Knee Acoustical Emissions
Juvenile idiopathic arthritis (JIA) is the most common rheumatic condition in children and one of the more common chronic illnesses of childhood. Using a small piezoelectric accelerometer, the acoustical emissions from the knee joints of the patients with JIA can be recorded and analyzed to compute a knee health score. These acoustical emissions can provide a novel and cost-effective method for monitoring JIA, and can be used as an objective guide for assessing treatment efficacy.
CNN featured our project!
Nov, 2017. [link]
Left Ventricular Assist Devices
Left ventricular assist devices (LVADs) fail in up to 10% of patients due to the development of pump thrombosis. Remote monitoring of patients with LVADs can enable early detection and, subsequently, treatment and prevention of pump thrombosis. We assessed whether acoustical signals measured on the chest of patients with LVADs, combined with machine learning algorithms, can be used for detecting pump thrombosis.
Heart Failure and Medication Changes
Investigating the hemodynamic responses to medication changes can assist clinical decisions in heart failure (HF) management. In addition, the use of such correlation can further be leveraged in non-invasive home-monitoring systems in order to ensure medication adherence. We investigated whether the ballistocardiogram (BCG) signals can be used for tracking hemodynamic responses to changes in diuretic doses in patients with HF.
This work highlights the advantages of sensor fusion for developing wearable sensors to monitor cardiac health. We performed a rigorous investigation of gyroscope and accelerometer based seismocardiography (SCG) measurement in the context of pre-ejection period (PEP) detection accuracy. We leveraged state-of-the-art nonlinear and linear regression algorithms to map features of the SCG signal to aortic valve opening (AVO).
An accurate identity recognition system does not only inhibit fraud and crime, but can also save critical resources and facilitate business processes. Ideally, a recognition system is expected to be unique, permanent, collectible and universal. Biometric identity recognition is gaining popularity as it is directly related to the subject’s body, thus it is definitive. In this project we investigated whether ballistocardiogram (BCG) signals can be used in subject identification and authentication.