A novel short-term blood pressure prediction model based on LSTM

Blood pressure (BP) can reflect many physiological characteristics, and timely monitoring of it can somehow prevent hypertension, asphyxia and other diseases. With the development of clinical medical technology, the accuracy requirements of the intelligent physiological monitoring equipment for predicting the physiological characteristics of BP are gradually increasing. This paper proposes a BP prediction model based on Long Short Term Memory Networks (LSTM-NN), which makes full use of the efficient processing characteristics of LSTM for time series information and accurately predicts the systolic BP and diastolic BP. The primitive photoplethysmographic pulse wave (PPW) signal and actual BP data in different time periods and different states were collected on 6 adult goats simultaneously. The blood flow changes were stimulated by injection of adrenaline to obtain a wide range of raw data to improve the generalization ability of the model. The clinical features of each PPW cycle were introduced into the LSTM model for training and prediction to resolve actual systolic BP and diastolic BP. Comparing the model with the prediction effect of BP neural network (BP-NN) model, the result shows that the prediction accuracy of LSTM model is high and the robustness is strong. The maximum error values for systolic and diastolic pressure prediction are 1.05mmHg and 1.8mmHg, respectively.