Association of Short-Term Increases in Ambient Fine Particulate Matter With Hospitalization for Asthma or COPD During Wildfire Season and Other Time Periods.

BACKGROUND: Short-term increases in air pollution are associated with poor asthma and COPD outcomes. Short-term elevations in fine particulate matter (PM2.5) due to wildfire smoke are becoming more common. RESEARCH QUESTION: Are short-term increases in PM2.5 and ozone in wildfire season and in winter inversion season associated with a composite of emergency or inpatient hospitalization for asthma and COPD? STUDY DESIGN AND METHODS: Case-crossover analyses evaluated 63,976 and 18,514 patients hospitalized for primary discharge diagnoses of asthma and COPD, respectively, between January 1999 and March 2022. Patients resided on Utah's Wasatch Front where PM2.5 and ozone were measured by Environmental Protection Agency-based monitors. ORs were calculated using Poisson regression adjusted for weather variables. RESULTS: Asthma risk increased on the same day that PM2.5 increased during wildfire season (OR, 1.057 per + 10 µg/m3; 95% CI, 1.019-1.097; P = .003) and winter inversions (OR, 1.023 per +10 µg/m3; 95% CI, 1.010-1.037; P = .0004). Risk decreased after 1 week, but during wildfire season risk rebounded at a 4-week lag (OR, 1.098 per +10 µg/m3; 95% CI, 1.033-1.167). Asthma risk for adults during wildfire season was highest in the first 3 days after PM2.5 increases, but for children, the highest risk was delayed by 3 to 4 weeks. PM2.5 exposure was weakly associated with COPD hospitalization. Ozone exposure was not associated with elevated risks. INTERPRETATION: In a large urban population, short-term increases in PM2.5 during wildfire season were associated with asthma hospitalization, and the effect sizes were greater than for PM2.5 during inversion season.

Periodic Fasting and Acute Cardiac Events in Patients Evaluated for COVID-19: An Observational Prospective Cohort Study.

BACKGROUND: Periodic fasting was previously associated with greater longevity and a lower incidence of heart failure (HF) in a pre-pandemic population. In patients with coronavirus disease 2019 (COVID-19), periodic fasting was associated with a lower risk of death or hospitalization. This study evaluated the association between periodic fasting and HF hospitalization and major adverse cardiovascular events (MACEs). METHODS: Patients enrolled in the INSPIRE registry from February 2013 to March 2020 provided periodic fasting information and were followed into the pandemic (n = 5227). Between March 2020 and February 2023, N = 2373 patients were studied, with n = 601 COVID-positive patients being the primary study population (2836 had no COVID-19 test; 18 were excluded due to fasting <5 years). A Cox regression was used to evaluate HF admissions, MACEs, and other endpoints through March 2023, adjusting for covariables, including time-varying COVID-19 vaccination. RESULTS: In patients positive for COVID-19, periodic fasting was reported by 180 (30.0% of 601), who periodically fasted over 43.1 ± 19.2 years (min: 7, max: 83). HF hospitalization (n = 117, 19.5%) occurred in 13.3% of fasters and 22.1% of non-fasters [adjusted hazard ratio (aHR) = 0.63, CI = 0.40, 0.99; p = 0.044]. Most HF admissions were exacerbations, with a prior HF diagnosis in 111 (94.9%) patients hospitalized for HF. Fasting was also associated with a lower MACE risk (aHR = 0.64, CI = 0.43, 0.96; p = 0.030). In n = 1772 COVID-negative patients (29.7% fasters), fasting was not associated with HF hospitalization (aHR = 0.82, CI = 0.64, 1.05; p = 0.12). In COVID-positive and negative patients combined, periodic fasting was associated with lower mortality (aHR = 0.60, CI = 0.39, 0.93; p = 0.021). CONCLUSIONS: Routine periodic fasting was associated with less HF hospitalization in patients positive for COVID-19.

Identifying consistent echocardiographic thresholds for risk stratification in pulmonary arterial hypertension.

Several indices of right heart remodeling and function have been associated with survival in pulmonary arterial hypertension (PAH). Outcome analysis and physiological relationships between variables may help develop a consistent grading system. Patients with Group 1 PAH followed at Stanford Hospital who underwent right heart catheterization and echocardiography within 2 weeks were considered for inclusion. Echocardiographic variables included tricuspid annular plane systolic excursion (TAPSE), right ventricular (RV) fractional area change (RVFAC), free wall strain (RVFWS), RV dimensions, and right atrial volumes. The main outcome consisted of death or lung transplantation at 5 years. Mathematical relationships between variables were determined using weighted linear regression and severity thresholds for were calibrated to a 20% 1-year mortality risk. PAH patients (n = 223) had mean (SD) age of 48.1 (14.1) years, most were female (78%), with a mean pulmonary arterial pressure of 51.6 (13.8) mmHg and pulmonary vascular resistance index of 22.5(6.3) WU/m2. Measures of right heart size and function were strongly related to each other particularly RVFWS and RVFAC (R 2 = 0.82, p < 0.001), whereas the relationship between TAPSE and RVFWS was weaker (R 2 = 0.28, p < 0.001). Death or lung transplantation at 5 years occurred in 78 patients (35%). Guided by outcome analysis, we ascertained a uniform set of parameter thresholds for grading the severity of right heart adaptation in PAH. Using these quantitative thresholds, we, then, validated the recently reported REVEAL-echo score (AUC 0.68, p < 0.001). This study proposes a consistent echocardiographic grading system for right heart adaptation in PAH guided by outcome analysis.

Real-world walking behaviors are associated with early-stage heart failure: a Project Baseline Health Study.

BACKGROUND: Data collected via wearables may complement in-clinic assessments to monitor subclinical heart failure (HF). OBJECTIVES: Evaluate the association of sensor-based digital walking measures with HF stage and characterize their correlation with in-clinic measures of physical performance, cardiac function and participant reported outcomes (PROs) in individuals with early HF. METHODS: The analyzable cohort included participants from the Project Baseline Health Study (PBHS) with HF stage 0, A, or B, or adaptive remodeling phenotype (without risk factors but with mild echocardiographic change, termed RF-/ECHO+) (based on available first-visit in-clinic test and echocardiogram results) and with sufficient sensor data. We computed daily values per participant for 18 digital walking measures, comparing HF subgroups vs stage 0 using multinomial logistic regression and characterizing associations with in-clinic measures and PROs with Spearman's correlation coefficients, adjusting all analyses for confounders. RESULTS: In the analyzable cohort (N=1265; 50.6% of the PBHS cohort), one standard deviation decreases in 17/18 walking measures were associated with greater likelihood for stage-B HF (multivariable-adjusted odds ratios [ORs] vs stage 0 ranging from 1.18-2.10), or A (ORs vs stage 0, 1.07-1.45), and lower likelihood for RF-/ECHO+ (ORs vs stage 0, 0.80-0.93). Peak 30-minute pace demonstrated the strongest associations with stage B (OR vs stage 0=2.10; 95% CI:1.74-2.53) and A (OR vs stage 0=1.43; 95% CI:1.23-1.66). Decreases in 13/18 measures were associated with greater likelihood for stage-B HF vs stage A. Strength of correlation with physical performance tests, echocardiographic cardiac-remodeling and dysfunction indices and PROs was greatest in stage B, then A, and lowest for 0. CONCLUSIONS: Digital measures of walking captured by wearable sensors could complement clinic-based testing to identify and monitor pre-symptomatic HF.

Smartphone-Based Recognition of Heart Failure by Means of Microelectromechanical Sensors.

BACKGROUND: Heart failure (HF) is the leading cause of hospitalization in individuals over 65 years of age. Identifying noninvasive methods to detect HF may address the epidemic of HF. Seismocardiography which measures cardiac vibrations transmitted to the chest wall has recently emerged as a promising technology to detect HF. OBJECTIVES: In this multicenter study, the authors examined whether seismocardiography using commercially available smartphones can differentiate control subjects from patients with stage C HF. METHODS: Both inpatients and outpatients with HF were enrolled from Finland and the United States. Inpatients with HF were assessed within 2 days of admission, and outpatients were assessed in the ambulatory setting. In a prespecified pooled data analysis, algorithms were derived using logistic regression and then validated using a bootstrap aggregation method. RESULTS: A total of 217 participants with HF (174 inpatients and 172 outpatients) and 786 control subjects from cardiovascular clinics were enrolled. The mean age of participants with acute HF was 64 ± 13 years, 64.9% were male, left ventricular ejection fraction was 39% ± 15%, and median N-terminal pro-B-type natriuretic peptide was 5,778 ng/L (Q1-Q3: 1,933-6,703). The majority (74%) of participants with HF had reduced EF, and 38% had atrial fibrillation. Across both HF cohorts, the algorithms had an area under the receiver operating characteristic curve of 0.95 with a sensitivity of 85%, specificity of 90%, and accuracy of 89% for the detection of HF, with a decision threshold of 0.5. The positive and negative likelihood ratios were 8.50 and 0.17, respectively. The accuracy of the algorithms was not significantly different in subgroups based on age, sex, body mass index, and atrial fibrillation. CONCLUSIONS: Smartphone-based assessment of cardiac function using seismocardiography is feasible and differentiates patients with HF from control subjects with high diagnostic accuracy. (Recognition of Heart Failure With Micro Electro-mechanical Sensors FI; NCT04444583; Recognition of Heart Failure With Micro Electro-mechanical Sensors [NCT04378179]; Detection of Coronary Artery Disease With Micro Electro-mechanical Sensors; NCT04290091).

Deep Learning-Derived Myocardial Strain.

BACKGROUND: Echocardiographic strain measurements require extensive operator experience and have significant intervendor variability. Creating an automated, open-source, vendor-agnostic method to retrospectively measure global longitudinal strain (GLS) from standard echocardiography B-mode images would greatly improve post hoc research applications and may streamline patient analyses. OBJECTIVES: This study was seeking to develop an automated deep learning strain (DLS) analysis pipeline and validate its performance across multiple applications and populations. METHODS: Interobserver/-vendor variation of traditional GLS, and simulated effects of variation in contour on speckle-tracking measurements were assessed. The DLS pipeline was designed to take semantic segmentation results from EchoNet-Dynamic and derive longitudinal strain by calculating change in the length of the left ventricular endocardial contour. DLS was evaluated for agreement with GLS on a large external dataset and applied across a range of conditions that result in cardiac hypertrophy. RESULTS: In patients scanned by 2 sonographers using 2 vendors, GLS had an intraclass correlation of 0.29 (95% CI: -0.01 to 0.53, P = 0.03) between vendor measurements and 0.63 (95% CI: 0.48-0.74, P < 0.001) between sonographers. With minor changes in initial input contour, step-wise pixel shifts resulted in a mean absolute error of 3.48% and proportional strain difference of 13.52% by a 6-pixel shift. In external validation, DLS maintained moderate agreement with 2-dimensional GLS (intraclass correlation coefficient [ICC]: 0.56, P = 0.002) with a bias of -3.31% (limits of agreement: -11.65% to 5.02%). The DLS method showed differences (P < 0.0001) between populations with cardiac hypertrophy and had moderate agreement in a patient population of advanced cardiac amyloidosis: ICC was 0.64 (95% CI: 0.53-0.72), P < 0.001, with a bias of 0.57%, limits of agreement of -4.87% to 6.01% vs 2-dimensional GLS. CONCLUSIONS: The open-source DLS provides lower variation than human measurements and similar quantitative results. The method is rapid, consistent, vendor-agnostic, publicly released, and applicable across a wide range of imaging qualities.

Quantifying assumptions underlying peak oxygen consumption equations across the body mass spectrum.

The goal of this study is to quantify the assumptions associated with the Wasserman-Hansen (WH) and Fitness Registry and the Importance of Exercise: A National Database (FRIEND) predictive peak oxygen consumption (pVO2) equations across body mass index (BMI). Assumptions in pVO2 for both equations were first determined using a simulation and then evaluated using exercise data from the Stanford Exercise Testing registry. We calculated percent-predicted VO2 (ppVO2) values for both equations and compared them using the Bland-Altman method. Assumptions associated with pVO2 across BMI categories were quantified by comparing the slopes of age-adjusted VO2 ratios (pVO2/pre-exercise VO2) and ppVO2 values for different BMI categories. The simulation revealed lower predicted fitness among adults with obesity using the FRIEND equation compared to the WH equations. In the clinical cohort, we evaluated 2471 patients (56.9% male, 22% with BMI >30 kg/m2, pVO2 26.8 mlO2/kg/min). The Bland-Altman plot revealed an average relative difference of -1.7% (95% CI: -2.1 to -1.2%) between WH and FRIEND ppVO2 values with greater differences among those with obesity. Analysis of the VO2 ratio to ppVO2 slopes across the BMI spectrum confirmed the assumption of lower fitness in those with obesity, and this trend was more pronounced using the FRIEND equation. Peak VO2 estimations between the WH and FRIEND equations differed significantly among individuals with obesity. The FRIEND equation resulted in a greater attributable reduction in pVO2 associated with obesity relative to the WH equations. The outlined relationships between BMI and predicted VO2 may better inform the clinical interpretation of ppVO2 values during cardiopulmonary exercise test evaluations.

Relationship between body mass index and cardiometabolic health in a multi-ethnic population: A project baseline health study.

Objective: Obesity is associated with a higher risk of cardiovascular disease. Understanding the associations between comprehensive health parameters and body mass index (BMI) may lead to targeted prevention efforts. Methods: Project Baseline Health Study (PBHS) participants were divided into six BMI categories: underweight (BMI <18.5 kg/m2), normal weight (BMI 18.5-24.9 kg/m2), overweight (BMI 25-29.9 kg/m2), class I obesity (30-34.9 kg/m2), class II obesity (35-39.9 kg/m2), and class III obesity (BMI ≥40 kg/m2). Demographic, cardiometabolic, mental health, and physical health parameters were compared across BMI categories, and multivariable logistic regression models were fit to evaluate associations. Results: A total of 2,493 PBHS participants were evaluated. The mean age was 50±17.2 years; 55 % were female, 12 % Hispanic, 16 % Black, and 10 % Asian. The average BMI was 28.4 kg/m2±6.9. The distribution of BMI by age group was comparable to the 2017-2018 National Health and Nutrition Examination Survey (NHANES) dataset. The obesity categories had higher proportions of participants with CAC scores >0, hypertension, diabetes, lower HDL-C, lower vitamin D, higher triglycerides, higher hsCRP, lower mean step counts, higher mean PHQ-9 scores, and higher mean GAD-7 scores. Conclusion: We identified associations of cardiometabolic and mental health characteristics with BMI, thereby providing a deeper understanding of cardiovascular health across BMI.

Being fit in the COVID-19 era and future epidemics prevention: Importance of cardiopulmonary exercise test in fitness evaluation.

Endurance and resistance physical activity have been shown to stimulate the production of immunoglobulins and boost the levels of anti-inflammatory cytokines, natural killer cells, and neutrophils in the bloodstream, thereby strengthening the ability of the innate immune system to protect against diseases and infections. Coronavirus disease 19 (COVID-19) greatly impacted people's cardiorespiratory fitness (CRF) and health worldwide. Cardiopulmonary exercise testing (CPET) remains valuable in assessing physical condition, predicting illness severity, and guiding interventions and treatments. In this narrative review, we summarize the connections and impact of COVID-19 on CRF levels and its implications on the disease's progression, prognosis, and mortality. We also emphasize the significant contribution of CPET in both clinical evaluations of recovering COVID-19 patients and scientific investigations focused on comprehending the enduring health consequences of SARS-CoV-2 infection.

Improving Reporting of Exercise Capacity Across Age Ranges Using Novel Workload Reference Equations.

Exercise capacity (EC) is an important predictor of survival in the general population and in subjects with cardiopulmonary disease. Despite its relevance, considering the percent-predicted workload (%pWL) given by current equations may overestimate EC in older adults. Therefore, to improve the reporting of EC in clinical practice, our main objective was to develop workload reference equations (pWL) that better reflect the relation between workload and age. Using the Fitness Registry and the Importance of Exercise National Database (FRIEND), we analyzed a reference group of 6,966 apparently healthy participants and 1,060 participants with heart failure who underwent graded treadmill cardiopulmonary exercise testing. For the first group, the mean age was 44 years (18 to 79); 56.5% of participants were males and 15.4% had obesity. Peak oxygen consumption was 11.6 ± 3.0 METs in males and 8.5 ± 2.4 METs in females. After partition analysis, we first developed sex-specific pWL equations to allow comparisons to a healthy weight reference. For males, pWL (METs) = 14.1-0.9×10-3×age2 and 11.5-0.87×10-3×age2 for females. We used those equations as denominators of %pWL, and based on their distribution, we determined thresholds for EC classification, with average EC defined by the range corresponding to 85% to 115%pWL. Compared with %pWL using current equations, the new equations yielded better-calibrated %pWL across different age ranges. We also derived body mass index-adjusted pWL equations that better assessed EC in subjects with heart failure. In conclusion, the novel pWL equations have the potential to impact the report of EC in practice.

Clinical and biochemical predictors of longitudinal changes in left atrial structure and function: A general population study.

PURPOSE: There is a need for better understanding the factors that modulate left atrial (LA) dysfunction. Therefore, we determined associations of clinical and biochemical biomarkers with serial changes in echocardiographic indexes of LA function in the general population. METHODS: We measured LA maximal and minimal volume indexes (LAVImax and LAVImin) by echocardiography and LA reservoir strain (LARS) by two-dimensional speckle-tracking in 627 participants (mean age 50.8 years, 51.2% women) at baseline and after 4.8 years. RESULTS: During follow-up, LARS decreased significantly in men (-.90%, P = .033) but not in women (-.23%, P = .60). In stepwise regression analysis, stronger decrease in LARS over time was associated with male sex, a higher age, body mass index (BMI), mean arterial pressure (MAP) and serum insulin at baseline and with a greater increase in BMI and MAP over time (P ≤ .018). Similarly, an increased risk of developing or retaining abnormal LARS was observed in older participants, in subjects with a higher baseline BMI, MAP, heart rate (HR), troponin T and ΔMAP, and in those who used ß-blockers at baseline. Both LAVImax and LAVImin increased significantly over time (P ≤ .0007). This increase was associated with a higher baseline age, pulse pressure and a lower HR at baseline and a greater increase in pulse pressure over time (P ≤ .029). Higher serum insulin and D-dimer were independently associated with a stronger increase in LAVImin (P ≤ .0034). CONCLUSION: Subclinical worsening in LA dysfunction was associated with older age, hypertension, obesity, insulin resistance and troponin T levels. Cardiovascular risk management strategies may delay LA deterioration.

Genetic architecture of cardiac dynamic flow volumes.

Cardiac blood flow is a critical determinant of human health. However, the definition of its genetic architecture is limited by the technical challenge of capturing dynamic flow volumes from cardiac imaging at scale. We present DeepFlow, a deep-learning system to extract cardiac flow and volumes from phase-contrast cardiac magnetic resonance imaging. A mixed-linear model applied to 37,653 individuals from the UK Biobank reveals genome-wide significant associations across cardiac dynamic flow volumes spanning from aortic forward velocity to aortic regurgitation fraction. Mendelian randomization reveals a causal role for aortic root size in aortic valve regurgitation. Among the most significant contributing variants, localizing genes (near ELN, PRDM6 and ADAMTS7) are implicated in connective tissue and blood pressure pathways. Here we show that DeepFlow cardiac flow phenotyping at scale, combined with genotyping data, reinforces the contribution of connective tissue genes, blood pressure and root size to aortic valve function.

High and intermediate risk pulmonary embolism in the ICU.

Pulmonary embolism (PE) is a common and important medical emergency, encountered by clinicians across all acute care specialties. PE is a relatively uncommon cause of direct admission to the intensive care unit (ICU), but these patients are at high risk of death. More commonly, patients admitted to ICU develop PE as a complication of an unrelated acute illness. This paper reviews the epidemiology, diagnosis, risk stratification, and particularly the management of PE from a critical care perspective. Issues around prevention, anticoagulation, fibrinolysis, catheter-based techniques, surgical embolectomy, and extracorporeal support are discussed.

Quantitative metrics of the LV trabeculated layer by cardiac CT and cardiac MRI in patients with suspected noncompaction cardiomyopathy.

OBJECTIVES: To compare cardiac computed tomography (CCT) and cardiac magnetic resonance (CMR) for the quantitative assessment of the left ventricular (LV) trabeculated layer in patients with suspected noncompaction cardiomyopathy (NCCM). MATERIALS AND METHODS: Subjects with LV excessive trabeculation who underwent both CMR and CCT imaging as part of the prospective international multicenter NONCOMPACT clinical study were included. For each subject, short-axis CCT and CMR slices were matched. Four quantitative metrics were estimated: 1D noncompacted-to-compacted ratio (NCC), trabecular-to-myocardial area ratio (TMA), trabecular-to-endocardial cavity area ratio (TCA), and trabecular-to-myocardial volume ratio (TMV). In 20 subjects, end-diastolic and mid-diastolic CCT images were compared for the quantification of the trabeculated layer. Relationships between the metrics were investigated using linear regression models and Bland-Altman analyses. RESULTS: Forty-eight subjects (49.9 ± 12.8 years; 28 female) were included in this study. NCC was moderately correlated (r = 0.62), TMA and TMV were strongly correlated (r = 0.78 and 0.78), and TCA had excellent correlation (r = 0.92) between CMR and CCT, with an underestimation bias from CCT of 0.3 units, and 5.1, 4.8, and 5.4 percent-points for the 4 metrics, respectively. TMA, TCA, and TMV had excellent correlations (r = 0.93, 0.96, 0.94) and low biases (- 3.8, 0.8, - 3.8 percent-points) between the end-diastolic and mid-diastolic CCT images. CONCLUSIONS: TMA, TCA, and TMV metrics of the LV trabeculated layer in patients with suspected NCCM demonstrated high concordance between CCT and CMR images. TMA and TCA were highly reproducible and demonstrated minimal differences between mid-diastolic and end-diastolic CCT images. CLINICAL RELEVANCE STATEMENT: The results indicate similarity of CCT to CMR for quantifying the LV trabeculated layer, and the small differences in quantification between end-diastole and mid-diastole demonstrate the potential for quantifying the LV trabeculated layer from clinically performed coronary CT angiograms. KEY POINTS: • Data on cardiac CT for quantifying the left ventricular trabeculated layer are limited. • Cardiac CT yielded highly reproducible metrics of the left ventricular trabeculated layer that correlated well with metrics defined by cardiac MR. • Cardiac CT appears to be equivalent to cardiac MR for the quantification of the left ventricular trabeculated layer.

The Echocardiographic Evaluation of the Right Heart: Current and Future Advances.

PURPOSE OF REVIEW: To discuss physiologic and methodologic advances in the echocardiographic assessment of right heart (RH) function, including the emergence of artificial intelligence (AI) and point-of-care ultrasound. RECENT FINDINGS: Recent studies have highlighted the prognostic value of right ventricular (RV) longitudinal strain, RV end-systolic dimensions, and right atrial (RA) size and function in pulmonary hypertension and heart failure. While RA pressure is a central marker of right heart diastolic function, the recent emphasis on venous excess imaging (VExUS) has provided granularity to the systemic consequences of RH failure. Several methodological advances are also changing the landscape of RH imaging including post-processing 3D software to delineate the non-longitudinal (radial, anteroposterior, and circumferential) components of RV function, as well as AI segmentation- and non-segmentation-based quantification. Together with recent guidelines and advances in AI technology, the field is shifting from specific RV functional metrics to integrated RH disease-specific phenotypes. A modern echocardiographic evaluation of RH function should focus on the entire cardiopulmonary venous unit-from the venous to the pulmonary arterial system. Together, a multi-parametric approach, guided by physiology and AI algorithms, will help define novel integrated RH profiles for improved disease detection and monitoring.

Feature-based clustering of the left ventricular strain curve for cardiovascular risk stratification in the general population.

Objective: Identifying individuals with subclinical cardiovascular (CV) disease could improve monitoring and risk stratification. While peak left ventricular (LV) systolic strain has emerged as a strong prognostic factor, few studies have analyzed the whole temporal profiles of the deformation curves during the complete cardiac cycle. Therefore, in this longitudinal study, we applied an unsupervised machine learning approach based on time-series-derived features from the LV strain curve to identify distinct strain phenogroups that might be related to the risk of adverse cardiovascular events in the general population. Method: We prospectively studied 1,185 community-dwelling individuals (mean age, 53.2 years; 51.3% women), in whom we acquired clinical and echocardiographic data including LV strain traces at baseline and collected adverse events on average 9.1 years later. A Gaussian Mixture Model (GMM) was applied to features derived from LV strain curves, including the slopes during systole, early and late diastole, peak strain, and the duration and height of diastasis. We evaluated the performance of the model using the clinical characteristics of the participants and the incidence of adverse events in the training dataset. To ascertain the validity of the trained model, we used an additional community-based cohort (n = 545) as external validation cohort. Results: The most appropriate number of clusters to separate the LV strain curves was four. In clusters 1 and 2, we observed differences in age and heart rate distributions, but they had similarly low prevalence of CV risk factors. Cluster 4 had the worst combination of CV risk factors, and a higher prevalence of LV hypertrophy and diastolic dysfunction than in other clusters. In cluster 3, the reported values were in between those of strain clusters 2 and 4. Adjusting for traditional covariables, we observed that clusters 3 and 4 had a significantly higher risk for CV (28% and 20%, P ≤ 0.038) and cardiac (57% and 43%, P ≤ 0.024) adverse events. Using SHAP values we observed that the features that incorporate temporal information, such as the slope during systole and early diastole, had a higher impact on the model's decision than peak LV systolic strain. Conclusion: Employing a GMM on features derived from the raw LV strain curves, we extracted clinically significant phenogroups which could provide additive prognostic information over the peak LV strain.

Segmenting computed tomograms for cardiac ablation using machine learning leveraged by domain knowledge encoding.

Background: Segmentation of computed tomography (CT) is important for many clinical procedures including personalized cardiac ablation for the management of cardiac arrhythmias. While segmentation can be automated by machine learning (ML), it is limited by the need for large, labeled training data that may be difficult to obtain. We set out to combine ML of cardiac CT with domain knowledge, which reduces the need for large training datasets by encoding cardiac geometry, which we then tested in independent datasets and in a prospective study of atrial fibrillation (AF) ablation. Methods: We mathematically represented atrial anatomy with simple geometric shapes and derived a model to parse cardiac structures in a small set of N = 6 digital hearts. The model, termed "virtual dissection," was used to train ML to segment cardiac CT in N = 20 patients, then tested in independent datasets and in a prospective study. Results: In independent test cohorts (N = 160) from 2 Institutions with different CT scanners, atrial structures were accurately segmented with Dice scores of 96.7% in internal (IQR: 95.3%-97.7%) and 93.5% in external (IQR: 91.9%-94.7%) test data, with good agreement with experts (r = 0.99; p < 0.0001). In a prospective study of 42 patients at ablation, this approach reduced segmentation time by 85% (2.3 ± 0.8 vs. 15.0 ± 6.9 min, p < 0.0001), yet provided similar Dice scores to experts (93.9% (IQR: 93.0%-94.6%) vs. 94.4% (IQR: 92.8%-95.7%), p = NS). Conclusions: Encoding cardiac geometry using mathematical models greatly accelerated training of ML to segment CT, reducing the need for large training sets while retaining accuracy in independent test data. Combining ML with domain knowledge may have broad applications.