Explainable machine learning using echocardiography to improve risk prediction in patients with chronic coronary syndrome.

Aims: The European Society of Cardiology guidelines recommend risk stratification with limited clinical parameters such as left ventricular (LV) function in patients with chronic coronary syndrome (CCS). Machine learning (ML) methods enable an analysis of complex datasets including transthoracic echocardiography (TTE) studies. We aimed to evaluate the accuracy of ML using clinical and TTE data to predict all-cause 5-year mortality in patients with CCS and to compare its performance with traditional risk stratification scores. Methods and results: Data of consecutive patients with CCS were retrospectively collected if they attended the outpatient clinic of Amsterdam UMC location AMC between 2015 and 2017 and had a TTE assessment of the LV function. An eXtreme Gradient Boosting (XGBoost) model was trained to predict all-cause 5-year mortality. The performance of this ML model was evaluated using data from the Amsterdam UMC location VUmc and compared with the reference standard of traditional risk scores. A total of 1253 patients (775 training set and 478 testing set) were included, of which 176 patients (105 training set and 71 testing set) died during the 5-year follow-up period. The ML model demonstrated a superior performance [area under the receiver operating characteristic curve (AUC) 0.79] compared with traditional risk stratification tools (AUC 0.62-0.76) and showed good external performance. The most important TTE risk predictors included in the ML model were LV dysfunction and significant tricuspid regurgitation. Conclusion: This study demonstrates that an explainable ML model using TTE and clinical data can accurately identify high-risk CCS patients, with a prognostic value superior to traditional risk scores.

The impact of valvular heart disease in patients with chronic coronary syndrome.

Background: The European Society of Cardiology 2019 Guidelines on chronic coronary syndrome (CCS) recommend echocardiographic measurement of the left ventricular function for risk stratification in all patients with CCS. Whereas CCS and valvular heart disease (VHD) share common pathophysiological pathways and risk factors, data on the impact of VHD in CCS patients are scarce. Methods: Clinical data including treatment and mortality of patients diagnosed with CCS who underwent comprehensive transthoracic echocardiography (TTE) in two tertiary centers were collected. The outcome was all-cause mortality. Data were analyzed with Kaplan-Meier curves and Cox proportional hazard analysis adjusting for significant covariables and time-dependent treatment. Results: Between 2014 and 2021 a total of 1,984 patients with CCS (59% men) with a median age of 65 years (interquartile range [IQR] 57-73) underwent comprehensive TTE. Severe VHD was present in 44 patients and moderate VHD in 325 patients. A total of 654 patients (33%) were treated with revascularization, 39 patients (2%) received valve repair or replacement and 299 patients (15%) died during the median follow-up time of 3.5 years (IQR 1.7-5.6). Moderate or severe VHD (hazard ratio = 1.33; 95% CI 1.02-1.72) was significantly associated with mortality risk, independent of LV function and other covariables, as compared to no/mild VHD. Conclusions: VHD has a significant impact on mortality in patients with CCS additional to LV dysfunction, which emphasizes the need for a comprehensive echocardiographic assessment in these patients.

Accuracy of a Standalone Atrial Fibrillation Detection Algorithm Added to a Popular Wristband and Smartwatch: Prospective Diagnostic Accuracy Study.

BACKGROUND: Silent paroxysmal atrial fibrillation (AF) may be difficult to diagnose, and AF burden is hard to establish. In contrast to conventional diagnostic devices, photoplethysmography (PPG)-driven smartwatches or wristbands allow for long-term continuous heart rhythm assessment. However, most smartwatches lack an integrated PPG-AF algorithm. Adding a standalone PPG-AF algorithm to these wrist devices might open new possibilities for AF screening and burden assessment. OBJECTIVE: The aim of this study was to assess the accuracy of a well-known standalone PPG-AF detection algorithm added to a popular wristband and smartwatch, with regard to discriminating AF and sinus rhythm, in a group of patients with AF before and after cardioversion (CV). METHODS: Consecutive consenting patients with AF admitted for CV in a large academic hospital in Amsterdam, the Netherlands, were asked to wear a Biostrap wristband or Fitbit Ionic smartwatch with Fibricheck algorithm add-on surrounding the procedure. A set of 1-min PPG measurements and 12-lead reference electrocardiograms was obtained before and after CV. Rhythm assessment by the PPG device-software combination was compared with the 12-lead electrocardiogram. RESULTS: A total of 78 patients were included in the Biostrap-Fibricheck cohort (156 measurement sets) and 73 patients in the Fitbit-Fibricheck cohort (143 measurement sets). Of the measurement sets, 19/156 (12%) and 7/143 (5%), respectively, were not classifiable by the PPG algorithm due to bad quality. The diagnostic performance in terms of sensitivity, specificity, positive predictive value, negative predictive value, and accuracy was 98%, 96%, 96%, 99%, 97%, and 97%, 100%, 100%, 97%, and 99%, respectively, at an AF prevalence of ~50%. CONCLUSIONS: This study demonstrates that the addition of a well-known standalone PPG-AF detection algorithm to a popular PPG smartwatch and wristband without integrated algorithm yields a high accuracy for the detection of AF, with an acceptable unclassifiable rate, in a semicontrolled environment.

Cardiac age detected by machine learning applied to the surface ECG of healthy subjects: Creation of a benchmark.

OBJECTIVE: The aim of the present study was to develop a neural network to characterize the effect of aging on the ECG in healthy volunteers. Moreover, the impact of the various ECG features on aging was evaluated. METHODS & RESULTS: A total of 6228 healthy subjects without structural heart disease were included in this study. A neural network regression model was created to predict age of the subjects based on their ECG; 577 parameters derived from a 12­lead ECG of each subject were used to develop and validate the neural network; A tenfold cross-validation was performed, using 118 subjects for validation each fold. Using SHapley Additive exPlanations values the impact of the individual features on the prediction of age was determined. Of 6228 subjects tested, 1808 (29%) were females and mean age was 34 years, range 18-75 years. Physiologic age was estimated as a continuous variable with an average error of 6.9 ± 5.6 years (R2 = 0.72 ± 0.04). The correlation was slightly stronger for men (R2 = 0.74) than for women (R2 = 0.66). The most important features on the prediction of physiologic age were T wave morphology indices in leads V4 and V5, and P wave amplitude in leads AVR and II. CONCLUSION: The application of machine learning to the ECG using a neural network regression model, allows accurate estimation of physiologic cardiac age. This technique could be used to pick up subtle age-related cardiac changes, but also estimate the reversing of these age-associated effects by administered treatments.

Current State and Future Perspectives of Artificial Intelligence for Automated Coronary Angiography Imaging Analysis in Patients with Ischemic Heart Disease.

PURPOSE OF REVIEW: Artificial intelligence (AI) applications in (interventional) cardiology continue to emerge. This review summarizes the current state and future perspectives of AI for automated imaging analysis in invasive coronary angiography (ICA). RECENT FINDINGS: Recently, 12 studies on AI for automated imaging analysis In ICA have been published. In these studies, machine learning (ML) models have been developed for frame selection, segmentation, lesion assessment, and functional assessment of coronary flow. These ML models have been developed on monocenter datasets (in range 31-14,509 patients) and showed moderate to good performance. However, only three ML models were externally validated. Given the current pace of AI developments for the analysis of ICA, less-invasive, objective, and automated diagnosis of CAD can be expected in the near future. Further research on this technology in the catheterization laboratory may assist and improve treatment allocation, risk stratification, and cath lab logistics by integrating ICA analysis with other clinical characteristics.

Cardiovascular magnetic resonance techniques for tissue characterization after acute myocardial injury.

The annual incidence of hospital admission for acute myocardial infarction lies between 90 and 312 per 100 000 inhabitants in Europe. Despite advances in patient care 1 year mortality after ST-segment elevation myocardial infarction (STEMI) remains around 10%. Cardiovascular magnetic resonance imaging (CMR) has emerged as a robust imaging modality for assessing patients after acute myocardial injury. In addition to accurate assessment of left ventricular ejection fraction and volumes, CMR offers the unique ability of visualization of myocardial injury through a variety of imaging techniques such as late gadolinium enhancement and T2-weighted imaging. Furthermore, new parametric mapping techniques allow accurate quantification of myocardial injury and are currently being exploited in large trials aiming to augment risk management and treatment of STEMI patients. Of interest, CMR enables the detection of microvascular injury (MVI) which occurs in approximately 40% of STEMI patients and is a major independent predictor of mortality and heart failure. In this article, we review traditional and novel CMR techniques used for myocardial tissue characterization after acute myocardial injury, including the detection and quantification of MVI. Moreover, we discuss clinical scenarios of acute myocardial injury in which the tissue characterization techniques can be applied and we provide proposed imaging protocols tailored to each scenario.

eHealth to improve patient outcome in rehabilitating myocardial infarction patients.

INTRODUCTION: Cardiac rehabilitation is aimed at risk factor modification and improving quality of life. eHealth has a couple of potential benefits to improve this aim. The primary purpose of this review is to summarize available literature for eHealth strategies that have been investigated in randomized controlled trials in post-myocardial infarction (MI) patients. The second purpose of this review is to investigate the clinical effectiveness in post-MI patients. Areas covered: The literature was searched using PubMed. Randomized controlled trials (RCTs) describing interventions in patients that had experienced an ST-elevation myocardial infarction or non-ST acute coronary syndrome were eligible for inclusion. Fifteen full-texts were included and their results are described in this review. These RCTs described interventions that used remote coaching or remote monitoring in post-MI patients. Most interventions resulted in an improved cardiovascular risk profile. Remote coaching had a positive effect on activity and dietary intake. Expert opinion: eHealth might be clinically beneficial in post-MI patients, particularly for risk estimation. Moreover, eHealth as a tool for remote coaching on activity is a good addition to traditional cardiac rehabilitation programs. Further research needs to corroborate these findings.

Double jeopardy: two major complications of a myocardial infarction in one patient.

A 62-year-old woman with no cardiac history was admitted to the hospital with an ambulant inferoposterolateral myocardial infarction. She experienced two major complications, namely, a free-wall rupture of the infarcted area, on which a bovine pericardial patch was glued surgically, and, a few days later, a posteromedial papillary muscle rupture, for which a mitral valve replacement was performed. She survived both complications and is now rehabilitating at home.

[Methaemoglobinaemia after using EMLA cream]. / Methemoglobinemie na gebruik van EMLA-crème.

BACKGROUND: The use of creams is considered to be generally safe. However, systemic side effects can occur. CASE DESCRIPTION: A 22-year-old woman came to the emergency department with dyspnea, confusion and 'blue' skin after laser treatment of the upper legs for excessive hair. She had used three tubes of a eutectic mixture of local anaesthetics (EMLA) cream containing lidocaine/prilocaine for analgesia. Her oxygen saturation was 87%, measured with pulse oximetry. Blood gas analysis showed a concentration of oxy-Hb of 79% and a met-Hb of 19%. Our working diagnosis was methaemoglobinaemia as a result of using excessive amounts of EMLA cream. Because the met-Hb concentration decreased spontaneously and the oxy-Hb concentration consequently normalised, we did not administer methylene blue. The patient was discharged symptom-free after several hours of observation. CONCLUSION: An overdose of EMLA cream, whether or not in combination with laser-induced skin damage, can produce a high systemic o-toluidine concentration. This can lead to methaemoglobinaemia. In such cases, the pulse oximeter is not reliable for measuring the oxygen saturation; therefore, blood gas analysis is necessary for making a diagnosis.

The acute effect of intra-aortic balloon counterpulsation during extracorporeal life support: an experimental study.

Hemodynamically unstable patients supported by an extracorporeal life support (ECLS) circuit often receive additional support by intra-aortic balloon pump (IABP). However, it is not established whether support of the failing heart is improved by adjunctive IABP in both peripheral cannulation (PC) and central cannulation (CC) settings. Seven sheep were supported by an IABP and an ECLS system which were cannulated centrally as well as peripherally. In each cannulation configuration, hemodynamic and cardiac function indices were measured at baseline, ECLS, and ECLS plus IABP. The primary variables were mean coronary artery flow (Qcor), diastolic pressure time index (DPTI), left ventricular (LV) pressure-volume area (PVA), and tension time index (TTI). Additional IABP with ECLS support (CC/PC) decreased LV afterload (LV systolic peak pressure -4%, P<0.05/-8%, P<0.02), as well as TTI -2%/-10% and PVA -10%/-12% (P<0.03). Coronary perfusion was increased by additional IABP: CC, Qcor, +9%, and DPTI, +18% (P<0.02); PC, Qcor,+6%, and DPTI, +11% (P<0.05). IABP augmented the myocardial oxygen supply/demand ratios (CC/PC): Qcor/(PVA.heart rate) (+21%/+22%, P<0.02) and DPTI/TTI (+27%/+24%, P<0.03). In case of low arterial pressure (<50 mm Hg) and reduced ECLS flow, the overall hemodynamic profile improved only with central cannulation. We conclude that in both central and peripheral ECLS cannulation settings, adjunctive IABP improves the myocardial oxygen supply demand balance. In case of low cardiac output and insufficient extracorporeal flow with PC, adjunctive IABP may be contraindicated.