Identifying risk of adverse outcomes in COVID-19 patients via artificial intelligence-powered analysis of 12-lead intake electrocardiogram.

BACKGROUND: Adverse events in COVID-19 are difficult to predict. Risk stratification is encumbered by the need to protect healthcare workers. We hypothesize that artificial intelligence (AI) can help identify subtle signs of myocardial involvement in the 12-lead electrocardiogram (ECG), which could help predict complications. OBJECTIVE: Use intake ECGs from COVID-19 patients to train AI models to predict risk of mortality or major adverse cardiovascular events (MACE). METHODS: We studied intake ECGs from 1448 COVID-19 patients (60.5% male, aged 63.4 ± 16.9 years). Records were labeled by mortality (death vs discharge) or MACE (no events vs arrhythmic, heart failure [HF], or thromboembolic [TE] events), then used to train AI models; these were compared to conventional regression models developed using demographic and comorbidity data. RESULTS: A total of 245 (17.7%) patients died (67.3% male, aged 74.5 ± 14.4 years); 352 (24.4%) experienced at least 1 MACE (119 arrhythmic, 107 HF, 130 TE). AI models predicted mortality and MACE with area under the curve (AUC) values of 0.60 ± 0.05 and 0.55 ± 0.07, respectively; these were comparable to AUC values for conventional models (0.73 ± 0.07 and 0.65 ± 0.10). There were no prominent temporal trends in mortality rate or MACE incidence in our cohort; holdout testing with data from after a cutoff date (June 9, 2020) did not degrade model performance. CONCLUSION: Using intake ECGs alone, our AI models had limited ability to predict hospitalized COVID-19 patients' risk of mortality or MACE. Our models' accuracy was comparable to that of conventional models built using more in-depth information, but translation to clinical use would require higher sensitivity and positive predictive value. In the future, we hope that mixed-input AI models utilizing both ECG and clinical data may be developed to enhance predictive accuracy.

Identification of novel pheno-groups in heart failure with preserved ejection fraction using machine learning.

OBJECTIVE: Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous syndrome. We aimed to derive HFpEF phenotype-based groups ('phenogroups') based on clinical and echocardiogram data using machine learning, and to compare clinical characteristics, proteomics and outcomes across the phenogroups. METHODS: We applied model-based clustering to 32 echocardiogram and 11 clinical and laboratory variables collected in stable condition from 320 HFpEF outpatients in the Karolinska-Rennes cohort study (56% female, median 78 years (IQR: 71-83)). Baseline proteomics and the composite end point of all-cause mortality or heart failure (HF) hospitalisation were used in secondary analyses. RESULTS: We identified six phenogroups, for which significant differences in the prevalence of concomitant atrial fibrillation (AF), anaemia and kidney disease were observed (p<0.05). Fifteen out of 86 plasma proteins differed between phenogroups (false discovery rate, FDR<0.05), including biomarkers of HF, AF and kidney function. The composite end point was significantly different between phenogroups (log-rank p<0.001), at short-term (100 days), mid-term (18 months) and longer-term follow-up (1000 days). Phenogroup 2 was older, with poorer diastolic and right ventricular function and higher burden of risk factors as AF (85%), hypertension (83%) and chronic obstructive pulmonary disease (30%). In this group a third experienced the primary outcome to 100 days, and two-thirds to 18 months (HR (95% CI) versus phenogroups 1, 3, 4, 5, 6: 1.5 (0.8-2.9); 5.7 (2.6-12.8); 2.9 (1.5-5.6); 2.7 (1.6-4.6); 2.1 (1.2-3.9)). CONCLUSIONS: Using machine learning we identified distinct HFpEF phenogroups with differential characteristics and outcomes, as well as differential levels of inflammatory and cardiovascular proteins.

Upgrades from a previous device compared to de novo cardiac resynchronization therapy in the European Society of Cardiology CRT Survey II.

BACKGROUND: To date, there are no data from randomized controlled studies on the benefit of cardiac resynchronization therapy (CRT) when implanted as an upgrade in patients with a previous device as compared to de novo CRT. In the CRT Survey II we compared the baseline data of patients upgraded to CRT (CRT-P/CRT-D) from a previous pacemaker (PM) or implantable cardioverter-defibrillator (ICD) to de novo CRT implantation. METHODS AND RESULTS: In the European CRT Survey II, clinical practice data of patients undergoing CRT and/or ICD implantation across 42 European Society of Cardiology (ESC) countries were collected between October 2015 and December 2016. Out of a total of 11 088 patients, 2396 (23.2%) were upgraded from a previous PM or ICD and 7933 (76.8%) underwent de novo implantation. Compared to de novo implantations, upgraded patients were older, more often male, more frequently had ischaemic heart failure aetiology, atrial fibrillation, reduced renal function, worse heart failure symptoms, and higher N-terminal pro-B-type natriuretic peptide levels. Upgraded patients were more often PM-dependent and less frequently received CRT-D. Total peri-procedural, in-hospital complications and length of hospital stay were similar. Upgraded patients were less frequently treated with heart failure medication at discharge. CONCLUSION: Despite a lack of evidenced-based data, close to one quarter of all CRT implantations across 42 ESC countries were upgrades from a previous PM or ICD. Despite older age and worse symptoms, the CRT implantation procedures in upgraded patients were equally frequently successful and complications similar to de novo implantations. These results call for more studies.

Sequential biventricular pacing: evaluation of safety and efficacy.

The study evaluated the clinical safety, performance, and efficacy of sequential biventricular pacing in the InSync III (Model 8042) biventricular stimulator in a multicenter, prospective 3-month study and assessed the proper functioning of features aiming at improving biventricular AV therapy delivery. The system was successfully implanted in 189 (95.9%) of 198 patients with symptomatic systolic heart failure and a prolonged QRS complex duration. Patients significantly improved their 6-minute hall walk distance (baseline 339 +/- 92 vs 3-month 422 +/- 127 meter, P < 0.001) and NYHA class (baseline 3.1 +/- 0.5 vs 3-month 1.9 +/- 0.7, P < 0.001). Echocardiographic optimization of sequential biventricular pacing showed an improvement in stroke volume compared to simultaneous stimulation (sequential 68 +/- 24 mL vs simultaneous 56 +/- 23 mL, P < 0.001) at baseline and at 3 months. In 88% (30/34) of the patients these improvements were seen within a small range of V-V delays of +/-20 ms and in 94% (32/34) within V-V delays of +/-40 ms. In contrast, programming beyond this range reduced stroke volume below that during simultaneous biventricular pacing. The device functioned as expected. LV lead dislodgement was observed in 12 patients and phrenic nerve stimulation required lead repositioning in 2 patients. Eight patients died during the study. Patient survival at 3 and 6 months was 97 +/- 2% and 94 +/- 2%, respectively. Cause of death was cardiac (n = 7), heart failure related (n = 3), arrhythmia related (n = 2), and unknown (n = 2). In conclusion, this sequential biventricular pacemaker was safe and efficacious.