FL-PMI: Federated Learning-Based Person Movement Identification through Wearable Devices in Smart Healthcare Systems.

Recent technological developments, such as the Internet of Things (IoT), artificial intelligence, edge, and cloud computing, have paved the way in transforming traditional healthcare systems into smart healthcare (SHC) systems. SHC escalates healthcare management with increased efficiency, convenience, and personalization, via use of wearable devices and connectivity, to access information with rapid responses. Wearable devices are equipped with multiple sensors to identify a person's movements. The unlabeled data acquired from these sensors are directly trained in the cloud servers, which require vast memory and high computational costs. To overcome this limitation in SHC, we propose a federated learning-based person movement identification (FL-PMI). The deep reinforcement learning (DRL) framework is leveraged in FL-PMI for auto-labeling the unlabeled data. The data are then trained using federated learning (FL), in which the edge servers allow the parameters alone to pass on the cloud, rather than passing vast amounts of sensor data. Finally, the bidirectional long short-term memory (BiLSTM) in FL-PMI classifies the data for various processes associated with the SHC. The simulation results proved the efficiency of FL-PMI, with 99.67% accuracy scores, minimized memory usage and computational costs, and reduced transmission data by 36.73%.

Short-Term Results With Ozaki Valved Conduit-A Simple Solution for Patients Needing Right Ventricle to Pulmonary Artery Conduit in a Low-Resource Setting.

BACKGROUND: The repair of certain types of complex congenital cardiac defects may require a right ventricle-pulmonary artery (RV-PA) conduit. Using the Ozaki Aortic valve neocuspidization (AVNeo)technique, a valved RV-PA conduit was constructed with an Ozaki valve inside a Dacron graft. This study aims to evaluate the short-term outcome of the Ozaki valved RV-PA conduit. MATERIAL/METHOD: A total of 22 patients received the Ozaki valved RV-PA conduit from November 2019 until December 2023. The median age was 12 years (interquartile range [IQR], 5.5-21), median body weight was 35 kg (IQR, 15.8-48.5). The conduit was used in 16 patients (72.7%) under 18 years of age. Indications for conduit placement included: anatomic repair of corrected transposition of the great arteries, ventricular septal defect/pulmonary stenosis, conduit replacement, pulmonary atresia with associated anomalies, pulmonary artery aneurysm with dysplastic pulmonary valve, tetralogy of Fallot with coronary artery crossing the right ventricular outflow tract, bioprosthetic pulmonary valve regurgitation, and rheumatic heart disease. Native pericardium was used for the Ozaki valve in 12 patients and bovine pericardium for 10 patients. Conduit sizes ranged from 18 mm to 30 mm. RESULT: The median intensive care unit stay was 4 (IQR, 2-6) days and the median hospital stay was 9 (IQR, 5.5-13.5) days. There were two perioperative mortalities (9.1%) both unrelated to the conduit. The median follow-up was 12.3 (IQR, 4.43-21.2) months. There was no infective endocarditis of the conduit. The median peak gradient across the conduit was 22 mm Hg (range 0-44 mm), and all were competent with trivial regurgitation on follow up. CONCLUSION: Creation of an Ozaki valved conduit is an attractive option due to low cost, reproducibility, and excellent hemodynamics. Longer-term studies are needed to confirm the durability.