Temporal trend and associated risk factors for new-onset atrial fibrillation following cardiac valve surgery.

AIMS: Post cardiac surgery atrial fibrillation (POAF) is common, with adverse implications. However, relatively little is known regarding the time varying nature of risk factors associated with POAF. We describe variation in POAF along with its associated risk factors. METHODS: Medical records of adult patients undergoing cardiac valve surgery from 2003-13, without a history of pre-operative AF were analyzed retrospectively. POAF was adjudicated using inpatient and outpatient electrocardiograms (EKG). Risk of AF over time along with time-varying risk factors were estimated using multiphase non-linear logistic mixed effects model. RESULTS: 10,461 patients with 100,149 EKGs were analyzed [median follow-up 4 months (IQR 48 hours-2 years)]. AF prevalence changed with time since surgery and two distinct phases were identified. Prevalence peaked to 13% at 2 weeks (early phase) and 9% near 7 years post-operatively (late phase). Older age, greater severity of preoperative tricuspid valve (TV) regurgitation, mitral valve replacement and prior cardiac surgery were time-independent risk factors for POAF. TV repair was associated with a decreased risk of early phase POAF. Pre-operative blood urea nitrogen, peripheral vascular disease and hypertension were associated with a higher risk of late phase POAF. CONCLUSIONS: POAF risk shows two distinct phases with an early peak and a late gradual rise, each associated with a different set of risk factors.

Swarm Learning as a privacy-preserving machine learning approach for disease classification

Identification of patients with life-threatening diseases including leukemias or infections such as tuberculosis and COVID-19 is an important goal of precision medicine. We recently illustrated that leukemia patients are identified by machine learning (ML) based on their blood transcriptomes. However, there is an increasing divide between what is technically possible and what is allowed because of privacy legislation. To facilitate integration of any omics data from any data owner world-wide without violating privacy laws, we here introduce Swarm Learning (SL), a decentralized machine learning approach uniting edge computing, blockchain-based peer-to-peer networking and coordination as well as privacy protection without the need for a central coordinator thereby going beyond federated learning. Using more than 14,000 blood transcriptomes derived from over 100 individual studies with non-uniform distribution of cases and controls and significant study biases, we illustrate the feasibility of SL to develop disease classifiers based on distributed data for COVID-19, tuberculosis or leukemias that outperform those developed at individual sites. Still, SL completely protects local privacy regulations by design. We propose this approach to noticeably accelerate the introduction of precision medicine.