Joint Health Monitoring
Using Knee Acoustical Emissions for Classifying Knee Joint Health
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]
Non-Invasive Cardiovascular Monitoring
(i) Acoustic Analysis of Left Ventricular Assist Devices for Thrombosis Detection
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.
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.
(ii) Heart Failure and Medication Changes
(i) Seismocardiography-Based Wearable Pre-Ejection Period Estimation
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).
(ii) Seismocardiography for Peri-Operative Use in Surgical Patients
Today, a commonly used tool for stroke volume estimation in the operating room is the Transesophageal Doppler (TED) which measures blood flow velocity in the descending thoracic aorta. Unfortunately, the use of the TED is restricted to the intra-operative setting in anesthetized patients and requires constant supervision and periodic adjustment for accurate signal quality. In this project, we propose the use of a wearable patch mounted on the mid-sternum, which captures the seismocardiogram (SCG) and electrocardiogram (ECG) signals continuously to predict SV in patients undergoing major surgery.
Subject Identification and Authentication
Subject Identification Using Scale-Based Ballistocardiogram Signals
Many electronic devices such as weighing scales, fitness equipment and medical devices are nowadays shared by multiple users. In such devices, automatic identification of device users becomes an important step towards improved user convenience, personalized service, and security. Physiological signals are highly subject-specific, naturally present in all living individuals and hard to replicate or counterfeit. In this project, we study subject identification using ballistocardiogram (BCG) signals collected from a modified weighing scale.