Risk Prediction of Cardiovascular Events by Exploration of Molecular Data with Explainable Artificial Intelligence.

Cardiovascular diseases (CVD) annually take almost 18 million lives worldwide. Most lethal events occur months or years after the initial presentation. Indeed, many patients experience repeated complications or require multiple interventions (recurrent events). Apart from affecting the individual, this leads to high medical costs for society. Personalized treatment strategies aiming at prediction and prevention of recurrent events rely on early diagnosis and precise prognosis. Complementing the traditional environmental and clinical risk factors, multi-omics data provide a holistic view of the patient and disease progression, enabling studies to probe novel angles in risk stratification. Specifically, predictive molecular markers allow insights into regulatory networks, pathways, and mechanisms underlying disease. Moreover, artificial intelligence (AI) represents a powerful, yet adaptive, framework able to recognize complex patterns in large-scale clinical and molecular data with the potential to improve risk prediction. Here, we review the most recent advances in risk prediction of recurrent cardiovascular events, and discuss the value of molecular data and biomarkers for understanding patient risk in a systems biology context. Finally, we introduce explainable AI which may improve clinical decision systems by making predictions transparent to the medical practitioner.

Novel Approaches to Fine-Tune Therapeutic Targeting of Platelets in Atherosclerosis: A Critical Appraisal.

The pathogenesis of atherosclerotic vascular disease is driven by a multitude of risk factors intertwining metabolic and inflammatory pathways. Increasing knowledge about platelet biology sheds light on how platelets take part in these processes from early to later stages of plaque development. Recent insights from experimental studies and mouse models substantiate platelets as initiators and amplifiers in atherogenic leukocyte recruitment. These studies are complemented by results from genetics studies shedding light on novel molecular mechanisms which provide an interesting prospect as novel targets. For instance, experimental studies provide further details how platelet-decorated von Willebrand factor tethered to activated endothelial cells plays a role in atherogenic monocyte recruitment. Novel aspects of platelets as atherogenic inductors of neutrophil extracellular traps and particularities in signaling pathways such as cyclic guanosine monophosphate and the inhibitory adaptor molecule SHB23/LNK associating platelets with atherogenesis are shared. In summary, it was our intention to balance insights from recent experimental data that support a plausible role for platelets in atherogenesis against a paucity of clinical evidence needed to validate this concept in humans.

KCND3 potassium channel gene variant confers susceptibility to electrocardiographic early repolarization pattern.

BACKGROUNDThe presence of an early repolarization pattern (ERP) on the surface ECG is associated with risk of ventricular fibrillation and sudden cardiac death. Family studies have shown that ERP is a highly heritable trait, but molecular genetic determinants are unknown.METHODSTo identify genetic susceptibility loci for ERP, we performed a GWAS and meta-analysis in 2,181 cases and 23,641 controls of European ancestry.RESULTSWe identified a genome-wide significant (P < 5 × 10-8) locus in the potassium voltage-gated channel subfamily D member 3 (KCND3) gene that was successfully replicated in additional 1,124 cases and 12,510 controls. A subsequent joint meta-analysis of the discovery and replication cohorts identified rs1545300 as the lead SNP at the KCND3 locus (OR 0.82 per minor T allele, P = 7.7 × 10-12) but did not reveal additional loci. Colocalization analyses indicate causal effects of KCND3 gene expression levels on ERP in both cardiac left ventricle and tibial artery.CONCLUSIONSIn this study, we identified for the first time to our knowledge a genome-wide significant association of a genetic variant with ERP. Our findings of a locus in the KCND3 gene provide insights not only into the genetic determinants but also into the pathophysiological mechanism of ERP, discovering a promising candidate for functional studies.FUNDINGThis project was funded by the German Center for Cardiovascular Research (DZHK Shared Expertise SE081 - STATS). For detailed funding information per study, see the Supplemental Acknowledgments.

Druggability of Coronary Artery Disease Risk Loci.

BACKGROUND: Genome-wide association studies have identified multiple loci associated with coronary artery disease and myocardial infarction, but only a few of these loci are current targets for on-market medications. To identify drugs suitable for repurposing and their targets, we created 2 unique pipelines integrating public data on 49 coronary artery disease/myocardial infarction-genome-wide association studies loci, drug-gene interactions, side effects, and chemical interactions. METHODS: We first used publicly available genome-wide association studies results on all phenotypes to predict relevant side effects, identified drug-gene interactions, and prioritized candidates for repurposing among existing drugs. Second, we prioritized gene product targets by calculating a druggability score to estimate how accessible pockets of coronary artery disease/myocardial infarction-associated gene products are, then used again the genome-wide association studies results to predict side effects, excluded loci with widespread cross-tissue expression to avoid housekeeping and genes involved in vital processes and accordingly ranked the remaining gene products. RESULTS: These pipelines ultimately led to 3 suggestions for drug repurposing: pentolinium, adenosine triphosphate, and riociguat (to target CHRNB4, ACSS2, and GUCY1A3, respectively); and 3 proteins for drug development: LMOD1 (leiomodin 1), HIP1 (huntingtin-interacting protein 1), and PPP2R3A (protein phosphatase 2, regulatory subunit b-double prime, α). Most current therapies for coronary artery disease/myocardial infarction treatment were also rediscovered. CONCLUSIONS: Integration of genomic and pharmacological data may prove beneficial for drug repurposing and development, as evidence from our pipelines suggests.

Stem cell mobilisation by granulocyte-colony stimulating factor in patients with acute myocardial infarction. Long-term results of the REVIVAL-2 trial.

Treatment with granulocyte-colony stimulating factor (G-CSF) mobilises cells from the bone marrow to the peripheral blood. Previous preclinical and early clinical trials may suggest that treatment with G-CSF leads to improved myocardial perfusion and function in acute or chronic ischaemic heart disease. In the REVIVAL-2 study we found that stem cell mobilisation by G-CSF does not influence infarct size, left ventricular function and coronary restenosis in patients with acute myocardial infarction (MI) that underwent successful percutaneous coronary intervention. The objective of the present analysis was to assess the impact of G-CSF treatment on seven-year clinical outcomes from the REVIVAL-2 trial. In the randomized, double-blind, placebo-controlled REVIVAL-2 study, 114 patients with the diagnosis of acute myocardial infarction were enrolled five days after successful reperfusion by percutaneous coronary intervention. Patients were assigned to receive 10 µg/kg G-CSF (n=56) or placebo (n=58) for five days. The primary endpoint for this long-term outcome analysis was the composite of death, myocardial infarction or stroke seven years after randomisation. The endpoint occurred in 14.3 % of patients in the G-CSF group versus 17.2 % assigned to placebo (p=0.67). The combined incidence of death or myocardial infarction occurred in 14.3 % of the patients assigned to G-CSF and 15.5 % of the patients assigned to placebo (p=0.85). In conclusion, these long-term follow-up data show that G-CSF does not improve clinical outcomes of patients with acute myocardial infarction.

Human and murine embryonic stem cell-derived cardiomyocytes serve together as a valuable model for drug safety screening.

AIMS: Screening of drug safety is typically performed in diverse non-human healthy species with an intact repolarization reserve. Nevertheless, these drugs are later applied in diseased humans with a reduced repolarization reserve. It would be optimal to set up a preclinical screening tool to estimate the proarrhythmic potential of drugs in human cardiac tissue with a reduced repolarization reserve in vitro. METHODS AND RESULTS: In our study spontaneously beating human embryonic stem cell-derived cardiomyocytes clusters (hESCM) and murine ES cell-derived cardiomyocytes (mESCMs) were plated onto micro-electrode arrays (MEAs) to record the extracelluar field potentials (FPs) as well as effects of several antiarrhythmic drugs. In line with clinical observations the class III antiarrhythmic drugs (+/-)-sotalol, E4031 and class I antiarrhythmic drug quinidine led to a prolongation of the cardiac repolarization phase (FP duration, FPdur) and a decrease of the FP frequency. Verapamil (a class IV antiarrhythmic drug) decreased the FP frequency and shortened FPdur. Both, quinidine and verapamil, but not (+/-)-sotalol or E4031 decreased conduction velocities in hESCM clusters. Moreover, (+/-)-sotalol exerted stronger effects on FPdur in early developmental stages of hESCMs, as proof for a reduced repolarization reserve. The EC(50) of the (+/-)-sotalol-induced prolongation of the FPdur was higher in mESCMs than in hESCMs implying species-dependent differences in cardiac repolarization. Likewise, the incidence of drug-induced early recurrent depolarization (ERDs) was higher in mESCMs than hESCMs. CONCLUSION: The combined measurement of drug effects on FP parameters in hESCMs and mESCMs serves as a reliable in vitro model for preclinical studies of drug safety.

Mild therapeutic hypothermia in patients after out-of-hospital cardiac arrest due to acute ST-segment elevation myocardial infarction undergoing immediate percutaneous coronary intervention.

OBJECTIVE: Mild therapeutic hypothermia (MTH) has been integrated into international resuscitation guidelines. In the majority of patients, sudden cardiac arrest is caused by myocardial infarction. This study investigated whether a combination of MTH with primary percutaneous coronary intervention (PCI) is feasible, safe, and potentially beneficial in patients after cardiac arrest due to acute myocardial infarction. DESIGN: Single-center observational study with a historical control group. SETTING: University clinic. PATIENTS: Thirty-three patients after cardiac arrest with ventricular fibrillation as initial rhythm and restoration of spontaneous circulation who remained unconscious at admission and presented with acute ST elevation myocardial infarction (STEMI). INTERVENTIONS: In 16 consecutive patients (2005-2006), MTH was initiated immediately after admission and continued during primary PCI. Seventeen consecutive patients who were treated in a similar 2-yr observation interval before implementation of MTH (2003-2004) served as a control group. Feasibility, safety, mortality, and neurologic outcome were documented. MEASUREMENTS AND MAIN RESULTS: Initiation of MTH did not result in longer door-to-balloon times compared with the control group (82 vs. 85 mins), indicating that implementation of MTH did not delay the onset of primary PCI. Target temperature (32-34 degrees C) in the MTH group was reached within 4 hrs, consistent with previous trials and suggesting that primary PCI did not affect the velocity of cooling. Despite a tendency to increased bleeding complications and infections, patients treated with MTH tended to have a lower mortality after 6 months (25% vs. 35%, p = .71) and an improved neurologic outcome as determined by a Glasgow-Pittsburgh Cerebral Performance Scale score of 1 or 2 (69% vs. 47% in the control group, p = .30). CONCLUSIONS: MTH in combination with primary PCI is feasible and safe in patients resuscitated after cardiac arrest due to acute myocardial infarction. A combination of these therapeutic procedures should be strongly considered as standard therapy in patients after out-of-hospital cardiac arrest due to STEMI.

An alternative splice variant in Abcc6, the gene causing dystrophic calcification, leads to protein deficiency in C3H/He mice.

Dystrophic cardiac calcification (DCC) is an autosomal recessive trait characterized by calcium phosphate deposits in myocardial tissue. The Abcc6 gene locus was recently found to mediate DCC; however, at the molecular level the causative variants remain to be determined. Examining the sequences of Abcc6 cDNA in DCC-resistant C57BL/6 and DCC-susceptible C3H/He mice, we identified a missense mutation (Cys to Thr at codon 619, rs32756904) at the 3'-border of exon 14 that creates an additional donor splice site (GT). Accordingly, an alternative transcript variant was detected, lacking the last 5 bp of exon 14 (-AGG(C/T)GCTgtga-) in DCC-susceptible C3H/He mice that carry the Thr allele. The 5-bp deletion was found to result in premature termination at codon 684, in turn leading to protein deficiency in DCC-susceptible mouse tissue as well as in cells transfected with Abcc6 cDNA lacking the last 5 bp of exon 14. All mouse strains that were found to carry the Thr allele, including C3H/He, DBA/2J, and 129S1/SvJ, were also found to be positive for DCC. In summary, we identified a splice variant leading to a 5-bp deletion in the Abcc6 transcript that gives rise to protein deficiency both in vivo and in vitro. The fact that all mouse strains that carry the deletion also develop dystrophic calcifications further suggests that the underlying splice variant affects the biological function of MRP6 protein and is a cause of DCC in mice.

Mild therapeutic hypothermia after cardiac arrest - a nationwide survey on the implementation of the ILCOR guidelines in German intensive care units.

AIM: To investigate the implementation of mild therapeutic hypothermia (MTH) after cardiac arrest into clinical practice. METHODS AND RESULTS: A structured evaluation questionnaire was sent to all German hospitals registered to have ICUs; 58% completed the survey. A total of 93 ICUs (24%) reported to use MTH. Of those, 93% started MTH in patients after out-of-hospital resuscitation with observed ventricular fibrillation and 72% when other initial rhythms were observed. Only a minority of ICUs initiate MTH in patients after cardiac arrest with cardiogenic shock (28%), whereas 48% regarded cardiogenic shock as a contra-indication for MTH. On average, target temperature was 33.1+/-0.6 degrees C and duration of cooling 22.9+/-4.9 h. Many centres used economically priced cold packs (82%) and cold infusions (80%) for cooling. The majority of the ICUs considered infection, hypotension and bleeding as relevant complications of hypothermia which was of therapeutic relevance in less than 25% of the cases. CONCLUSIONS: MTH is underused in German ICUs. Centres which use MTH widely follow the recommendations of ILCOR with respect to the indication and timing of cooling. In hospitals that use MTH the technique is considered to be safe and inexpensive. More efforts are needed to promote this therapeutic option and hypothermia since MTH has now been included into European advanced cardiovascular life support protocols.