ABSTRACT
Hemodialysis is the main treatment for patients with renal failure. Significant complications associated with treatment include hypotension, cramps, insufficient blood flow, and arrhythmia. Most complications are related to unstable blood pressure during hemodialysis. Although the science and technology and computer industry have made great progress in recent years, the problem of blood pressure prediction during hemodialysis is still a big challenge. Aiming at the problem that the shallow model used in the current research does not consider the high-dimensional nonlinear combination characteristics of hemodialysis data, this paper proposes a blood pressure prediction model during hemodialysis based on deep belief network (DBN) and support vector regression (SVR). In this model, DBN extracts the non-linear combination features of hemodialysis data layer by layer, and then transfers the extracted high-dimensional features to the top-level SVR for regression prediction. The experimental results show that the mean absolute error (MAE) of the model is 3.79, the root mean square error (RMSE) is 9.01, and is 0.88. Compared with the shallow model used in the current research, the prediction effect has been significantly improved.
- Meredith D J, Pugh C W, Sutherland S, The relationship between symptoms and blood pressure during maintenance hemodialysis[J]. Hemodialysis International, 2015, 19(4): 543-552.Google ScholarCross Ref
- Flythe J E, Xue H, Lynch K E, Association of mortality risk with various definitions of intradialytic hypotension[J]. Journal of the American Society of Nephrology, 2015, 26(3): 724-734.Google ScholarCross Ref
- Chou J A, Kalantar‐Zadeh K, Mathew A T. A brief review of intradialytic hypotension with a focus on survival[C]//Seminars in dialysis. 2017, 30(6): 473-480.Google Scholar
- Sars B, van der Sande F M, Kooman J P. Intradialytic hypotension: mechanisms and outcome[J]. Blood purification, 2020, 49(1-2): 158-167.Google Scholar
- Kuipers J, Verboom L M, Ipema K J R, The prevalence of intradialytic hypotension in patients on conventional hemodialysis: a systematic review with meta-analysis[J]. American journal of nephrology, 2019, 49(6): 497-506.Google Scholar
- Sands J J, Usvyat L A, Sullivan T, Intradialytic hypotension: frequency, sources of variation and correlation with clinical outcome[J]. Hemodialysis international, 2014, 18(2): 415-422.Google Scholar
- Santos S F F, Peixoto A J, Perazella M A. How should we manage adverse intradialytic blood pressure changes?[J]. Advances in chronic kidney disease, 2012, 19(3): 158-165.Google Scholar
- Smith B P, Ward R A, Brier M E. Prediction of anticoagulation during hemodialysis by population kinetics and an artificial neural network[J]. Artificial organs, 1998, 22(9): 731-739.Google Scholar
- Wang Y F, Hu T M, Wu C C, Prediction of target range of intact parathyroid hormone in hemodialysis patients with artificial neural network[J]. Computer methods and programs in biomedicine, 2006, 83(2): 111-119.Google Scholar
- Barbieri C, Mari F, Stopper A, A new machine learning approach for predicting the response to anemia treatment in a large cohort of End Stage Renal Disease patients undergoing dialysis[J]. Computers in biology and medicine, 2015, 61: 56-61.Google ScholarDigital Library
- Lin C J, Chen C Y, Wu P C, Intelligent system to predict intradialytic hypotension in chronic hemodialysis[J]. Journal of the Formosan Medical Association, 2018, 117(10): 888-893.Google ScholarCross Ref
- Chen J B, Wu K C, Moi S H, Deep learning for intradialytic hypotension prediction in hemodialysis patients[J]. IEEE Access, 2020, 8: 82382-82390.Google ScholarCross Ref
- Barbieri C, Cattinelli I, Neri L, Development of an artificial intelligence model to guide the management of blood pressure, fluid volume, and dialysis dose in end-stage kidney disease patients: proof of concept and first clinical assessment[J]. Kidney Diseases, 2019, 5(1): 28-33.Google ScholarCross Ref
- Huang J C, Tsai Y C, Wu P Y, Predictive modeling of blood pressure during hemodialysis: a comparison of linear model, random forest, support vector regression, XGBoost, LASSO regression and ensemble method[J]. Computer Methods and Programs in Biomedicine, 2020, 195: 105536.Google ScholarCross Ref
- Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural computation, 2006, 18(7): 1527-1554.Google Scholar
- Assimon M M, Flythe J E. Definitions of intradialytic hypotension[C]//Seminars in dialysis. 2017, 30(6): 464-472.Google Scholar
Recommendations
Blood Pressure Drop Prediction by using HRV Measurements in Orthostatic Hypotension
Orthostatic Hypotension is defined as a reduction of systolic and diastolic blood pressure within 3 minutes of standing, and may cause dizziness and loss of balance. Orthostatic Hypotension has been considered an important risk factor for falls since ...
Effect of Blood Pressure and Diameter on Carotid Artery
ICBEA '21: 4th International Conference on Biometric Engineering and ApplicationsStroke has become the first cause of death in China. The study on the relationship between stroke and the risk factors of carotid artery diameter and pulse rate is helpful to provide theoretical basis for the prevention and treatment of stroke. Stroke ...
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 ...
Comments