Calf measurement of blood pressure is intermittent and its invasive nature limits its use during biking or exercise. In a recent study we used recurrent neural networks (RNN) to continuously predict BP from ECG, PPG, and signals from accelerometer and gyroscope. These signals are continuously collected by a wearable device called BioRadio. Our study is one of the first that trained a RNN for resting conditions, but tested it on signals collected during walking or biking to result in accurate BP prediction.

Related Publications

• S. Ghosh, A. Banerjee, N. Ray, P. Wood, P. Boulanger, R. Padwal, “Using Accelerometric and gyroscopic data to improve blood pressue prediction from pulse transit time using recurrent neural network,” ICASSP 2018.
• S. Ghosh, A. Banerjee, N. Ray, P.W. Wood, P. Boulanger, R. Padwal, “Continuous blood pressure prediction from pulse transit time using ECG and PPG signals,” 2016 IEEE Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT).
• S. Ghosh, A. Banerjee, N. Ray, P. W. Wood, P. Boulanger, R. Padwal, “Non-Invasive and Continuous Blood Pressure Prediction from Pulse Transit Time Using ECG and PPG Signals,” Poster presented at: Canadian Hypertension Congress Hypertension Canada; October 2016; Montreal, Quebec.
• S. Ghosh, N. Ray, P. W. Wood, P. Boulanger, R. Padwal, “Pulse Transit Time Computation Using Signal Sparsity for Continuous Blood Pressure Prediction,” Poster presented at: 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society; August 2016; Orlando, Florida.