Continuous ECG monitoring should be the heart of bedside AI-based predictive analytics monitoring for early detection of clinical deterioration.

The idea that we can detect subacute potentially catastrophic illness earlier by using statistical models trained on clinical data is now well-established. We review evidence that supports the role of continuous cardiorespiratory monitoring in these predictive analytics monitoring tools. In particular, we review how continuous ECG monitoring reflects the patient and not the clinician, is less likely to be biased, is unaffected by changes in practice patterns, captures signatures of illnesses that are interpretable by clinicians, and is an underappreciated and underutilized source of detailed information for new mathematical methods to reveal.

Exercise, Sports Participation, and Quality of Life in Young Patients with Heritable Thoracic Aortic Disease.

INTRODUCTION: Patients with heritable thoracic aortic disease (HTAD)are often restricted from sports and certain types of exercise. This study was designed to investigate the effect of lifetime exercise exposure and competitive sports participation on quality of life (QOL) in patients aged 15-35 with syndromic [Marfan syndrome (MFS), Loeys-Dietz syndrome (LDS), vascular Ehlers-Danlos syndrome (vEDS)] and non-syndromic heritable thoracic aortic disease (nsHTAD). METHODS: This cross-sectional study employed questionnaires to assess lifetime exercise exposure and utilized the PedsQL QOL Inventory. We developed an Exercise Exposure Score (EES) to quantify lifetime exercise exposure. Questionnaires were completed via telephone with complimentary medical record review. RESULTS: Forty patients were enrolled. Mean age was 26 years. The diagnosis was MFS in 83%. Despite 88% of patients being restricted by their provider, 65% reported competitive sports participation and 93% reported recreational exercise. Participants with an EES greater than the median had significantly better total QOL scores compared to those below the median (78 vs 65, p = 0.03). There were significant positive correlations between current frequency of exercise and psychosocial QOL (slope = 3.9, 95% CI: (1.2, 6.6), p = 0.005), physical QOL (slope = 8.1, 95% CI: (4.1, 12), p < 0.001), and total QOL score (slope = 6.0, 95% CI: (3.1, 9.0), p < 0.001). We found no difference in aortic size or need for surgical intervention between those above and below the median EES, or between those who did and did not participate in competitive sports. CONCLUSIONS: Despite exercise restrictions, young HTAD patients are physically active. Increased lifetime exercise and current physical activity levels were associated with improved QOL in HTAD patients.

Prospective validation of clinical deterioration predictive models prior to intensive care unit transfer among patients admitted to acute care cardiology wards.

Objective. Very few predictive models have been externally validated in a prospective cohort following the implementation of an artificial intelligence analytic system. This type of real-world validation is critically important due to the risk of data drift, or changes in data definitions or clinical practices over time, that could impact model performance in contemporaneous real-world cohorts. In this work, we report the model performance of a predictive analytics tool developed before COVID-19 and demonstrate model performance during the COVID-19 pandemic.Approach. The analytic system (CoMETⓇ, Nihon Kohden Digital Health Solutions LLC, Irvine, CA) was implemented in a randomized controlled trial that enrolled 10 422 patient visits in a 1:1 display-on display-off design. The CoMET scores were calculated for all patients but only displayed in the display-on arm. Only the control/display-off group is reported here because the scores could not alter care patterns.Main results.Of the 5184 visits in the display-off arm, 311 experienced clinical deterioration and care escalation, resulting in transfer to the intensive care unit, primarily due to respiratory distress. The model performance of CoMET was assessed based on areas under the receiver operating characteristic curve, which ranged from 0.725 to 0.737.Significance.The models were well-calibrated, and there were dynamic increases in the model scores in the hours preceding the clinical deterioration events. A hypothetical alerting strategy based on a rise in score and duration of the rise would have had good performance, with a positive predictive value more than 10-fold the event rate. We conclude that predictive statistical models developed five years before study initiation had good model performance despite the passage of time and the impact of the COVID-19 pandemic.

Beyond prediction: Off-target uses of artificial intelligence-based predictive analytics in a learning health system.

Introduction: Artificial-intelligence (AI)-based predictive analytics provide new opportunities to leverage rich sources of continuous data to improve patient care through early warning of the risk of clinical deterioration and improved situational awareness.Part of the success of predictive analytic implementation relies on integration of the analytic within complex clinical workflows. Pharmaceutical interventions have off-target uses where a drug indication has not been formally studied for a different indication but has potential for clinical benefit. An analog has not been described in the context of AI-based predictive analytics, that is, when a predictive analytic has been trained on one outcome of interest but is used for additional applications in clinical practice. Methods: In this manuscript we present three clinical vignettes describing off-target use of AI-based predictive analytics that evolved organically through real-world practice. Results: Off-target uses included:real-time feedback about treatment effectiveness, indication of readiness to discharge, and indication of the acuity of a hospital unit. Conclusion: Such practice fits well with the learning health system goals to continuously integrate data and experience to provide.

First-in-human noninvasive left ventricular ultrasound pacing: A potential screening tool for cardiac resynchronization therapy.

Background: A screening tool to predict response to cardiac resynchronization therapy (CRT) could improve patient selection and outcomes. Objective: The purpose of this study was to investigate the feasibility and safety of noninvasive CRT via transcutaneous ultrasonic left ventricular (LV) pacing applied as a screening test before CRT implants. Methods: P-wave-triggered ultrasound stimuli were delivered during bolus dosing of an echocardiographic contrast agent to simulate CRT noninvasively. Ultrasound pacing was delivered at a variety of LV locations with a range of atrioventricular delays to achieve fusion with intrinsic ventricular activation. Three-dimensional cardiac activation maps were acquired via the Medtronic CardioInsight 252-electrode mapping vest during baseline, ultrasound pacing, and after CRT implantation. A separate control group received only the CRT implants. Results: Ultrasound pacing was achieved in 10 patients with a mean of 81.2 ± 50.8 ultrasound paced beats per patient and up to 20 consecutive beats of ultrasound pacing. QRS width at baseline (168.2 ± 17.8 ms) decreased significantly to 117.3 ± 21.5 ms (P <.001) in the best ultrasound paced beat and to 125.8 ± 13.3 ms (P <.001) in the best CRT beat. Electrical activation patterns were similar between CRT pacing and ultrasound pacing with stimulation from the same area of the LV. Troponin results were similar between the ultrasound pacing and the control groups (P = .96), confirming safety. Conclusion: Noninvasive ultrasound pacing before CRT is safe and feasible, and it estimates the degree of electrical resynchronization achievable with CRT. Further study of this promising technique to guide CRT patient selection is warranted.

Cardiac Magnetic Resonance, Electromechanical Activation, Kidney Function, and Natriuretic Peptides in Cardiac Resynchronization Therapy Upgrades.

As the mechanism for worse prognosis after cardiac resynchronization therapy (CRT) upgrades in heart failure patients with RVP dependence (RVP-HF) has clinical implications for patient selection and CRT implementation approaches, this study's objective was to evaluate prognostic implications of cardiac magnetic resonance (CMR) findings and clinical factors in 102 HF patients (23.5% female, median age 66.5 years old, median follow-up 4.8 years) with and without RVP dependence undergoing upgrade and de novo CRT implants. Compared with other CRT groups, RVP-HF patients had decreased survival (p = 0.02), more anterior late-activated LV pacing sites (p = 0.002) by CMR, more atrial fibrillation (p = 0.0006), and higher creatinine (0.002). CMR activation timing at the LV pacing site predicted post-CRT LV functional improvement (p < 0.05), and mechanical activation onset < 34 ms by CMR at the LVP site was associated with decreased post-CRT survival in a model with higher pre-CRT creatinine and B-type natriuretic peptide (AUC 0.89; p < 0.0001); however, only the higher pre-CRT creatinine partially mediated (37%) the decreased survival in RVP-HF patients. In conclusion, RVP-HF had a distinct CMR phenotype, which has important implications for the selection of LV pacing sites in CRT upgrades, and only chronic kidney disease mediated the decreased survival after CRT in RVP-HF.

Machine learning for multidimensional response and survival after cardiac resynchronization therapy using features from cardiac magnetic resonance.

Background: Cardiac resynchronization therapy (CRT) response is complex, and better approaches are required to predict survival and need for advanced therapies. Objective: The objective was to use machine learning to characterize multidimensional CRT response and its relationship with long-term survival. Methods: Associations of 39 baseline features (including cardiac magnetic resonance [CMR] findings and clinical parameters such as glomerular filtration rate [GFR]) with a multidimensional CRT response vector (consisting of post-CRT left ventricular end-systolic volume index [LVESVI] fractional change, post-CRT B-type natriuretic peptide, and change in peak VO2) were evaluated. Machine learning generated response clusters, and cross-validation assessed associations of clusters with 4-year survival. Results: Among 200 patients (median age 67.4 years, 27.0% women) with CRT and CMR, associations with more than 1 response parameter were noted for the CMR CURE-SVD dyssynchrony parameter (associated with post-CRT brain natriuretic peptide [BNP] and LVESVI fractional change) and GFR (associated with peak VO2 and post-CRT BNP). Machine learning defined 3 response clusters: cluster 1 (n = 123, 90.2% survival [best]), cluster 2 (n = 45, 60.0% survival [intermediate]), and cluster 3 (n = 32, 34.4% survival [worst]). Adding the 6-month response cluster to baseline features improved the area under the receiver operating characteristic curve for 4-year survival from 0.78 to 0.86 (P = .02). A web-based application was developed for cluster determination in future patients. Conclusion: Machine learning characterizes distinct CRT response clusters influenced by CMR features, kidney function, and other factors. These clusters have a strong and additive influence on long-term survival relative to baseline features.

Cardiac magnetic resonance defines mechanisms of sex-based differences in outcomes following cardiac resynchronization therapy.

Background: Mechanisms of sex-based differences in outcomes following cardiac resynchronization therapy (CRT) are poorly understood. Objective: To use cardiac magnetic resonance (CMR) to define mechanisms of sex-based differences in outcomes after CRT and describe distinct CMR-based phenotypes of CRT candidates based on sex and non-ischemic/ischemic cardiomyopathy type. Materials and methods: In a prospective study, sex-based differences in three short-term CRT response measures [fractional change in left ventricular end-systolic volume index 6 months after CRT (LVESVI-FC), B-type natriuretic peptide (BNP) 6 months after CRT, change in peak VO2 6 months after CRT], and long-term survival were evaluated with respect to 39 baseline parameters from CMR, exercise testing, laboratory testing, electrocardiograms, comorbid conditions, and other sources. CMR was also used to quantify the degree of left-ventricular mechanical dyssynchrony by deriving the circumferential uniformity ratio estimate (CURE-SVD) parameter from displacement encoding with stimulated echoes (DENSE) strain imaging. Statistical methods included multivariable linear regression with evaluation of interaction effects associated with sex and cardiomyopathy type (ischemic and non-ischemic cardiomyopathy) and survival analysis. Results: Among 200 patients, the 54 female patients (27%) pre-CRT had a smaller CMR-based LVEDVI (p = 0.04), more mechanical dyssynchrony based on the validated CMR CURE-SVD parameter (p = 0.04), a lower frequency of both late gadolinium enhancement (LGE) and ischemic cardiomyopathy (p < 0.0001), a greater RVEF (p = 0.02), and a greater frequency of LBBB (p = 0.01). After categorization of patients into four groups based on cardiomyopathy type (ischemic/non-ischemic cardiomyopathy) and sex, female patients with non-ischemic cardiomyopathy had the lowest CURE-SVD (p = 0.003), the lowest pre-CRT BNP levels (p = 0.01), the lowest post-CRT BNP levels (p = 0.05), and the most favorable LVESVI-FC (p = 0.001). Overall, female patients had better 3-year survival before adjustment for cardiomyopathy type (p = 0.007, HR = 0.45) and after adjustment for cardiomyopathy type (p = 0.009, HR = 0.67). Conclusion: CMR identifies distinct phenotypes of female CRT patients with non-ischemic and ischemic cardiomyopathy relative to male patients stratified by cardiomyopathy type. The more favorable short-term response and long-term survival outcomes in female heart failure patients with CRT were associated with lower indexed CMR-based LV volumes, decreased presence of scar associated with prior myocardial infarction and ICM, and greater CMR-based dyssynchrony with the CURE-SVD.

cAMP-Dependent Signaling Restores AP Firing in Dormant SA Node Cells via Enhancement of Surface Membrane Currents and Calcium Coupling.

Action potential (AP) firing rate and rhythm of sinoatrial nodal cells (SANC) are controlled by synergy between intracellular rhythmic local Ca2+ releases (LCRs) ("Ca2+ clock") and sarcolemmal electrogenic mechanisms ("membrane clock"). However, some SANC do not fire APs (dormant SANC). Prior studies have shown that ß-adrenoceptor stimulation can restore AP firing in these cells. Here we tested whether this relates to improvement of synchronization of clock coupling. We characterized membrane potential, ion currents, Ca2+ dynamics, and phospholamban (PLB) phosphorylation, regulating Ca2+ pump in enzymatically isolated single guinea pig SANC prior to, during, and following ß-adrenoceptor stimulation (isoproterenol) or application of cell-permeant cAMP (CPT-cAMP). Phosphorylation of PLB (Serine 16) was quantified in the same cells following Ca2+ measurement. In dormant SANC LCRs were small and disorganized at baseline, membrane potential was depolarized (-38 ± 1 mV, n = 46), and ICaL, If, and IK densities were smaller vs SANC firing APs. ß-adrenoceptor stimulation or application of CPT-cAMP led to de novo spontaneous AP generation in 44 and 46% of dormant SANC, respectively. The initial response was an increase in size, rhythmicity and synchronization of LCRs, paralleled with membrane hyperpolarization and small amplitude APs (rate ∼1 Hz). During the transition to steady-state AP firing, LCR size further increased, while LCR period shortened. LCRs became more synchronized resulting in the growth of an ensemble LCR signal peaked in late diastole, culminating in AP ignition; the rate of diastolic depolarization, AP amplitude, and AP firing rate increased. ICaL, IK, and If amplitudes in dormant SANC increased in response to ß-adrenoceptor stimulation. During washout, all changes reversed in order. Total PLB was higher, but the ratio of phosphorylated PLB (Serine 16) to total PLB was lower in dormant SANC. ß-adrenoceptor stimulation increased this ratio in AP-firing cells. Thus, transition of dormant SANC to AP firing is linked to the increased functional coupling of membrane and Ca2+ clock proteins. The transition occurs via (i) an increase in cAMP-mediated phosphorylation of PLB accelerating Ca2+ pumping, (ii) increased spatiotemporal LCR synchronization, yielding a larger diastolic LCR ensemble signal resulting in an earlier increase in diastolic INCX; and (iii) increased current densities of If, ICaL, and IK.

Predictive Monitoring-Impact in Acute Care Cardiology Trial (PM-IMPACCT): Protocol for a Randomized Controlled Trial.

BACKGROUND: Patients in acute care wards who deteriorate and are emergently transferred to intensive care units (ICUs) have poor outcomes. Early identification of patients who are decompensating might allow for earlier clinical intervention and reduced morbidity and mortality. Advances in bedside continuous predictive analytics monitoring (ie, artificial intelligence [AI]-based risk prediction) have made complex data easily available to health care providers and have provided early warning of potentially catastrophic clinical events. We present a dynamic, visual, predictive analytics monitoring tool that integrates real-time bedside telemetric physiologic data into robust clinical models to estimate and communicate risk of imminent events. This tool, Continuous Monitoring of Event Trajectories (CoMET), has been shown in retrospective observational studies to predict clinical decompensation on the acute care ward. There is a need to more definitively study this advanced predictive analytics or AI monitoring system in a prospective, randomized controlled, clinical trial. OBJECTIVE: The goal of this trial is to determine the impact of an AI-based visual risk analytic, CoMET, on improving patient outcomes related to clinical deterioration, response time to proactive clinical action, and costs to the health care system. METHODS: We propose a cluster randomized controlled trial to test the impact of using the CoMET display in an acute care cardiology and cardiothoracic surgery hospital floor. The number of admissions to a room undergoing cluster randomization was estimated to be 10,424 over the 20-month study period. Cluster randomization based on bed number will occur every 2 months. The intervention cluster will have the CoMET score displayed (along with standard of care), while the usual care group will receive standard of care only. RESULTS: The primary outcome will be hours free from events of clinical deterioration. Hours of acute clinical events are defined as time when one or more of the following occur: emergent ICU transfer, emergent surgery prior to ICU transfer, cardiac arrest prior to ICU transfer, emergent intubation, or death. The clinical trial began randomization in January 2021. CONCLUSIONS: Very few AI-based health analytics have been translated from algorithm to real-world use. This study will use robust, prospective, randomized controlled, clinical trial methodology to assess the effectiveness of an advanced AI predictive analytics monitoring system in incorporating real-time telemetric data for identifying clinical deterioration on acute care wards. This analysis will strengthen the ability of health care organizations to evolve as learning health systems, in which bioinformatics data are applied to improve patient outcomes by incorporating AI into knowledge tools that are successfully integrated into clinical practice by health care providers. TRIAL REGISTRATION: ClinicalTrials.gov NCT04359641; https://clinicaltrials.gov/ct2/show/NCT04359641. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/29631.

Cardiac Magnetic Resonance Assessment of Response to Cardiac Resynchronization Therapy and Programming Strategies.

OBJECTIVES: The objective was to determine the feasibility and effectiveness of cardiac magnetic resonance (CMR) cine and strain imaging before and after cardiac resynchronization therapy (CRT) for assessment of response and the optimal resynchronization pacing strategy. BACKGROUND: CMR with cardiac implantable electronic devices can safely provide high-quality right ventricular/left ventricular (LV) ejection fraction (RVEF/LVEF) assessments and strain. METHODS: CMR with cine imaging, displacement encoding with stimulated echoes for the circumferential uniformity ratio estimate with singular value decomposition (CURE-SVD) dyssynchrony parameter, and scar assessment was performed before and after CRT. Whereas the pre-CRT scan constituted a single "imaging set" with complete volumetric, strain, and scar imaging, multiple imaging sets with complete strain and volumetric data were obtained during the post-CRT scan for biventricular pacing (BIVP), LV pacing (LVP), and asynchronous atrial pacing modes by reprogramming the device outside the scanner between imaging sets. RESULTS: 100 CMRs with a total of 162 imaging sets were performed in 50 patients (median age 70 years [IQR: 50-86 years]; 48% female). Reduction in LV end-diastolic volumes (P = 0.002) independent of CRT pacing were more prominent than corresponding reductions in right ventricular end-diastolic volumes (P = 0.16). A clear dependence of the optimal CRT pacing mode (BIVP vs LVP) on the PR interval (P = 0.0006) was demonstrated. The LVEF and RVEF improved more with BIVP than LVP with PR intervals ≥240 milliseconds (P = 0.025 and P = 0.002, respectively); the optimal mode (BIVP vs LVP) was variable with PR intervals <240 milliseconds. A lower pre-CRT displacement encoding with stimulated echoes (DENSE) CURE-SVD was associated with greater improvements in the post-CRT CURE-SVD (r = -0.69; P < 0.001), LV end-systolic volume (r = -0.58; P < 0.001), and LVEF (r = -0.52; P < 0.001). CONCLUSIONS: CMR evaluation with assessment of multiple pacing modes during a single scan after CRT is feasible and provides useful information for patient care with respect to response and the optimal pacing strategy.

Heart rate fragmentation gives novel insights into non-autonomic mechanisms governing beat-to-beat control of the heart's rhythm.

To demonstrate how heart rate fragmentation gives novel insights into non-autonomic mechanisms of beat-to-beat variability in cycle length, and predicts survival of cardiology clinic patients, over and above traditional clinical risk factors and measures of heart rate variability. Approach: We studied 2893 patients seen by cardiologists with clinical data including 24-hour Holter monitoring. Novel measures of heart rate fragmentation alongside canonical time and frequency domain measures of heart rate variability, as well as an existing local dynamics score were calculated. A proportional hazards model was utilized to relate the results to survival. Main results: The novel heart rate fragmentation measures were validated and characterized with respect to the effects of age, ectopy and atrial fibrillation. Correlations between parameters were determined. Critically, heart rate fragmentation results could not be accounted for by undersampling respiratory sinus arrhythmia. Increased heart rate fragmentation was associated with poorer survival (p ≪ 0.01 in the univariate model). In multivariable analyses, increased heart rate fragmentation and more abnormal local dynamics (p 0.045), along with increased clinical risk factors (age (p ≪ 0.01), tobacco use (p ≪ 0.01) and history of heart failure (p 0.019)) and lower low- to high-frequency ratio (p 0.022) were all independent predictors of 2-year mortality. Significance: Analysis of continuous ECG data with heart rate fragmentation indices yields information regarding non-autonomic control of beat-to-beat variability in cycle length that is independent of and additive to established parameters for investigating heart rate variability, and predicts mortality in concert with measures of local dynamics, frequency content of heart rate, and clinical risk factors.

A coupled-clock system drives the automaticity of human sinoatrial nodal pacemaker cells.

The spontaneous rhythmic action potentials generated by the sinoatrial node (SAN), the primary pacemaker in the heart, dictate the regular and optimal cardiac contractions that pump blood around the body. Although the heart rate of humans is substantially slower than that of smaller experimental animals, current perspectives on the biophysical mechanisms underlying the automaticity of sinoatrial nodal pacemaker cells (SANCs) have been gleaned largely from studies of animal hearts. Using human SANCs, we demonstrated that spontaneous rhythmic local Ca2+ releases generated by a Ca2+ clock were coupled to electrogenic surface membrane molecules (the M clock) to trigger rhythmic action potentials, and that Ca2+-cAMP-protein kinase A (PKA) signaling regulated clock coupling. When these clocks became uncoupled, SANCs failed to generate spontaneous action potentials, showing a depolarized membrane potential and disorganized local Ca2+ releases that failed to activate the M clock. ß-Adrenergic receptor (ß-AR) stimulation, which increases cAMP concentrations and clock coupling in other species, restored spontaneous, rhythmic action potentials in some nonbeating "arrested" human SANCs by increasing intracellular Ca2+ concentrations and synchronizing diastolic local Ca2+ releases. When ß-AR stimulation was withdrawn, the clocks again became uncoupled, and SANCs reverted to a nonbeating arrested state. Thus, automaticity of human pacemaker cells is driven by a coupled-clock system driven by Ca2+-cAMP-PKA signaling. Extreme clock uncoupling led to failure of spontaneous action potential generation, which was restored by recoupling of the clocks. Clock coupling and action potential firing in some of these arrested cells can be restored by ß-AR stimulation-induced augmentation of Ca2+-cAMP-PKA signaling.