Risk prediction of hypertension complications based on the intelligent algorithm optimized Bayesian network

  • Gang Du
  • Xi Liang
  • Xiaoling OuyangEmail author
  • Chunming Wang


Hypertension and its related complications could be a major threat issue for cardiopathy and stroke. Effective prevention and control can decrease the incidence rate of complications in hypertension. Based on the medical data of 3062 patients with cardiovascular and cerebrovascular diseases from 2017 to 2018 in a grade-A tertiary hospital in Shanghai, the study identified the risk factors of hypertension complications by text mining. On this basis, the K2 algorithm based on the improved particle swarm optimization was proposed to optimize the structure of the Bayesian network (BN) by establishing a multi-population cooperative search mechanism. Then the optimized BN was used to analyze and predict the incidence rate of hypertension complications. Results indicate that the major indicators of accuracy, sensitivity, specificity, and AUC have been improved, and the proposed algorithm is superior to the common data mining algorithms such as the back propagation neural network and the decision tree. Through the proposed model and algorithm, the high-risk factors were identified and the occurrence probability of hypertension complications was predicted, which could provide the personalized health management guidance for hypertensive patients to prevent and control hypertension complications.


Hypertension complications Risk prediction Intelligent algorithm optimized Bayesian network Improved particle swarm optimization 



We would like to express our sincere gratitude to the editor and anonymous referees for their insightful and constructive comments. This research has been supported by National Natural Science Foundation of China (Grant Nos. 71772065, 71472065), and Shanghai Pujiang Program (14PJC027).


  1. Antza C, Cifkova R, Kotsis V (2018) Hypertensive complications of pregnancy: a clinical overview. Metabolism 86:102–111CrossRefGoogle Scholar
  2. Arlot S, Celisse A (2010) A survey of cross-validation procedures for model selection. Stat Surveys 4:40–79MathSciNetzbMATHCrossRefGoogle Scholar
  3. Bai Y, Han X, Chen T et al (2015) Quadratic kernel-free least squares support vector machine for target diseases classification. J Comb Optim 30(4):850–870MathSciNetzbMATHCrossRefGoogle Scholar
  4. Bornmann L, Haunschild R, Hug SE (2018) Visualizing the context of citations referencing papers published by Eugene Garfield: a new type of keyword co-occurrence analysis. Scientometrics 114(2):427–437CrossRefGoogle Scholar
  5. Borsuk ME, Stow CA, Reckhow KH (2004) A Bayesian network of eutrophication models for synthesis, prediction, and uncertainty analysis. Ecol Model 173(2–3):219–239CrossRefGoogle Scholar
  6. Burgoslunar CD, Salinerofort MA, Cárdenasvalladolid J et al (2011) Validation of diabetes mellitus and hypertension diagnosis in computerized medical records in primary health care. BMC Med Res Methodol 11(1):146CrossRefGoogle Scholar
  7. Cooper GF, Herskovits E (1992) A Bayesian method for the induction of probabilistic networks from data. Mach Learn 9(4):309–347zbMATHGoogle Scholar
  8. Dagliati A, Marini S, Sacchi L et al (2018) Machine learning methods to predict diabetes complications. J Diabetes Sci Technol 12(2):295–302CrossRefGoogle Scholar
  9. Devereux RB, De SG, Ganau A et al (1993) Left ventricular hypertrophy associated with hypertension and its relevance as a risk factor for complications. J Cardiovasc Pharmacol 21(1):S38–44CrossRefGoogle Scholar
  10. Ding S, Li Z, Liu X et al (2019) Diabetic complication prediction using a similarity-enhanced latent Dirichlet allocation model. Inf Sci 499:12–24CrossRefGoogle Scholar
  11. Du G, Jiang Z, Diao X et al (2012) Knowledge extraction algorithm for variances handling of CP using integrated hybrid genetic double multi-group cooperative PSO and DPSO. J Med Syst 36(2):979–994CrossRefGoogle Scholar
  12. Du G, Jiang Z, Diao X et al (2013) Intelligent ensemble T-S fuzzy neural networks with RCDPSO\_DM optimization for effective handling of complex clinical pathway variances. Comput Biol Med 43(6):613–634CrossRefGoogle Scholar
  13. Du G, Zheng L, Ouyang X (2019) Real-time scheduling optimization considering the unexpected events in home health care. J Comb Optim 37(1):196–220MathSciNetzbMATHCrossRefGoogle Scholar
  14. Feldman R, Dagan I (1995) Knowledge discovery in textual databases (KDT). KDD 95:112–117Google Scholar
  15. Frantz TL (2018) Blockmap: an interactive visualization tool for big-data networks. Comput Math Organ Theory 33:1–20Google Scholar
  16. Friedman N, Geiger D, Goldszmidt M (1997) Bayesian network classifiers. Mach Learn 29(2–3):131–163zbMATHCrossRefGoogle Scholar
  17. Gao W, Bao W, Zhou X (2019) Analysis of cough detection index based on decision tree and support vector machine. J Comb Optim 37(1):375–384MathSciNetzbMATHCrossRefGoogle Scholar
  18. Gheisari S, Meybodi MR, Dehghan M et al (2017) Bayesian network structure training based on a game of learning automata. Int J Mach Learn Cybern 8(4):1093–1105CrossRefGoogle Scholar
  19. Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1):29–36CrossRefGoogle Scholar
  20. Kahle D, Savitsky T, Schnelle S (2008) Rice university. STAT 631/ELEC 639: graphical models, junction tree algorithm [EB/OL]. Available at Accessed 21 Nov 2019
  21. Kim DH (2002) Bayesian and empirical Bayesian analysis under informative sampling. Sankhyā Indian J Stat Ser B 64(3):267–288MathSciNetzbMATHGoogle Scholar
  22. Kitson MT, Roberts SK, Colman JC et al (2015) Liver stiffness and the prediction of clinically significant portal hypertension and portal hypertensive complications. Scand J Gastroenterol 50(4):462–469CrossRefGoogle Scholar
  23. Koller D, Friedman N (2009) Probabilistic graphical models: principles and techniques. MIT press, CambridgezbMATHGoogle Scholar
  24. Kshirsagar AV, Chiu Y, Bomback AS et al (2010) A hypertension risk score for middle-aged and older adults. J Clin Hypertens 12(10):800–808CrossRefGoogle Scholar
  25. Kumar CA, Srinivas S (2010) Concept lattice reduction using fuzzy K-means clustering. Expert Syst Appl 37(3):2696–2704CrossRefGoogle Scholar
  26. Lee M, Entzminger L (2006) Risk factors of hypertension and correlates of blood pressure and mean arterial pressure among patients receiving health exams at the preventive medicine clinic, King Chulalongkorn Memorial Hospital, Thailand. J Med Assoc Thail 89(8):1213–1221Google Scholar
  27. Lee W, Lee J, Lee H et al (2014) Prediction of hypertension complications risk using classification techniques. Ind Eng Manag Syst 13(4):449–453Google Scholar
  28. Lee J, Lee W, Park IS et al (2016) Risk assessment for hypertension and hypertension complications incidences using a Bayesian network. IIE Trans Healthc Syst Eng 6(4):246–259CrossRefGoogle Scholar
  29. Lee J, Kwon RH, Kim HW et al (2018) A data-driven procedure of providing a health promotion program for hypertension prevention. Service Sci 10(3):289–301CrossRefGoogle Scholar
  30. Li J, Dong M, Ren Y et al (2015) How patient compliance impacts the recommendations for colorectal cancer screening. J Comb Optim 30(4):920–937MathSciNetzbMATHCrossRefGoogle Scholar
  31. Mensah GA (1999) Refining strategies for the prevention and control of hypertension and related complications. Ethn Disease 9(3):327–332Google Scholar
  32. Meyer M (2007) What do we know about innovation in nanotechnology? Some propositions about an emerging field between hype and path-dependency. Scientometrics 70(3):779–810CrossRefGoogle Scholar
  33. Ojha R, Ghadge A, Tiwari MK et al (2018) Bayesian network modelling for supply chain risk propagation. Int J Product Res 56(17):5795–5819CrossRefGoogle Scholar
  34. Parikh Nisha I (2008) A risk score for predicting near-term incidence of hypertension: the Framingham heart study. Ann Intern Med 148(2):102CrossRefGoogle Scholar
  35. Pearl J (1987) Evidential reasoning using stochastic simulation of causal models. Artif Intell 32(2):245–257MathSciNetzbMATHCrossRefGoogle Scholar
  36. Ponomariov B (2013) Government-sponsored university-industry collaboration and the production of nanotechnology patents in US universities. J Technol Transf 38(6):749–767CrossRefGoogle Scholar
  37. Qureshi AI, Suri MFK, Kirmani JF et al (2005) Is prehypertension a risk factor for cardiovascular diseases? Stroke J Cereb Circ 36(9):1859CrossRefGoogle Scholar
  38. Rachmani R, Levi Z, Slavachevski I et al (2010) Teaching patients to monitor their risk factors retards the progression of vascular complications in high-risk patients with type 2 diabetes mellitus-a randomized prospective study. Diabet Med 19(5):385–392CrossRefGoogle Scholar
  39. Ratnaweera A, Halgamuge SK, Watson HC (2004) Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients. IEEE Trans Evol Comput 8(3):240–255CrossRefGoogle Scholar
  40. Ropero RF, Renooij S, Van der Gaag LC (2018) Discretizing environmental data for learning Bayesian-network classifiers. Ecol Model 368:391–403CrossRefGoogle Scholar
  41. Shi Y, Eberhart RC (1999) Empirical study of particle swarm optimization. In: Proceedings of the 1999 congress on evolutionary computation-CEC99 (Cat. No. 99TH8406), vol 3. IEEE, pp 1945–1950Google Scholar
  42. Staessen JA, Wang JG, Thijs L (2001) Cardiovascular protection and blood pressure reduction: a meta-analysis. Lancet 358(9290):1305–1315CrossRefGoogle Scholar
  43. Tavana M, Abtahi AR, Di Caprio D et al (2018) An artificial neural network and Bayesian network model for liquidity risk assessment in banking. Neurocomputing 275:2525–2554CrossRefGoogle Scholar
  44. Vasan RS, Larson MG, Leip EP et al (2001) Impact of high-normal blood pressure on the risk of cardiovascular disease. N Engl J Med 11(2):31–31Google Scholar
  45. Wiysonge CUS, Blackett KN, Mbuagbaw JN (2004) Risk factors and complications of hypertension in Yaounde, Cameroon: cardiovascular topics. Cardiovasc J S Afr 15(5):215–219Google Scholar
  46. Wu Q (2010) Power load forecasts based on hybrid PSO with Gaussian and adaptive mutation and Wv-SVM. Expert Syst Appl 37(1):194–201CrossRefGoogle Scholar
  47. Yang Y, Luo S, Fan J et al (2019) Study on specialist outpatient matching appointment and the balance matching model. J Comb Optim 37(1):20–39MathSciNetzbMATHCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Gang Du
    • 1
  • Xi Liang
    • 1
  • Xiaoling Ouyang
    • 2
    Email author
  • Chunming Wang
    • 3
  1. 1.School of Business and Administration, Faculty of Economics and ManagementEast China Normal UniversityShanghaiChina
  2. 2.School of Economics, Faculty of Economics and ManagementEast China Normal UniversityShanghaiChina
  3. 3.Renji Hospital, School of MedicineShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations