Machine learning for pacemaker implantation prediction after TAVI using multimodal imaging data.

Pacemaker implantation (PMI) after transcatheter aortic valve implantation (TAVI) is a common complication. While computed tomography (CT) scan data are known predictors of PMI, no machine learning (ML) model integrating CT with clinical, ECG, and transthoracic echocardiography (TTE) data has been proposed. This study investigates the contribution of ML methods to predict PMI after TAVI, with a focus on the role of CT imaging data. A retrospective analysis was conducted on a cohort of 520 patients who underwent TAVI. Recursive feature elimination with SHAP values was used to select key variables from clinical, ECG, TTE, and CT data. Six ML models, including Support Vector Machines (SVM), were trained using these selected variables. The model's performance was evaluated using AUC-ROC, F1 score, and accuracy metrics. The PMI rate was 18.8%. The best-performing model achieved an AUC-ROC of 92.1% ± 4.7, an F1 score of 71.8% ± 9.9, and an accuracy of 87.9% ± 4.7 using 22 variables, 9 of which were CT-based. Membranous septum measurements and their dynamic variations were critical predictors. Our ML model provides robust PMI predictions, enabling personalized risk assessments. The model is implemented online for broad clinical use.

Profile of patients hospitalized in intensive cardiac care units in France: ADDICT-ICCU registry.

BACKGROUND: Intensive cardiac care units (ICCU) were initially developed to monitor ventricular arrhythmias after myocardial infarction. In recent decades, ICCU have diversified their activities. AIM: To determine the type of patients hospitalized in ICCU in France. METHODS: We analysed the characteristics of patients enrolled in the ADDICT-ICCU registry (NCT05063097), a prospective study of consecutive patients admitted to ICCU in 39 centres throughout France from 7th-22nd April 2021. In-hospital major adverse events (MAE) (death, resuscitated cardiac arrest and cardiogenic shock) were recorded. RESULTS: Among 1499 patients (median age 65 [interquartile range 54-74] years, 69.6% male, 21.7% diabetes mellitus, 64.7% current or previous smokers), 34.9% had a history of coronary artery disease, 11.7% atrial fibrillation and 5.2% cardiomyopathy. The most frequent reason for admission to ICCU was acute coronary syndromes (ACS; 51.5%), acute heart failure (AHF; 14.1%) and unexplained chest pain (6.8%). An invasive procedure was performed in 36.2%. "Advanced" ICCU therapies were required for 19.9% of patients (intravenous diuretics 18.4%, non-invasive ventilation 6.1%, inotropic drugs 2.3%). No invasive procedures or advanced therapies were required in 44.1%. Cardiac computed tomography or magnetic resonance imaging was carried out in 12.3% of patients. The median length of ICCU hospitalization was 2.0 (interquartile range 1.0-4.0) days. The mean rate of MAE was 4.5%, and was highest in patients with AHF (10.4%). CONCLUSIONS: ACS remains the main cause of admissions to ICCU, with most having a low rate of in-hospital MAE. Most patients experience a brief stay in ICCU before being discharged home. AHF is associated with highest death rate and with higher resource consumption.

Phenotypic clustering of patients hospitalized in intensive cardiac care units: Insights from the ADDICT-ICCU study.

BACKGROUND: Intensive cardiac care units (ICCUs) were created to manage ventricular arrhythmias after acute coronary syndromes, but have diversified to include a more heterogeneous population, the characteristics of which are not well depicted by conventional methods. AIMS: To identify ICCU patient subgroups by phenotypic unsupervised clustering integrating clinical, biological, and echocardiographic data to reveal pathophysiological differences. METHODS: During 7-22 April 2021, we recruited all consecutive patients admitted to ICCUs in 39 centers. The primary outcome was in-hospital major adverse events (MAEs; death, resuscitated cardiac arrest or cardiogenic shock). A cluster analysis was performed using a Kamila algorithm. RESULTS: Of 1499 patients admitted to the ICCU (69.6% male, mean age 63.3±14.9 years), 67 (4.5%) experienced MAEs. Four phenogroups were identified: PG1 (n=535), typically patients with non-ST-segment elevation myocardial infarction; PG2 (n=444), younger smokers with ST-segment elevation myocardial infarction; PG3 (n=273), elderly patients with heart failure with preserved ejection fraction and conduction disturbances; PG4 (n=247), patients with acute heart failure with reduced ejection fraction. Compared to PG1, multivariable analysis revealed a higher risk of MAEs in PG2 (odds ratio [OR] 3.13, 95% confidence interval [CI] 1.16-10.0) and PG3 (OR 3.16, 95% CI 1.02-10.8), with the highest risk in PG4 (OR 20.5, 95% CI 8.7-60.8) (all P<0.05). CONCLUSIONS: Cluster analysis of clinical, biological, and echocardiographic variables identified four phenogroups of patients admitted to the ICCU that were associated with distinct prognostic profiles. TRIAL REGISTRATION: ClinicalTrials.gov identifier: NCT05063097.

Tricuspid annular plane systolic excursion over systolic pulmonary artery pressure prognostic value for in-hospital adverse events in patients hospitalized for acute coronary syndrome.

AIMS: Although several studies have shown that the right ventricular to pulmonary artery (RV-PA) coupling, assessed by the ratio between tricuspid annular plane systolic excursion and systolic pulmonary artery pressure (TAPSE/sPAP) using echocardiography, is strongly associated with cardiovascular events, its prognostic value is not established in acute coronary syndrome (ACS). We aimed to assess the in-hospital prognostic value of TAPSE/sPAP among patients hospitalized for ACS in a retrospective analysis from the prospective ADDICT-ICCU study. METHODS AND RESULTS: A total of 481 consecutive patients hospitalized in intensive cardiac care unit [mean age 65 ± 13 years, 73% of male, 46% ST-elevation myocardial infarction (STEMI)] for ACS [either STEMI or non-STEMI (NSTEMI)] with TAPSE/sPAP available were included in this prospective French multicentric study (39 centres). The primary outcome was in-hospital major adverse cardiovascular events (MACEs) defined as all-cause death, resuscitated cardiac arrest, or cardiogenic shock and occurred in 33 (7%) patients. Receiver operating characteristic curve analysis identified 0.55 mm/mmHg as the best TAPSE/sPAP cut-off to predict in-hospital MACEs. TAPSE/sPAP <0.55 was associated with in-hospital MACEs, even after adjustment with comorbidities [odds ratio (OR): 19.1, 95% confidence interval (CI) 7.78-54.8], clinical severity including left ventricular ejection fraction (OR: 14.4, 95% CI 5.70-41.7), and propensity-matched population analysis (OR: 22.8, 95% CI 7.83-97.2, all P < 0.001). After adjustment, TAPSE/sPAP <0.55 showed the best improvement in model discrimination and reclassification above traditional prognosticators (C-statistic improvement: 0.16; global χ2 improvement: 52.8; likelihood ratio test P < 0.001) with similar results for both STEMI and NSTEMI subgroups. CONCLUSION: A low RV-PA coupling defined as TAPSE/sPAP ratio <0.55 was independently associated with in-hospital MACEs and provided incremental prognostic value over traditional prognosticators in patients hospitalized for ACS. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT05063097.

Prevalence and impact of recreational drug use in patients with acute cardiovascular events.

OBJECTIVE: While recreational drug use is a risk factor for cardiovascular events, its exact prevalence and prognostic impact in patients admitted for these events are not established. We aimed to assess the prevalence of recreational drug use and its association with in-hospital major adverse events (MAEs) in patients admitted to intensive cardiac care units (ICCU). METHODS: In the Addiction in Intensive Cardiac Care Units (ADDICT-ICCU) study, systematic screening for recreational drugs was performed by prospective urinary testing all patients admitted to ICCU in 39 French centres from 7 to 22 April 2021. The primary outcome was prevalence of recreational drug detection. In-hospital MAEs were defined by death, resuscitated cardiac arrest, or haemodynamic shock. RESULTS: Of 1499 consecutive patients (63±15 years, 70% male), 161 (11%) had a positive test for recreational drugs (cannabis 9.1%, opioids 2.1%, cocaine 1.7%, amphetamines 0.7%, 3,4-methylenedioxymethamphetamine (MDMA) 0.6%). Only 57% of these patients declared recreational drug use. Patients who used recreational drugs exhibited a higher MAE rate than others (13% vs 3%, respectively, p<0.001). Recreational drugs were associated with a higher rate of in-hospital MAEs after adjustment for comorbidities (OR 8.84, 95% CI 4.68 to 16.7, p<0.001). After adjustment, cannabis, cocaine, and MDMA, assessed separately, were independently associated with in-hospital MAEs. Multiple drug detection was frequent (28% of positive patients) and associated with an even higher incidence of MAEs (OR 12.7, 95% CI 4.80 to 35.6, p<0.001). CONCLUSION: The prevalence of recreational drug use in patients hospitalised in ICCU was 11%. Recreational drug detection was independently associated with worse in-hospital outcomes. CLINICAL TRIAL REGISTRATION: NCT05063097.