Applying Artificial Intelligence for Phenotyping of Inherited Arrhythmia Syndromes.

Inherited arrhythmia disorders account for a significant proportion of sudden cardiac death, particularly among young individuals. Recent advances in our understanding of these syndromes have improved patient diagnosis and care, yet certain clinical gaps remain, particularly within case ascertainment, access to genetic testing and risk stratification. Artificial intelligence (AI), specifically machine learning and its subset deep learning, present promising solutions to these challenges. The capacity of AI to process vast amounts of patient data and identify disease patterns differentiates them from traditional methods, which are time and resource intensive. To date, AI models have demonstrated immense potential in condition detection (including asymptomatic/concealed disease) and genotype and phenotype identification, exceeding expert cardiologists in these tasks. Additionally, they have exhibited applicability for general population screening, improving case ascertainment in a set of conditions that are often asymptomatic such as left ventricular dysfunction. Third, models have displayed ability to improve testing protocols, as through model identification of disease and genotype, specific clinical testing (e.g. drug challenges or further diagnostic imaging) can be avoided, reducing health care expenses, speeding diagnosis, and possibly allowing for more incremental or targeted genetic testing approaches. These significant benefits warrant continued investigation of the field, particularly regarding the development and implementation of clinically applicable screening tools. This review summarizes key developments in the field, including studies in Long QT Syndrome, Brugada Syndrome, Hypertrophic Cardiomyopathy, and Arrhythmogenic Cardiomyopathies, and provides direction for effective future AI implementation in clinical practice.

Deep Learning-Augmented ECG Analysis for Screening and Genotype Prediction of Congenital Long QT Syndrome.

Importance: Congenital long QT syndrome (LQTS) is associated with syncope, ventricular arrhythmias, and sudden death. Half of patients with LQTS have a normal or borderline-normal QT interval despite LQTS often being detected by QT prolongation on resting electrocardiography (ECG). Objective: To develop a deep learning-based neural network for identification of LQTS and differentiation of genotypes (LQTS1 and LQTS2) using 12-lead ECG. Design, Setting, and Participants: This diagnostic accuracy study used ECGs from patients with suspected inherited arrhythmia enrolled in the Hearts in Rhythm Organization Registry (HiRO) from August 2012 to December 2021. The internal dataset was derived at 2 sites and an external validation dataset at 4 sites within the HiRO Registry; an additional cross-sectional validation dataset was from the Montreal Heart Institute. The cohort with LQTS included probands and relatives with pathogenic or likely pathogenic variants in KCNQ1 or KCNH2 genes with normal or prolonged corrected QT (QTc) intervals. Exposures: Convolutional neural network (CNN) discrimination between LQTS1, LQTS2, and negative genetic test results. Main Outcomes and Measures: The main outcomes were area under the curve (AUC), F1 scores, and sensitivity for detecting LQTS and differentiating genotypes using a CNN method compared with QTc-based detection. Results: A total of 4521 ECGs from 990 patients (mean [SD] age, 42 [18] years; 589 [59.5%] female) were analyzed. External validation within the national registry (101 patients) demonstrated the CNN's high diagnostic capacity for LQTS detection (AUC, 0.93; 95% CI, 0.89-0.96) and genotype differentiation (AUC, 0.91; 95% CI, 0.86-0.96). This surpassed expert-measured QTc intervals in detecting LQTS (F1 score, 0.84 [95% CI, 0.78-0.90] vs 0.22 [95% CI, 0.13-0.31]; sensitivity, 0.90 [95% CI, 0.86-0.94] vs 0.36 [95% CI, 0.23-0.47]), including in patients with normal or borderline QTc intervals (F1 score, 0.70 [95% CI, 0.40-1.00]; sensitivity, 0.78 [95% CI, 0.53-0.95]). In further validation in a cross-sectional cohort (406 patients) of high-risk patients and genotype-negative controls, the CNN detected LQTS with an AUC of 0.81 (95% CI, 0.80-0.85), which was better than QTc interval-based detection (AUC, 0.74; 95% CI, 0.69-0.78). Conclusions and Relevance: The deep learning model improved detection of congenital LQTS from resting ECGs and allowed for differentiation between the 2 most common genetic subtypes. Broader validation over an unselected general population may support application of this model to patients with suspected LQTS.

A Novel Continuous Left Ventricular Diastolic Function Score Using Machine Learning.

BACKGROUND: Unlike left ventricular (LV) ejection fraction, which provides a precise, reliable, and prognostically valuable measure of systolic function, there is no single analogous measure of LV diastolic function. OBJECTIVES: We aimed to develop a continuous score to grade LV diastolic function using machine learning modeling of echocardiographic data. METHODS: Consecutive echo studies performed at a tertiary-care center between February 1, 2010, and March 31, 2016, were assessed, excluding studies containing features that would interfere with diastolic function assessment as well as studies in which 1 or more parameters within the contemporary diastolic function assessment algorithm were not reported. Diastolic function was graded based on 2016 American Society of Echocardiography (ASE)/European Association of Cardiovascular Imaging (EACVI) guidelines, excluding indeterminate studies. Machine learning models were trained (support vector machine [SVM], decision tree [DT], XGBoost [XGB], and dense neural network [DNN]) to classify studies within the training set by diastolic dysfunction severity, blinded to the ASE/EACVI classification. The DNN model was retrained to generate a regression model (R-DNN) to predict a continuous LV diastolic function score. RESULTS: A total of 28,986 studies were included; 23,188 studies were used to train the models, and 5,798 studies were used for validation. The models were able to reclassify studies with high agreement to the ASE/EACVI algorithm (SVM, 83%; DT, 100%; XGB, 100%; DNN, 98%). The continuous diastolic function score corresponded well with ASE/EACVI guidelines, with scores of 1.00 ± 0.01 for studies with normal function and 0.74 ± 0.05, 0.51 ± 0.06, and 0.27 ± 0.11 for mild, moderate, and severe diastolic dysfunction, respectively (mean ± 1 SD). A score of <0.91 predicted abnormal diastolic function (area under the receiver operator curve = 0.99), while a score of <0.65 predicted elevated filling pressure (area under the receiver operator curve = 0.99). CONCLUSIONS: Machine learning can assimilate echocardiographic data and generate an automated continuous diastolic function score that corresponds well with current diastolic function grading recommendations.

Impact of the updated diastolic function guidelines in the real world.

BACKGROUND: Echocardiographic assessment of diastolic function is complex but can aid in the diagnosis of heart failure, particularly in patients with preserved ejection fraction. In 2016, the American Society of Echocardiography (ASE) and European Association of Cardiovascular Imaging (EACVI) published an updated algorithm for the evaluation of diastolic function. The objective of our study was to assess its impact on diastolic function assessment in a real-world cohort of echo studies. METHODS: We retrospectively identified 71,727 consecutive transthoracic echo studies performed at a tertiary care center between February 2010 and March 2016 in which diastolic function was reported based on the 2009 ASE Guidelines. We then programmed a software algorithm to assess diastolic function in these echo studies according to the 2016 ASE/EACVI Guidelines. RESULTS: When diastolic function assessment based on the 2009 guidelines was compared to that using the 2016 guidelines, there were significant differences in proportion of studies classified as normal (23% vs. 32%) or indeterminate (43% vs. 36%) function, and mild (23% vs. 23%), moderate (10% vs. 8%), or severe (1% vs. 2%) diastolic dysfunction, with poor agreement between the two methods (Kappa 0.323, 95% CI 0.318-0.328). Furthermore, within the subgroup of studies with preserved ejection fraction and no evidence of myocardial disease, there was significant reclassification from mild diastolic dysfunction to normal diastolic function. CONCLUSION: The updated guidelines result in significant differences in diastolic function interpretation in the real world. Our findings have important implications for the identification of patients with or at risk for heart failure.

Comparison of the age-adjusted and clinical probability-adjusted D-dimer to exclude pulmonary embolism in the ED.

BACKGROUND: Diagnosing pulmonary embolism (PE) in the emergency department (ED) can be challenging because its signs and symptoms are non-specific. OBJECTIVE: We compared the efficacy and safety of using age-adjusted D-dimer interpretation, clinical probability-adjusted D-dimer interpretation and standard D-dimer approach to exclude PE in ED patients. DESIGN/METHODS: We performed a health records review at two emergency departments over a two-year period. We reviewed all cases where patients had a D-dimer ordered to test for PE or underwent CT or VQ scanning for PE. PE was considered to be present during the emergency department visit if PE was diagnosed on CT or VQ (subsegmental level or above), or if the patient was subsequently found to have PE or deep vein thrombosis during the next 30 days. We applied the three D-dimer approaches to the low and moderate probability patients. The primary outcome was exclusion of PE with each rule. Secondary objective was to estimate the negative predictive value (NPV) for each rule. RESULTS: 1163 emergency patients were tested for PE and 1075 patients were eligible for inclusion in our analysis. PE was excluded in 70.4% (95% CI 67.6-73.0%), 80.3% (95% CI 77.9-82.6%) and 68.9%; (95% CI 65.7-71.3%) with the age-adjusted, clinical probability-adjusted and standard D-dimer approach. The NPVs were 99.7% (95% CI 99.0-99.9%), 99.1% (95% CI 98.3-99.5%) and 100% (95% CI 99.4-100.0%) respectively. CONCLUSION: The clinical probability-adjusted rule appears to exclude PE in a greater proportion of patients, with a very small reduction in the negative predictive value.

H3K4 Methylation Dependent and Independent Chromatin Regulation by JHD2 and SET1 in Budding Yeast.

Set1 and Jhd2 regulate the methylation state of histone H3 lysine-4 (H3K4me) through their opposing methyltransferase and demethylase activities in the budding yeast Saccharomyces cerevisiae H3K4me associates with actively transcribed genes and, like both SET1 and JHD2 themselves, is known to regulate gene expression diversely. It remains unclear, however, if Set1 and Jhd2 act solely through H3K4me. Relevantly, Set1 methylates lysine residues in the kinetochore protein Dam1 while genetic studies of the S. pombe SET1 ortholog suggest the existence of non-H3K4 Set1 targets relevant to gene regulation. We interrogated genetic interactions of JHD2 and SET1 with essential genes involved in varied aspects of the transcription cycle. Our findings implicate JHD2 in genetic inhibition of the histone chaperone complexes Spt16-Pob3 (FACT) and Spt6-Spn1 This targeted screen also revealed that JHD2 inhibits the Nrd1-Nab3-Sen1 (NNS) transcription termination complex. We find that while Jhd2's impact on these transcription regulatory complexes likely acts via H3K4me, Set1 governs the roles of FACT and NNS through opposing H3K4-dependent and -independent functions. We also identify diametrically opposing consequences for mutation of H3K4 to alanine or arginine, illuminating that caution must be taken in interpreting histone mutation studies. Unlike FACT and NNS, detailed genetic studies suggest an H3K4me-centric mode of Spt6-Spn1 regulation by JHD2 and SET1 Chromatin immunoprecipitation and transcript quantification experiments show that Jhd2 opposes the positioning of a Spt6-deposited nucleosome near the transcription start site of SER3, a Spt6-Spn1 regulated gene, leading to hyper-induction of SER3 In addition to confirming and extending an emerging role for Jhd2 in the control of nucleosome occupancy near transcription start sites, our findings suggest some of the chromatin regulatory functions of Set1 are independent of H3K4 methylation.

Mitochondrial control through nutritionally regulated global histone H3 lysine-4 demethylation.

Histone demethylation by Jumonji-family proteins is coupled with the decarboxylation of α-ketoglutarate (αKG) to yield succinate, prompting hypotheses that their activities are responsive to levels of these metabolites in the cell. Consistent with this paradigm we show here that the Saccharomyces cerevisiae Jumonji demethylase Jhd2 opposes the accumulation of H3K4me3 in fermenting cells only when they are nutritionally manipulated to contain an elevated αKG/succinate ratio. We also find that Jhd2 opposes H3K4me3 in respiratory cells that do not exhibit such an elevated αKG/succinate ratio. While jhd2∆ caused only limited gene expression defects in fermenting cells, transcript profiling and physiological measurements show that JHD2 restricts mitochondrial respiratory capacity in cells grown in non-fermentable carbon in an H3K4me-dependent manner. In association with these phenotypes, we find that JHD2 limits yeast proliferative capacity under physiologically challenging conditions as measured by both replicative lifespan and colony growth on non-fermentable carbon. JHD2's impact on nutrient response may reflect an ancestral role of its gene family in mediating mitochondrial regulation.