite diversity in subjects, the machine-learning model predicted the quantitative values of the LV relaxation velocities (e') measured by echocardiography in both internal and external test sets (mean absolute error: 1.46 and 1.93 cm/s; adjusted R² = 0.57 and 0.46, respectively). Analysis of the area under the receiver operating characteristic curve (AUC) revealed that the estimated e' discriminated the guideline-recommended thresholds for abnormal myocardial relaxation and diastolic and systolic dysfunction (LV ejection fraction) the internal (area under the curve [AUC]: 0.83, 0.76, and 0.75) and external test sets (0.84, 0.80, and 0.81), respectively. Moreover, the estimated e' allowed prediction of LV diastolic dysfunction based on multiple age- and sex-adjusted reference limits (AUC: 0.88 and 0.94 in the internal and external sets, respectively).

CONCLUSIONS

A quantitative prediction of myocardial relaxation can be performed using easily obtained clinical and ECG features. This cost-effective strategy may be a valuable first clinical step for assessing the presence of LV dysfunction and may potentially aid in the early diagnosis and management of heart failure patients.

In-hospital outcomes of percutaneous mitral valve repair in patients with chronic obstructive pulmonary disease: insights from the national inpatient sample database

OBJECTIVES

We aimed to assess the in-hospital outcomes in patients with mitral regurgitation treated with percutaneous mitral valve repair (PMVR) among patients with chronic obstructive pulmonary disease (COPD).

BACKGROUND

There is lack of data on the outcomes of PMVR for mitral regurgitation in patients with COPD.

METHODS

We analyzed the national inpatient sample (NIS) database from January 2012 to December 2016.

RESULTS

A total of 9125 patients underwent PMVR in the period between January 2012 and December 2016, of whom 2,495 (27.3%) patients had concomitant COPD. Comparing COPD patients to non-COPD patients, COPD patients had higher proportion of females (48.3% vs. 46.6%, p = .16), were younger (75.8 ± 10.0 years vs. 76.4 ± 12.2 years; p = .04), had higher prevalence of peripheral vascular disease (17.4% vs. 13.5%; p < .01) and renal failure (39.3% vs. 37%; p < .01). After propensity matching, there was no significant difference in mortality among the COPD group versus non-COPD patients (2.6% vs. 2.9%; p = .6). Patients with COPD had higher proportion of in-hospital morbidities including St-segment elevation myocardial infarction (1.8% vs. 1.0%; p = .02), cardiogenic shock (1.4% vs. 0.4%; p < .01), vascular complications (2% vs. 0.8; p < .01), pneumothorax (1% vs. 0.4%; p < .01), and septic shock (1.2% vs. 0.4%; p < .01). Moreover, surrogates of severe disability (mechanical intubation and non-home discharges), cost of hospitalization, and length of stay were higher in the COPD group.

CONCLUSIONS

There was no difference in mortality between the COPD and non-COPD patients after PMVR. Moreover, we observed higher rates of in-hospital morbidities, surrogates of severe disability, and higher resources utilization by the COPD group.

The Role of Artificial Intelligence in Cardiovascular Imaging: State of the Art Review

In this current digital landscape, artificial intelligence (AI) has established itself as a powerful tool in the commercial industry and is an evolving technology in healthcare. Cutting-edge imaging modalities outputting multi-dimensional data are becoming increasingly complex. In this era of data explosion, the field of cardiovascular imaging is undergoing a paradigm shift toward machine learning (ML) driven platforms. These diverse algorithms can seamlessly analyze information and automate a range of tasks. In this review article, we explore the role of ML in the field of cardiovascular imaging.

Prediction of coronary artery calcium scoring from surface electrocardiogram in atherosclerotic cardiovascular disease: a pilot study

Aims

Coronary artery calcium (CAC) scoring is an established tool for cardiovascular risk stratification. However, the lack of widespread availability and concerns about radiation exposure have limited the universal clinical utilization of CAC. In this study, we sought to explore whether machine learning (ML) approaches can aid cardiovascular risk stratification by predicting guideline recommended CAC score categories from clinical features and surface electrocardiograms.

Methods and results

In this substudy of a prospective, multicentre trial, a total of 534 subjects referred for CAC scores and electrocardiographic data were split into 80% training and 20% testing sets. Two binary outcome ML logistic regression models were developed for prediction of CAC scores equal to 0 and ≥400. Both CAC = 0 and CAC ≥400 models yielded values for the area under the curve, sensitivity, specificity, and accuracy of 84%, 92%, 70%, and 75%, and 87%, 91%, 75%, and 81%, respectively. We further tested the CAC ≥400 model to risk stratify a cohort of 87 subjects referred for invasive coronary angiography. Using an intermediate or higher pretest probability (≥15%) to predict CAC ≥400, the model predicted the presence of significant coronary artery stenosis (P = 0.025), the need for revascularization (P &lt; 0.001), notably bypass surgery (P = 0.021), and major adverse cardiovascular events (P = 0.023) during a median follow-up period of 2 years.

Conclusion

ML techniques can extract information from electrocardiographic data and clinical variables to predict CAC score categories and similarly risk-stratify patients with suspected coronary artery disease.

The dawn of aspirin free strategy after short term dual antiplatelet for percutaneous coronary intervention: meta-analysis of randomized controlled trials

There is still a debate about the safety and efficacy of an aspirin free strategy after percutaneous coronary intervention (PCI). Hence, we performed a meta-analysis comparing aspirin free strategy to dual antiplatlets therapy (DAPT). Randomized trials (RCTs) comparing aspirin free strategy to DAPT in patients who received PCI were included. The primary outcome of interest was bleeding, defined per the Bleeding Academic Research Consortium (BARC). Secondary outcomes included major adverse cardiovascular and cerebrovascular events (MACE); defined as all-cause mortality, myocardial infarction or stroke, the individual component of MACE and stent thrombosis. A total of 4 RCTs with 29,089 patients were included. There was significant reduction in BARC 2,3 or 5 bleeding events in patients who were treated with aspirin free strategy versus DAPT (HR 0.61, 95% CI 0.39-, p = 0.03, I² = 89%). Moreover, although there was a trend of reduced major bleeding (BARC 3 or 5) outcomes in the aspirin free strategy group compared to the DAPT group, this did not achieve statistical significance (HR 0.63, 95% CI 0.37-1.06, p = 0.08, I² = 795). Additionally, there was no difference between the aspirin free strategy and DAPT in term of MACE (HR 0.92, 95% CI 0.82-1.03, p = 0.13, I² = 0%), all-cause mortality (HR 0.89, 95% CI 0.77-1.04, p = 0.15, I² = 0%), MI (HR 0.89, 95% CI 0.74-1.08, p = 0.24, I² = 0%), stroke (HR 1.13, 95% CI 0.65-1.99, p = 0.66, I² = 60%) or stent thrombosis (HR 0.1.01, 95% CI 0.83-1.22, p = 0.93, I² = 0%). Aspirin free strategy is as effective as DAPT in reducing MACE with better safety profile in term of bleeding.

Use of the Burden of Diabetes Mellitus Score for Cardiovascular Disease Risk Assessment

Uncontrolled type II diabetes mellitus (DM) using single point hemoglobin A1c levels has been associated with poor cardiovascular outcomes. However, methods to quantify the effect of uncontrolled DM over time have been inconsistent. To quantify hyperglycemia over time and assess its cardiovascular effects we developed and tested a DM burden score which accounts for time in years prior to DM diagnosis, diagnostic HbA1c, and aggregate HbA1c levels thereafter. A retrospective cohort study was performed with patients (n = 188) from a single academic center with type II DM and no prior cardiac disease history. Patient scores were calculated from diagnosis until the year 2015 and were grouped into low (<5.3%; n = 55), moderate (5.3% to 5.5%; n = 80), and high (>5.5%; n = 53) DM burden score cohorts. At 48 months, the cohort with high DM burden scores correlated with significantly worse major adverse cardiovascular events (hazard ratio [HR] 3.07, p = 0.012), myocardial infarction (HR 12.78, p = 0.015), coronary revascularization (HR 4.53, p = 0.019), cardiovascular hospitalizations (HR 4.20, p = 0.005), and all-cause hospitalizations (HR 2.57, p = 0.01). Cardiovascular and all-cause mortality showed significant difference between groups in log-rank testing. Also, a multivariate regression model showed DM burden score (p = 0.045) to be an independent predictor of major adverse cardiovascular events (HR 9.38, p = 0.045). In conclusion, this study provides evidence that DM control over time impacts cardiovascular outcomes.

Meta-Analysis Comparing Complete Versus Infarct-Related Artery Revascularization in Patients With ST-Elevation Myocardial Infarction and Multivessel Coronary Disease

A strategy of complete revascularization (CR) versus infarct-related artery revascularization (IRA) in patients with ST-elevation myocardial infarction (STEMI) continues to be a subject of debate. We performed an updated meta-analysis to compare the 2 strategies. Outcomes of interest included major adverse cardiovascular events (MACE), cardiovascular mortality, all-cause mortality, stroke, repeat revascularization, myocardial infarction, and contrast-induced nephropathy. Ten randomized trials including 7,423 patients (CR = 3,574 and IRA = 3,849), with a follow-up of 2.0 ± 0.8 years were included. There was a significant reduction in MACE with CR versus IRA (10.7% vs 18.6%, relative risk [RR] 0.64, 95% confidence interval [CI] 0.51 to 0.81, p = 0.002, I² = 66%), with higher risk reduction with immediate versus stages revascularization (RR 0.40, 95% CI 0.32 to 0.5 vs RR 0.69, 95% CI 0.54 to 0.89, P-interaction = 0.002). Complete revascularization was associated with lower rates of repeat revascularization (4.0% vs 11.7%, RR 0.44, 95% CI 0.28 to 0.70, p <0.0001, I² = 81%), and a nonsignificant trend toward lower cardiovascular mortality (2.8% vs 3.7%, RR 0.78, 95% CI 0.60 to 1.03, p = 0.08, I² = 0%). However, there was no difference between the 2 strategies in all-cause mortality (4.6% vs 4.8%, RR 0.90, 95% CI 0.73 to 1.12, p = 0.36, I² = 0%), myocardial infarction (5.2% vs 6.5%, RR 0.73, 95% CI, 0.58 to 1.08, p = 0.08, I² = 30%), stroke (1.5% vs 1.2%, RR 1.14, 95% CI 0.56 to 2.29, p = 0.33, I² = 14%), or contrast-induced nephropathy (1.6% vs 1.2%, RR 1.35, 95% CI 0.85 to 2.15, p = 0.78, I² = 0%). In conclusion, CR in patients with STEMI is associated with significant reduction in MACE compared with IRA. This reduction is derived mainly by the low rates of repeat revascularization in the CR group.

Early-onset Lyme carditis with concurrent disseminated erythema migrans

BACKGROUND

Lyme disease is an infection that is estimated to affect over 300,000 people in the United States annually. Typically, it presents with erythema migrans (EM), an annular rash at the site of tick attachment, within 3 to 30 days of inoculation. Untreated patients may progress to early disseminated disease. A further complication, Lyme carditis is rare but may occur several weeks later. It commonly manifests as a variable atrioventricular (AV) conduction block, with a high-grade AV block occurring in only 1% of untreated patients. This case demonstrates an unusually early presentation of Lyme carditis with complete heart block.

CASE PRESENTATION

A 21-year-old male was transferred from an outside emergency department (ED) for possible pacemaker placement due to symptomatic third-degree AV block. Four days earlier the patient presented to the outside ED with fever, chills, and unrecognized EM on his right neck. He was discharged with antipyretics, but no antibiotic therapy. On the day of transfer, he returned with persistent fevers, EM now on his trunk and upper extremities, lightheadedness, and substernal chest pressure. An electrocardiogram revealed the third-degree AV block leading to transfer. Upon arrival, the patient was promptly diagnosed with Lyme carditis. Pacemaker implantation was deferred, and intravenous (IV) ceftriaxone was initiated. Within 48 hours his third-degree AV block improved to a first-degree block. By this time, his EM had also resolved. He was discharged with oral doxycycline and a 30-day event monitor, which ultimately showed persistent first-degree AV block.

CONCLUSIONS

This case reinforces a unique presentation of Lyme carditis. Disseminated EM and Lyme carditis may present concurrently within 2 weeks of tick attachment. Early recognition and treatment is important for preventing progression to disseminated infection. Lyme-associated AV block will reverse within 48 to 72 hours of initiating IV antibiotic therapy and will not require pacemaker implantation. Lyme carditis should be considered in patients without heart disease who present with any degree of AV block.