ABSTRACT
Recently, the percentage of people with hypertension is increasing, and this phenomenon is widely concerned. At the same time, wireless home Blood Pressure (BP) monitors become accessible in people's life. Since machine learning methods have made important contributions in different fields, many researchers have tried to employ them in dealing with medical problems. However, the existing studies for BP prediction are all based on clinical data with short time ranges. Besides, there do not exist works which can jointly make use of historical measurement data (e.g. BP and heart rate) and contextual data (e.g. age, gender, BMI and altitude). Recurrent Neural Networks (RNNs), especially those using Long Short-Term Memory (LSTM) units, can capture long range dependencies, so they are effective in modeling variable-length sequences. In this paper, we propose a novel model named recurrent models with contextual layer, which can model the sequential measurement data and contextual data simultaneously to predict the trend of users' BP. We conduct our experiments on the BP data set collected from a type of wireless home BP monitors, and experimental results show that the proposed models outperform several competitive compared methods.
- M. Auli, M. Galley, C. Quirk, and G. Zweig. Joint language and translation modeling with recurrent neural networks. American Journal of Psychoanalysis, 74(2):212--3, 2013.Google Scholar
- G. E. Batista and M. C. Monard. An analysis of four missing data treatment methods for supervised learning. Applied Artificial Intelligence, 17(5--6):519--533, 2003.Google Scholar
- F. P. Cappuccio, S. M. Kerry, L. Forbes, and A. Donald. Blood pressure control by home monitoring: Meta-analysis of randomised trials. Bmj, 329(7458):145, 2004.Google ScholarCross Ref
- P. R. Chang and J. T. Hu. Optimal nonlinear adaptive prediction and modeling of mpeg video in atm networks using pipelined recurrent neural networks. IEEE Journal on Selected Areas in Communications, 15(6):1087--1100, 2006. Google ScholarDigital Library
- A. V. Chobanian, G. L. Bakris, H. R. Black, W. C. Cushman, L. A. Green, J. L. Izzo Jr, D. W. Jones, B. J. Materson, S. Oparil, J. T. Wright Jr, et al. The seventh report of the joint national committee on prevention, detection, evaluation, and treatment of high blood pressure: the jnc 7 report. Jama, 289(19):2560--2571, 2003.Google ScholarCross Ref
- J. Chung, C. Gulcehre, K. H. Cho, and Y. Bengio. Empirical evaluation of gated recurrent neural networks on sequence modeling. Eprint Arxiv, 2014.Google Scholar
- F. Dabek and J. J. Caban. A Neural Network Based Model for Predicting Psychological Conditions. 2015.Google ScholarCross Ref
- G. B. Ehret, K. M. Rice, M. Bochud, A. D. Johnson, D. I. Chasman, A. V. Smith, M. D. Tobin, G. C. Verwoert, S. J. Hwang, and V. Pihur. Genetic variants in novel pathways influence blood pressure and cardiovascular disease risk. Nature, 478(7367):103--109, 2011.Google ScholarCross Ref
- X. H. Fang, W. T. Longstreth Jr, S. C. Li, R. A. Kronmal, X. M. Cheng, W. Z. Wang, S. Wu, X. L. Du, and X. Y. Dai. Longitudinal study of blood pressure and stroke in over 37,000 people in china. Cerebrovascular Diseases, 11(3):225--9, 2001.Google ScholarCross Ref
- J. H. Friedman. Greedy function approximation: a gradient boosting machine. Annals of statistics, pages 1189--1232, 2001.Google Scholar
- M. Gerrard, F. X. Gibbons, A. E. Houlihan, M. L. Stock, and E. A. Pomery. Probabilistic detection of short events, with application to critical care monitoring. In NIPS, pages 49--56, 2008. Google ScholarDigital Library
- A. Gers F., J. Schmidhuber, and F. Cummins. Learning to forget: Continual prediction with lstm. Neural Computation, 12(10):2451--71, 2000. Google ScholarDigital Library
- H. F. Golino, L. S. Amaral, S. F. Duarte, C. M. Gomes, T. J. Soares, L. A. Dos Reis, and J. Santos. Predicting increased blood pressure using machine learning. Journal of Obesity, 2014(5):637635--637635, 2014.Google Scholar
- A. Graves, M. Liwicki, S. Fernández, R. Bertolami, H. Bunke, and J. Schmidhuber. A novel connectionist system for unconstrained handwriting recognition. TPAMI, 31(5):855--868, 2009. Google ScholarDigital Library
- A. Graves, A. R. Mohamed, and G. Hinton. Speech recognition with deep recurrent neural networks. 1(2003):6645--6649, 2013.Google Scholar
- N. Hammerla, J. Fisher, P. Andras, L. Rochester, R. Walker, and T. Ploetz. Pd disease state assessment in naturalistic environments using deep learning. 2015.Google Scholar
- S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural Computation, 9(8):1735--1780, 1997. Google ScholarDigital Library
- P. A. James, S. Oparil, B. L. Carter, W. C. Cushman, C. Dennison-Himmelfarb, J. Handler, D. T. Lackland, M. L. LeFevre, T. D. MacKenzie, O. Ogedegbe, et al. 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the eighth joint national committee (jnc 8). Jama, 311(5):507--520, 2014.Google ScholarCross Ref
- J. Kolen and S. Kremer. Gradient Flow in Recurrent Nets: The Difficulty of Learning LongTerm Dependencies. Wiley-IEEE Press, 2009.Google Scholar
- S. Kombrink, T. Mikolov, M. Karafiät, and L. Burget. Recurrent neural network based language modeling in meeting recognition. In INTERSPEECH, volume 11, pages 2877--2880, 2011.Google Scholar
- Z. C. Lipton, D. C. Kale, C. Elkan, and R. Wetzell. Learning to diagnose with lstm recurrent neural networks. Computer Science, 2015.Google Scholar
- Q. Liu, S. Wu, D. Wang, Z. Li, and L. Wang. Context-aware sequential recommendation. 2016.Google ScholarCross Ref
- Q. Liu, S. Wu, L. Wang, and T. Tan. Predicting the next location: A recurrent model with spatial and temporal contexts. In Thirtieth AAAI Conference on Artificial Intelligence, 2016. Google ScholarDigital Library
- A. G. Logan, A. Dunai, W. J. Mcisaac, M. J. Irvine, and A. Tisler. Attitudes of primary care physicians and their patients about home blood pressure monitoring in ontario. Journal of Hypertension, 26(3):446--52, 2008.Google ScholarCross Ref
- A. F. Members, G. Mancia, R. Fagard, K. Narkiewicz, J. Redon, A. Zanchetti, M. B Ãühm, T. Christiaens, R. Cifkova, and G. D. Backer. 2013 esh/esc guidelines for the management of arterial hypertension. European Heart Journal, 34(28):2159--219, 2013.Google ScholarCross Ref
- T. Mikolov, M. Karafiát, L. Burget, J. Cernock'y, and S. Khudanpur. Recurrent neural network based language model. In Interspeech, volume 2, page 3, 2010.Google ScholarCross Ref
- W. H. Organization. Q&As on hypertension. http://www.who.int/features/qa/82/en/, 2015.Google Scholar
- L. R. Rabiner. A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2):257--286, 1989.Google ScholarCross Ref
- S. Rendle. Factorization machines. In ICDM, pages 995--1000. IEEE, 2010. Google ScholarDigital Library
- C. Sideris, H. Kalantarian, E. Nemati, and M. Sarrafzadeh. Building continuous arterial blood pressure prediction models using recurrent networks. In IEEE International Conference on Smart Computing, pages 1--5, 2016.Google ScholarCross Ref
- A. J. Smola and B. Schölkopf. A tutorial on support vector regression. Statistics and computing, 14(3):199--222, 2004. Google ScholarDigital Library
- S. Somanchi, S. Adhikari, A. Lin, E. Eneva, and R. Ghani. Early prediction of cardiac arrest (code blue) using electronic medical records. In ACM SIGKDD, pages 2119--2126, 2015. Google ScholarDigital Library
- G. S. Stergiou and E. G. Nasothimiou. Hypertension: Does home telemonitoring improve hypertension management? Nature Reviews Nephrology, 7(9):493--5, 2011.Google ScholarCross Ref
- P. W. Wilson, R. B. D'Agostino, D. Levy, A. M. Belanger, H. Silbershatz, and W. B. Kannel. Prediction of coronary heart disease using risk factor categories. Circulation, 97(18):1837--1847, 1998.Google ScholarCross Ref
- T. H. Wu, K. H. Pang, and W. Y. Kwong. Predicting systolic blood pressure using machine learning. pages 1--6, 2015.Google Scholar
- Y. Zhang, H. Dai, C. Xu, J. Feng, T. Wang, J. Bian, B. Wang, and T. Y. Liu. Sequential click prediction for sponsored search with recurrent neural networks. Computer Science, 2014Google Scholar
Index Terms
- Blood Pressure Prediction via Recurrent Models with Contextual Layer
Recommendations
Double Channel Neural Non Invasive Blood Pressure Prediction
Intelligent Computing Theories and ApplicationAbstractCardiovascular Diseases represent the leading cause of deaths in the world. Arterial Blood Pressure (ABP) is an important physiological parameter that should be properly monitored for the purposes of prevention. This work applies the neural ...
A recurrent neural network classifier for Doppler ultrasound blood flow signals
The aim of this study is to evaluate the diagnostic accuracy of the recurrent neural networks (RNNs) trained with Levenberg-Marquardt algorithm on the Doppler ultrasound blood flow signals. The ophthalmic arterial (OA) and internal carotid arterial (ICA)...
Using Accelerometric and Gyroscopic Data to Improve Blood Pressure Prediction from Pulse Transit Time Using Recurrent Neural Network
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)We propose a method for estimating blood pressure (BP) non-invasively from electrocardiogram (ECG) and photoplethysmogram (PPG) signals. This method has potential to be used as a continuous form of BP estimation. Along with these signals, to our knowledge,...
Comments