Integrating Sensors Into the New Era of Artificial Intelligence

Regular, accurate blood pressure (BP) monitoring is essential for the diagnosis and treatment of hypertension and related diseases. Hypertension affects approximately 1.3 billion people and is the most common cause of cardiovascular disease worldwide. It increases the risk of heart attack, stroke, kidney disease and heart failure, and has also been linked to mental health disorders such as anxiety and depression. Strokes or serious heart events can be significantly reduced by regularly controlling blood pressure.

​

Inflatable cuff-based ambulatory BP monitoring (ABPM) has been shown to be reliable for accurate hypertension diagnosis. However, this cuff-based technology is expensive and can interfere with sleep and other daily activities. It is uncomfortable to wear such a monitor, thus limiting its 24/7 usage. There are a few non-invasive cuffless blood pressure monitoring technologies that can overcome these limitations, but some challenges are encountered.  

​

DiracSens' non-invasive blood pressure monitoring approach is based on AI modeling of pressure pulse waves (bottom right), reflecting pressure changes within arterial vessels through the use of our proprietary miniaturized, conformal piezoelectric sensors and arrays. The physical data obtained from the sensors are extracted, including labels of the pulse waveforms such as amplitude, frequency components, waveform morphology, etc. Next, advanced machine learning algorithms such as support vector machines (SVMs), convolutional neural networks (CNNs) and recurrent neural networks (RNNs) can be used. Real-time blood pressure monitoring systems can be implemented as wearable devices combined with mobile applications, or integrated into existing medical platforms.

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​​

​