Life-threatening ventricular arrhythmias (VA) are the leading cause of sudden cardiac death (SCD), which is the most significant cause of natural death in the US [6]. The implantable cardioverter defibrillator (ICD) is a small device implanted to patients under high risk of SCD as a preventive treatment. The ICD continuously monitors the intracardiac rhythm and delivers shock when detecting the lifethreatening VA. Traditional methods detect VA by setting criteria on the detected rhythm. However, those methods suffer from a high inappropriate shock rate and require a regular follow-up to optimize criteria parameters for each ICD recipient. To ameliorate the challenges, we propose the personalized computing framework for deep learning based VA detection on medical IoT systems. The system consists of intracardiac and surface rhythm monitors, and the cloud platform for data uploading, diagnosis, and CNN model personalization. We equip the system with real-time inference on both intracardiac and surface rhythm monitors. To improve the detection accuracy, we enable the monitors to detect VA collaboratively by proposing the cooperative inference. We also introduce the CNN personalization for each patient based on the computing framework to tackle the unlabeled and limited rhythm data problem. When compared with the traditional detection algorithm, the proposed method achieves comparable accuracy on VA rhythm detection and 6.6% reduction in inappropriate shock rate, while the average inference latency is kept at 71ms.

Piezoelectric acoustic transducers consisting of a circular aluminum nitride and silicon nitride unimorph diaphragm and an encapsulated air-filled back cavity are reported. Analytical and finite element analysis models are used to design the transducer to achieve low minimum detectable pressure (MDP) within chosen size restrictions. A series of transducers with varying radii are fabricated using microelectromechanical systems (MEMS) techniques. Experimental results are reported for a transducer with a 175 lm radius on a 400 Â 500 Â 500 lm 3 die exhibiting structural resonances at 552 kHz in air and 133 kHz in water. The low-frequency (10 Hz-50 kHz) sensitivity is 1.87 lV/Pa (À114.5 dB re 1 V/Pa) in both air and water. The sensor has an MDP of 43.7 mPa/ ffiffiffiffiffiffi Hz p (67 dB SPL) at 100 Hz and 10.9 mPa/ ffiffiffiffiffiffi Hz p (55 dB SPL) at 1 kHz. This work contributes a set of design rules for MEMS piezoelectric diaphragm transducers that focuses on decreasing the MDP of the sensor through size, material properties, and residual stress considerations.

No abstract

Life-threatening ventricular arrhythmias (VAs) detection on intracardiac electrograms (IEGMs) is essential to Implantable Cardioverter Defibrillators (ICDs). However, current VAs detection methods count on a variety of heuristic detection criteria, and require frequent manual interventions to personalize criteria parameters for each patient to achieve accurate detection. In this work, we propose a one-dimensional convolutional neural network (1D-CNN) based life-threatening VAs detection on IEGMs. The network architecture is elaborately designed to satisfy the extreme resource constraints of the ICD while maintaining high detection accuracy. We further propose a meta-learning algorithm with a novel patient-wise training tasks formatting strategy to personalize the 1D-CNN. The algorithm generates a well-generalized model initialization containing across-patient knowledge, and performs a quick adaptation of the model to the specific patient's IEGMs. In this way, a new patient could be immediately assigned with personalized 1D-CNN model parameters using limited input data. Compared with the conventional VAs detection method, the proposed method achieves 2.2% increased sensitivity for detecting VAs rhythm and 8.6% increased specificity for non-VAs rhythm.

No abstract