Use of Artificial Intelligence in Improving Outcomes in Heart Disease: A Scientific Statement From the American Heart Association.

A major focus of academia, industry, and global governmental agencies is to develop and apply artificial intelligence and other advanced analytical tools to transform health care delivery. The American Heart Association supports the creation of tools and services that would further the science and practice of precision medicine by enabling more precise approaches to cardiovascular and stroke research, prevention, and care of individuals and populations. Nevertheless, several challenges exist, and few artificial intelligence tools have been shown to improve cardiovascular and stroke care sufficiently to be widely adopted. This scientific statement outlines the current state of the art on the use of artificial intelligence algorithms and data science in the diagnosis, classification, and treatment of cardiovascular disease. It also sets out to advance this mission, focusing on how digital tools and, in particular, artificial intelligence may provide clinical and mechanistic insights, address bias in clinical studies, and facilitate education and implementation science to improve cardiovascular and stroke outcomes. Last, a key objective of this scientific statement is to further the field by identifying best practices, gaps, and challenges for interested stakeholders.

Recommendations for risk allele evidence curation, classification, and reporting from the ClinGen Low Penetrance/Risk Allele Working Group.

PURPOSE: Genetic variants at the low end of the penetrance spectrum have historically been challenging to interpret because their high population frequencies exceed the disease prevalence of the associated condition, leading to a lack of clear segregation between the variant and disease. There is currently substantial variation in the classification of these variants, and no formal classification framework has been widely adopted. The Clinical Genome Resource Low Penetrance/Risk Allele Working Group was formed to address these challenges and promote harmonization within the clinical community. METHODS: The work presented here is the product of internal and community Likert-scaled surveys in combination with expert consensus within the Working Group. RESULTS: We formally recognize risk alleles and low-penetrance variants as distinct variant classes from those causing highly penetrant disease that require special considerations regarding their clinical classification and reporting. First, we provide a preferred terminology for these variants. Second, we focus on risk alleles and detail considerations for reviewing relevant studies and present a framework for the classification these variants. Finally, we discuss considerations for clinical reporting of risk alleles. CONCLUSION: These recommendations support harmonized interpretation, classification, and reporting of variants at the low end of the penetrance spectrum.

Implementing evidence-based assertions of clinical actionability in the context of secondary findings: Updates from the ClinGen Actionability Working Group.

PURPOSE: The ClinGen Actionability Working Group (AWG) developed an evidence-based framework to generate actionability reports and scores of gene-condition pairs in the context of secondary findings from genome sequencing. Here we describe the expansion of the framework to include actionability assertions. METHODS: Initial development of the actionability rubric was based on previously scored adult gene-condition pairs and individual expert evaluation. Rubric refinement was iterative and based on evaluation, feedback, and discussion. The final rubric was pragmatically evaluated via integration into actionability assessments for 27 gene-condition pairs. RESULTS: The resulting rubric has a 4-point scale (limited, moderate, strong, and definitive) and uses the highest-scoring outcome-intervention pair of each gene-condition pair to generate a preliminary assertion. During AWG discussions, predefined criteria and factors guide discussion to produce a consensus assertion for a gene-condition pair, which may differ from the preliminary assertion. The AWG has retrospectively generated assertions for all previously scored gene-condition pairs and are prospectively asserting on gene-condition pairs under assessment, having completed over 170 adult and 188 pediatric gene-condition pairs. CONCLUSION: The AWG expanded its framework to provide actionability assertions to enhance the clinical value of their resources and increase their utility as decision aids regarding return of secondary findings.

A Clinical Diagnostic Test for Calcium Release Deficiency Syndrome.

Importance: Sudden death and cardiac arrest frequently occur without explanation, even after a thorough clinical evaluation. Calcium release deficiency syndrome (CRDS), a life-threatening genetic arrhythmia syndrome, is undetectable with standard testing and leads to unexplained cardiac arrest. Objective: To explore the cardiac repolarization response on an electrocardiogram after brief tachycardia and a pause as a clinical diagnostic test for CRDS. Design, Setting, and Participants: An international, multicenter, case-control study including individual cases of CRDS, 3 patient control groups (individuals with suspected supraventricular tachycardia; survivors of unexplained cardiac arrest [UCA]; and individuals with genotype-positive catecholaminergic polymorphic ventricular tachycardia [CPVT]), and genetic mouse models (CRDS, wild type, and CPVT were used to define the cellular mechanism) conducted at 10 centers in 7 countries. Patient tracings were recorded between June 2005 and December 2023, and the analyses were performed from April 2023 to December 2023. Intervention: Brief tachycardia and a subsequent pause (either spontaneous or mediated through cardiac pacing). Main Outcomes and Measures: Change in QT interval and change in T-wave amplitude (defined as the difference between their absolute values on the postpause sinus beat and the last beat prior to tachycardia). Results: Among 10 case patients with CRDS, 45 control patients with suspected supraventricular tachycardia, 10 control patients who experienced UCA, and 3 control patients with genotype-positive CPVT, the median change in T-wave amplitude on the postpause sinus beat (after brief ventricular tachycardia at ≥150 beats/min) was higher in patients with CRDS (P < .001). The smallest change in T-wave amplitude was 0.250 mV for a CRDS case patient compared with the largest change in T-wave amplitude of 0.160 mV for a control patient, indicating 100% discrimination. Although the median change in QT interval was longer in CRDS cases (P = .002), an overlap between the cases and controls was present. The genetic mouse models recapitulated the findings observed in humans and suggested the repolarization response was secondary to a pathologically large systolic release of calcium from the sarcoplasmic reticulum. Conclusions and Relevance: There is a unique repolarization response on an electrocardiogram after provocation with brief tachycardia and a subsequent pause in CRDS cases and mouse models, which is absent from the controls. If these findings are confirmed in larger studies, this easy to perform maneuver may serve as an effective clinical diagnostic test for CRDS and become an important part of the evaluation of cardiac arrest.

Enhancing the interpretation of genetic observations in KCNQ1 in unselected populations: relevance to secondary findings.

AIMS: Rare variants in the KCNQ1 gene are found in the healthy population to a much greater extent than the prevalence of Long QT Syndrome type 1 (LQTS1). This observation creates challenges in the interpretation of KCNQ1 rare variants that may be identified as secondary findings in whole exome sequencing.This study sought to identify missense variants within sub-domains of the KCNQ1-encoded Kv7.1 potassium channel that would be highly predictive of disease in the context of secondary findings. METHODS AND RESULTS: We established a set of KCNQ1 variants reported in over 3700 patients with diagnosed or suspected LQTS sent for clinical genetic testing and compared the domain-specific location of identified variants to those observed in an unselected population of 140 000 individuals. We identified three regions that showed a significant enrichment of KCNQ1 variants associated with LQTS at an odds ratio (OR) >2: the pore region, and the adjacent 5th (S5) and 6th (S6) transmembrane (TM) regions. An additional segment within the carboxyl terminus of Kv7.1, conserved region 2 (CR2), also showed an increased OR of disease association. Furthermore, the TM spanning S5-Pore-S6 region correlated with a significant increase in cardiac events. CONCLUSION: Rare missense variants with a clear phenotype of LQTS have a high likelihood to be present within the pore and adjacent TM segments (S5-Pore-S6) and a greater tendency to be present within CR2. This data will enhance interpretation of secondary findings within the KCNQ1 gene. Further, our data support a more severe phenotype in LQTS patients with variants within the S5-Pore-S6 region.

Evaluation of gene validity for CPVT and short QT syndrome in sudden arrhythmic death.

AIMS: Catecholaminergic polymorphic ventricular tachycardia (CPVT) and short QT syndrome (SQTS) are inherited arrhythmogenic disorders that can cause sudden death. Numerous genes have been reported to cause these conditions, but evidence supporting these gene-disease relationships varies considerably. To ensure appropriate utilization of genetic information for CPVT and SQTS patients, we applied an evidence-based reappraisal of previously reported genes. METHODS AND RESULTS: Three teams independently curated all published evidence for 11 CPVT and 9 SQTS implicated genes using the ClinGen gene curation framework. The results were reviewed by a Channelopathy Expert Panel who provided the final classifications. Seven genes had definitive to moderate evidence for disease causation in CPVT, with either autosomal dominant (RYR2, CALM1, CALM2, CALM3) or autosomal recessive (CASQ2, TRDN, TECRL) inheritance. Three of the four disputed genes for CPVT (KCNJ2, PKP2, SCN5A) were deemed by the Expert Panel to be reported for phenotypes that were not representative of CPVT, while reported variants in a fourth gene (ANK2) were too common in the population to be disease-causing. For SQTS, only one gene (KCNH2) was classified as definitive, with three others (KCNQ1, KCNJ2, SLC4A3) having strong to moderate evidence. The majority of genetic evidence for SQTS genes was derived from very few variants (five in KCNJ2, two in KCNH2, one in KCNQ1/SLC4A3). CONCLUSIONS: Seven CPVT and four SQTS genes have valid evidence for disease causation and should be included in genetic testing panels. Additional genes associated with conditions that may mimic clinical features of CPVT/SQTS have potential utility for differential diagnosis.

Importance of genetic testing in unexplained cardiac arrest.

AIMS: Genetic testing is recommended in specific inherited heart diseases but its role remains unclear and it is not currently recommended in unexplained cardiac arrest (UCA). We sought to assess the yield and clinical utility of genetic testing in UCA using whole-exome sequencing (WES). METHODS AND RESULTS: Survivors of UCA requiring external defibrillation were included from the Cardiac Arrest Survivor with Preserved Ejection fraction Registry. Whole-exome sequencing was performed, followed by assessment of rare variants in previously reported cardiovascular disease genes. A total of 228 UCA survivors (mean age at arrest 39 ± 13 years) were included. The majority were males (66%) and of European ancestry (81%). Following advanced clinical testing at baseline, the likely aetiology of cardiac arrest was determined in 21/228 (9%) cases. Whole-exome sequencing identified a pathogenic or likely pathogenic (P/LP) variant in 23/228 (10%) of UCA survivors overall, increasing the proportion of 'explained' cases from 9% only following phenotyping to 18% when combining phenotyping with WES. Notably, 13 (57%) of the 23 P/LP variants identified were located in genes associated with cardiomyopathy, in the absence of a diagnosis of cardiomyopathy at the time of arrest. CONCLUSIONS: Genetic testing identifies a disease-causing variant in 10% of apparent UCA survivors. The majority of disease-causing variants was located in cardiomyopathy-associated genes, highlighting the arrhythmogenic potential of such variants in the absence of an overt cardiomyopathy diagnosis. The present study supports the use of genetic testing including assessment of arrhythmia and cardiomyopathy genes in survivors of UCA.

Endocrinopathies mimicking gene negative long QT syndrome.

Ventricular repolarisation can be influenced by hormonal milieu which may mimic long QT syndrome. We describe a series of patients referred for genetic testing for diagnosed long QT syndrome where a detailed clinical workup demonstrated endocrinopathies as the cause of presumed "gene negative" long QT syndrome and QT prolongation.

An International, Multicentered, Evidence-Based Reappraisal of Genes Reported to Cause Congenital Long QT Syndrome.

BACKGROUND: Long QT syndrome (LQTS) is the first described and most common inherited arrhythmia. Over the last 25 years, multiple genes have been reported to cause this condition and are routinely tested in patients. Because of dramatic changes in our understanding of human genetic variation, reappraisal of reported genetic causes for LQTS is required. METHODS: Utilizing an evidence-based framework, 3 gene curation teams blinded to each other's work scored the level of evidence for 17 genes reported to cause LQTS. A Clinical Domain Channelopathy Working Group provided a final classification of these genes for causation of LQTS after assessment of the evidence scored by the independent curation teams. RESULTS: Of 17 genes reported as being causative for LQTS, 9 (AKAP9, ANK2, CAV3, KCNE1, KCNE2, KCNJ2, KCNJ5, SCN4B, SNTA1) were classified as having limited or disputed evidence as LQTS-causative genes. Only 3 genes (KCNQ1, KCNH2, SCN5A) were curated as definitive genes for typical LQTS. Another 4 genes (CALM1, CALM2, CALM3, TRDN) were found to have strong or definitive evidence for causality in LQTS with atypical features, including neonatal atrioventricular block. The remaining gene (CACNA1C) had moderate level evidence for causing LQTS. CONCLUSIONS: More than half of the genes reported as causing LQTS have limited or disputed evidence to support their disease causation. Genetic variants in these genes should not be used for clinical decision-making, unless accompanied by new and sufficient genetic evidence. The findings of insufficient evidence to support gene-disease associations may extend to other disciplines of medicine and warrants a contemporary evidence-based evaluation for previously reported disease-causing genes to ensure their appropriate use in precision medicine.

An International Multicenter Evaluation of Type 5 Long QT Syndrome: A Low Penetrant Primary Arrhythmic Condition.

BACKGROUND: Insight into type 5 long QT syndrome (LQT5) has been limited to case reports and small family series. Improved understanding of the clinical phenotype and genetic features associated with rare KCNE1 variants implicated in LQT5 was sought through an international multicenter collaboration. METHODS: Patients with either presumed autosomal dominant LQT5 (N = 229) or the recessive Type 2 Jervell and Lange-Nielsen syndrome (N = 19) were enrolled from 22 genetic arrhythmia clinics and 4 registries from 9 countries. KCNE1 variants were evaluated for ECG penetrance (defined as QTc >460 ms on presenting ECG) and genotype-phenotype segregation. Multivariable Cox regression was used to compare the associations between clinical and genetic variables with a composite primary outcome of definite arrhythmic events, including appropriate implantable cardioverter-defibrillator shocks, aborted cardiac arrest, and sudden cardiac death. RESULTS: A total of 32 distinct KCNE1 rare variants were identified in 89 probands and 140 genotype positive family members with presumed LQT5 and an additional 19 Type 2 Jervell and Lange-Nielsen syndrome patients. Among presumed LQT5 patients, the mean QTc on presenting ECG was significantly longer in probands (476.9±38.6 ms) compared with genotype positive family members (441.8±30.9 ms, P<0.001). ECG penetrance for heterozygous genotype positive family members was 20.7% (29/140). A definite arrhythmic event was experienced in 16.9% (15/89) of heterozygous probands in comparison with 1.4% (2/140) of family members (adjusted hazard ratio [HR] 11.6 [95% CI, 2.6-52.2]; P=0.001). Event incidence did not differ significantly for Type 2 Jervell and Lange-Nielsen syndrome patients relative to the overall heterozygous cohort (10.5% [2/19]; HR 1.7 [95% CI, 0.3-10.8], P=0.590). The cumulative prevalence of the 32 KCNE1 variants in the Genome Aggregation Database, which is a human database of exome and genome sequencing data from now over 140 000 individuals, was 238-fold greater than the anticipated prevalence of all LQT5 combined (0.238% vs 0.001%). CONCLUSIONS: The present study suggests that putative/confirmed loss-of-function KCNE1 variants predispose to QT prolongation, however, the low ECG penetrance observed suggests they do not manifest clinically in the majority of individuals, aligning with the mild phenotype observed for Type 2 Jervell and Lange-Nielsen syndrome patients.

An International Multicenter Evaluation of Inheritance Patterns, Arrhythmic Risks, and Underlying Mechanisms of CASQ2-Catecholaminergic Polymorphic Ventricular Tachycardia.

BACKGROUND: Genetic variants in calsequestrin-2 (CASQ2) cause an autosomal recessive form of catecholaminergic polymorphic ventricular tachycardia (CPVT), although isolated reports have identified arrhythmic phenotypes among heterozygotes. Improved insight into the inheritance patterns, arrhythmic risks, and molecular mechanisms of CASQ2-CPVT was sought through an international multicenter collaboration. METHODS: Genotype-phenotype segregation in CASQ2-CPVT families was assessed, and the impact of genotype on arrhythmic risk was evaluated using Cox regression models. Putative dominant CASQ2 missense variants and the established recessive CASQ2-p.R33Q variant were evaluated using oligomerization assays and their locations mapped to a recent CASQ2 filament structure. RESULTS: A total of 112 individuals, including 36 CPVT probands (24 homozygotes/compound heterozygotes and 12 heterozygotes) and 76 family members possessing at least 1 presumed pathogenic CASQ2 variant, were identified. Among CASQ2 homozygotes and compound heterozygotes, clinical penetrance was 97.1% and 26 of 34 (76.5%) individuals had experienced a potentially fatal arrhythmic event with a median age of onset of 7 years (95% CI, 6-11). Fifty-one of 66 CASQ2 heterozygous family members had undergone clinical evaluation, and 17 of 51 (33.3%) met diagnostic criteria for CPVT. Relative to CASQ2 heterozygotes, CASQ2 homozygote/compound heterozygote genotype status in probands was associated with a 3.2-fold (95% CI, 1.3-8.0; P=0.013) increased hazard of a composite of cardiac syncope, aborted cardiac arrest, and sudden cardiac death, but a 38.8-fold (95% CI, 5.6-269.1; P<0.001) increased hazard in genotype-positive family members. In vitro turbidity assays revealed that p.R33Q and all 6 candidate dominant CASQ2 missense variants evaluated exhibited filamentation defects, but only p.R33Q convincingly failed to dimerize. Structural analysis revealed that 3 of these 6 putative dominant negative missense variants localized to an electronegative pocket considered critical for back-to-back binding of dimers. CONCLUSIONS: This international multicenter study of CASQ2-CPVT redefines its heritability and confirms that pathogenic heterozygous CASQ2 variants may manifest with a CPVT phenotype, indicating a need to clinically screen these individuals. A dominant mode of inheritance appears intrinsic to certain missense variants because of their location and function within the CASQ2 filament structure.

Novel cases of pediatric sudden cardiac death secondary to TRDN mutations presenting as long QT syndrome at rest and catecholaminergic polymorphic ventricular tachycardia during exercise: The TRDN arrhythmia syndrome.

TRDN mutations cause catecholaminergic polymorphic ventricular tachycardia (CPVT) but may present with abnormal electrocardiogram (ECG) findings provoking a diagnosis of long QT syndrome (LQTS). We report two novel cases of sudden cardiac death in children due to mutations of TRDN, providing further insight into this rare and aggressive inherited arrhythmia syndrome. Whole exome sequencing (WES) was performed in two unrelated children who experienced cardiac arrest during exercise and were negative for targeted testing of LQTS. WES identified a novel homozygous splice-site mutation in both patients, denoted c.22+1G>T, absent from gnomAD and suggesting a founder variant in the Iranian population. We now summarize the genetic architecture of all reported TRDN-related patients, including 27 patients from 21 families. The average age-onset was 30 months (range 1-10) for all cases. Adrenergic-mediated cardiac events were common, occurring in 23 of 27 cases (85%). LQTS was diagnosed in 10 cases (37%), CPVT in 10 (37%) cases, and in 7 cases. No phenotypic diagnosis was provided. Five cases (15%) had evidence for associated skeletal myopathy. Four missense TRDN variants (24%) were observed in diseased cases, while the remaining variants reflect putative loss-of-function (LOF) mutations. No disease phenotype was reported in 26 heterozygous carriers. In conclusion, TRDN mutations cause a rare autosomal recessive arrhythmia syndrome presenting with adrenergic-mediated arrhythmic events, but with ECG abnormalities leading to a diagnosis of LQTS in a proportion of cases. Heterozygous carriers are free of disease manifestations.

Reappraisal of Reported Genes for Sudden Arrhythmic Death: Evidence-Based Evaluation of Gene Validity for Brugada Syndrome.

BACKGROUND: Implicit in the genetic evaluation of patients with suspected genetic diseases is the assumption that the genes evaluated are causative for the disease based on robust scientific and statistical evidence. However, in the past 20 years, considerable variability has existed in the study design and quality of evidence supporting reported gene-disease associations, raising concerns of the validity of many published disease-causing genes. Brugada syndrome (BrS) is an arrhythmia syndrome with a risk of sudden death. More than 20 genes have been reported to cause BrS and are assessed routinely on genetic testing panels in the absence of a systematic, evidence-based evaluation of the evidence supporting the causality of these genes. METHODS: We evaluated the clinical validity of genes tested by diagnostic laboratories for BrS by assembling 3 gene curation teams. Using an evidence-based semiquantitative scoring system of genetic and experimental evidence for gene-disease associations, curation teams independently classified genes as demonstrating limited, moderate, strong, or definitive evidence for disease causation in BrS. The classification of curator teams was reviewed by a clinical domain expert panel that could modify the classifications based on their independent review and consensus. RESULTS: Of 21 genes curated for clinical validity, biocurators classified only 1 gene ( SCN5A) as definitive evidence, whereas all other genes were classified as limited evidence. After comprehensive review by the clinical domain Expert panel, all 20 genes classified as limited evidence were reclassified as disputed with regard to any assertions of disease causality for BrS. CONCLUSIONS: Our results contest the clinical validity of all but 1 gene clinically tested and reported to be associated with BrS. These findings warrant a systematic, evidence-based evaluation for reported gene-disease associations before use in patient care.

Evaluation of Prolonged QT Interval: Structural Heart Disease Mimicking Long QT Syndrome.

BACKGROUND: In about 20-25% of patients with congenital long QT syndrome (LQTS) a causative pathogenic mutation is not found. The aim of this study was to explore the prevalence of alternative cardiac diagnoses among patients exhibiting prolongation of QT interval with negative genetic testing for LQTS genes. METHODS: We conducted a retrospective analysis of 239 consecutive patients who were evaluated in the inherited arrhythmia clinic at the Toronto General Hospital between July 2013 and December 2015 for possible LQTS. A detailed review of the patients' charts, electrocardiograms, and imaging was carried out. RESULTS: The analysis included 56 gene-negative patients and 61 gene-positive patients. Of the gene-negative group, 25% had structural heart disease compared to only 1.6% of gene-positive patients (P < 0.001). Structural heart disease was more likely if only one abnormal QTc parameter was found in the course of the evaluation (35.2% vs 9.1%, P = 0.01). The most common structural cardiac pathology was bileaflet mitral valve prolapse (8.9%). No gene-positive patient had episodes of nonsustained ventricular tachycardia, compared to seven of the gene-negative patients (0% vs 12.5%, P = 0.005). CONCLUSIONS: Structural pathology was detected in a quarter of gene-negative patients evaluated for possible LQTS. Hence, cardiac imaging and Holter monitoring should be strongly encouraged to rule out structural heart disease in this population.