Aims The EURO-ENDO registry aimed to study the management and outcomes of patients with infective endocarditis (IE). Methods and results Prospective cohort of 3116 adult patients (2470 from Europe, 646 from non-ESC countries), admitted to 156 hospitals in 40 countries between January 2016 and March 2018 with a diagnosis of IE based on ESC 2015 diagnostic criteria. Clinical, biological, microbiological, and imaging [echocardiography, computed tomography (CT) scan, 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT)] data were collected. Infective endocarditis was native (NVE) in 1764 (56.6%) patients, prosthetic (PVIE) in 939 (30.1%), and device-related (CDRIE) in 308 (9.9%). Infective endocarditis was community-acquired in 2046 (65.66%) patients. Microorganisms involved were staphylococci in 1085 (44.1%) patients, oral streptococci in 304 (12.3%), enterococci in 390 (15.8%), and Streptococcus gallolyticus in 162 (6.6%). 18F-fluorodeoxyglucose positron emission tomography/computed tomography was performed in 518 (16.6%) patients and presented with cardiac uptake (major criterion) in 222 (42.9%) patients, with a better sensitivity in PVIE (66.8%) than in NVE (28.0%) and CDRIE (16.3%). Embolic events occurred in 20.6% of patients, and were significantly associated with tricuspid or pulmonary IE, presence of a vegetation and Staphylococcus aureus IE. According to ESC guidelines, cardiac surgery was indicated in 2160 (69.3%) patients, but finally performed in only 1596 (73.9%) of them. In-hospital death occurred in 532 (17.1%) patients and was more frequent in PVIE. Independent predictors of mortality were Charlson index, creatinine > 2 mg/dL, congestive heart failure, vegetation length > 10 mm, cerebral complications, abscess, and failure to undertake surgery when indicated. Conclusion Infective endocarditis is still a life-threatening disease with frequent lethal outcome despite profound changes in its clinical, microbiological, imaging, and therapeutic profiles.

Patients with rare conditions such as cardiac amyloidosis (CA) are difficult to identify, given the similarity of disease manifestations to more prevalent disorders. The deployment of approved therapies for CA has been limited by delayed diagnosis of this disease. Artificial intelligence (AI) could enable detection of rare diseases. Here we present a pipeline for CA detection using AI models with electrocardiograms (ECG) or echocardiograms as inputs. These models, trained and validated on 3 and 5 academic medical centers (AMC) respectively, detect CA with C-statistics of 0.85–0.91 for ECG and 0.89–1.00 for echocardiography. Simulating deployment on 2 AMCs indicated a positive predictive value (PPV) for the ECG model of 3–4% at 52–71% recall. Pre-screening with ECG enhance the echocardiography model performance at 67% recall from PPV of 33% to PPV of 74–77%. In conclusion, we developed an automated strategy to augment CA detection, which should be generalizable to other rare cardiac diseases.

Progressive superior shift of the mitral valve (MV) during systole is associated with abnormal papillary muscle (PM) superior shift in late systolic MV prolapse (MVP). The causal relation of these superior shifts remains unclarified. We hypothesized that the MV superior shift is related to augmented MV superiorly pushing force by systolic left ventricular pressure due to MV annular dilatation, which can be corrected by surgical MV plasty, leading to postoperative disappearance of these superior shifts. In 35 controls, 28 patients with holosystolic MVP, and 28 patients with late systolic MVP, the MV coaptation depth from the MV annulus was measured at early and late systole by two-dimensional echocardiography. The PM tip superior shift was monitored by echocardiographic speckle tracking. MV superiorly pushing force was obtained as MV annular area × (systolic blood pressure − 10). Measurements were repeated after MV plasty in 14 patients with late systolic MVP. Compared with controls and patients with holosystolic MVP, MV and PM superior shifts and MV superiorly pushing force were greater in patients with late systolic MVP [1.3 (0.5) vs. 0.9 (0.6) vs. 3.9 (1.0) mm/m2, 1.3 (0.5) vs. 1.2 (1.0) vs. 3.3 (1.3) mm/m2, and 487 (90) vs. 606 (167) vs. 742 (177) mmHg·cm2·m−2, respectively, means (SD), P < 0.001]. MV superior shift was correlated with PM superior shift ( P < 0.001), which was further related to augmented MV superiorly pushing force ( P < 0.001). MV and PM superior shift disappeared after surgical MV plasty for late systolic MVP. These data suggest that MV annulus dilatation augmenting MV superiorly pushing force may promote secondary superior shift of the MV (equal to late systolic MVP) that causes subvalvular PM traction in patients with late systolic MVP. NEW & NOTEWORTHY Late systolic mitral valve prolapse (MVP) is associated with mitral valve (MV) and papillary muscle (PM) abnormal superior shifts during systole, but the causal relation remains unclarified. MV and PM superior shifts were correlated with augmented MV superiorly pushing force by annular dilatation and disappeared after surgical MV plasty with annulus size and MV superiorly pushing force reduction. This suggests that MV annulus dilatation may promote secondary superior shifts of the MV (late systolic MVP) that cause subvalvular PM traction.

Although individually uncommon, rare diseases collectively affect over 350 million patients worldwide and are increasingly the target of therapeutic development efforts. Unfortunately, the pursuit and use of such therapies have been hindered by a common challenge: patients with specific rare diseases are difficult to identify, especially if the conditions resemble more prevalent disorders. Cardiac amyloidosis is one such rare disease, which is characterized by deposition of misfolded proteins within the heart muscle resulting in heart failure and death. In recent years, specific therapies have emerged for cardiac amyloidosis and several more are under investigation, but because cardiac amyloidosis is mistaken for common forms of heart failure, it is typically diagnosed late in its course. As a possible solution, artificial intelligence methods could enable automated detection of rare diseases, but model performance must address low disease prevalence. Here we present an automated multi-modality pipeline for cardiac amyloidosis detection using two neural-network models; one using electrocardiograms (ECG) and the second using echocardiographic videos as input. These models were trained and validated on 3 and 5 academic medical centers (AMC), respectively, in the United States and Japan. Both models had excellent accuracy for detecting cardiac amyloidosis with C-statistics of 0.85-0.92 and 0.91-1.00 for the ECG and echocardiography models, respectively, with the latter outperforming expert diagnosis. Simulating deployment on 13,906 and 7775 patients with ECG-echocardiography paired data for AMC2 and AMC3 indicated a positive predictive value (PPV) for the ECG model of 4% and 3% at 61% and 54% recall, respectively. Pre-screening with ECG enhanced the echocardiography model performance from PPV 23% and 20% to PPV 58% and 53% at 64% recall, respectively for AMC2 and AMC3. In conclusion, we have developed a robust pipeline to augment detection of cardiac amyloidosis, which should serve as a generalizable strategy for other rare and intermediate frequency cardiac diseases with established or emerging therapies.