Keywords
Abstract
Objective: Systolic blood pressure (SBP) is a powerful prognostic factor in heart failure (HF) patients, which is associated with death and readmission. Therefore, control of blood pressure is an important element for managing these patients. The goal of this study was to compare the performance of classical and machine learning models for predicting SBP and identify important variables related to SBP changes over time.
Methods: The information of 483 HF patients was analyzed in this retrospective cohort study. These patients were hospitalized at least twice in Farshchian Heart Center Hamadan province, the west of Iran, between October 2015 and July 2019. We applied a linear mixed-effects model (LMM) and mixed-effects least-square support vector regression (MLS-SVR) for predicting SBP. The performance of both models was assessed by mean absolute error, and root mean squared error.
Results: Based on LMM results, there was a significant association between sex, body mass index (BMI), sodium, time, and history of hypertension with SBP changes over time (P-value <0.05). Also, MLS-SVR indicated that the four most important variables were history of hypertension, sodium, BMI, and triglyceride. The performance of MLS-SVR compared to LMM was better in both training and testing datasets.
Conclusions: According to our results, BMI, sodium, and history of hypertension were the important variables on SBP changes in both LMM and MLS-SVR models. Also, it seems that MLS-SVR can be used as an alternative for classical longitudinal models for predicting SBP in HF patients.
References
Ponikowski P, Voors AA, Anker SD, Bueno H, Cleland JG, Coats AJ, et al. 2016 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure: The Task Force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC) Developed with the special contribution of the Heart Failure Association (HFA) of the ESC. European heart journal. 2016;37(27):2129-200.
Najafi-Vosough R, Faradmal J, Hosseini SK, Moghimbeigi A, Mahjub H. Predicting hospital readmission in heart failure patients in Iran: a comparison of various machine learning methods. Healthcare informatics research. 2021;27(4):307-14. https://doi.org/10.4258/hir.2021.27.4.307.
López-Sendón J. The heart failure epidemic. Medicographia. 2011;33(4):363-9.
Mosterd A, Hoes AW. Clinical epidemiology of heart failure. Heart. 2007;93(9):1137-46. http://doi.org/10.1136/hrt.2003.025270.
Riegel B, Lee CS, Dickson VV. Self care in patients with chronic heart failure. Nature reviews cardiology. 2011;8(11):644.
Braunwald E. The war against heart failure: the Lancet lecture. The Lancet. 2015;385(9970):812-24. https://doi.org/10.1016/S0140-6736(14)61889-
Sahle BW, Owen AJ, Mutowo MP, Krum H, Reid CM. Prevalence of heart failure in Australia: a systematic review. BMC cardiovascular disorders. 2016;16(1):32. https://doi.org/10.1186/s12872-016-0208-4.
Bahrami M, Etemadifar S, Shahriari M, Farsani AK. Caregiver burden among Iranian heart failure family caregivers: A descriptive, exploratory, qualitative study. Iranian journal of nursing and midwifery research. 2014;19(1):56.
Raphael CE, Whinnett ZI, Davies J, Fontana M, Ferenczi E, Manisty CH, et al. Quantifying the paradoxical effect of higher systolic blood pressure on mortality in chronic heart failure. Heart. 2009;95(1):56-62. http://doi.org/10.1136/hrt.2007.134973.
Schmid FA, Schlager O, Keller P, Seifert B, Huang R, Fröhlich GM, et al. Prognostic value of long‐term blood pressure changes in patients with chronic heart failure. European journal of heart failure. 2017;19(7):837-42. https://doi.org/10.1002/ejhf.805.
Pocock SJ, Ariti CA, McMurray JJ, Maggioni A, Køber L, Squire IB, et al. Predicting survival in heart failure: a risk score based on 39 372 patients from 30 studies. European heart journal. 2013;34(19):1404-13. https://doi.org/10.1093/eurheartj/ehs337.
Lee TT, Chen J, Cohen DJ, Tsao L. The association between blood pressure and mortality in patients with heart failure. American heart journal. 2006;151(1):76-83. https://doi.org/10.1016/j.ahj.2005.03.009.
Desai RV, Banach M, Ahmed MI, Mujib M, Aban I, Love TE, et al. Impact of baseline systolic blood pressure on long-term outcomes in patients with advanced chronic systolic heart failure (insights from the BEST trial). The American journal of cardiology. 2010;106(2):221-7. https://doi.org/10.1016/j.amjcard.2010.02.032.
Lip GY, Skjøth F, Overvad K, Rasmussen LH, Larsen TB. Blood pressure and prognosis in patients with incident heart failure: the Diet, Cancer and Health (DCH) cohort study. Clinical Research in Cardiology. 2015;104(12):1088-96. https://doi.org/10.1007/s00392-015-0878-4.
Pinho-Gomes AC, Rahimi K. Management of blood pressure in heart failure. Heart. 2019;105(8):589-95. http://dx.doi.org/10.1136/heartjnl-2018-314438.
Cleland J, Swedberg K, Follath F, Komajda M, Cohen-Solal A, Aguilar JC, et al. The EuroHeart Failure survey programme—a survey on the quality of care among patients with heart failure in Europe: Part 1: patient characteristics and diagnosis. European heart journal. 2003;24(5):442-63. https://doi.org/10.1016/S0195-668X(02)00823-0.
Fakhri M, Sarokhani D, Ghiasi B, Dehkordi AH. Prevalence of Hypertension in Cardiovascular Disease in Iran: Systematic Review and Meta‑Analysis. International Journal of Preventive Medicine. 2020;1(4):11-56. https://doi.org/10.4103/ijpvm. IJPVM_351_18.
Group SR. A randomized trial of intensive versus standard blood-pressure control. New England Journal of Medicine. 2015;373(22):2103-16. https://doi.org/10.1056/NEJMoa1511939.
Sánchez-Gil J, Manzano L, Flather M, Formiga F, Martel AC, Molinero AM, et al. Combining heart rate and systolic blood pressure to improve risk stratification in older patients with heart failure: Findings from the RICA Registry. International Journal of Cardiology. 2017;230:625-9. https://doi.org/10.1016/j.ijcard.2016.12.041.
Moreno-González R, Formiga F, Lujan JMM, Chivite D, Ariza-Solé A, Corbella X. Usefulness of systolic blood pressure combined with heart rate measured on admission to identify 1-year all-cause mortality risk in elderly patients firstly hospitalized due to acute heart failure. Aging Clinical and Experimental Research. 2020;32(1):99-106. https://doi.org/10.1007/s40520-019-01153-2.
Gheorghiade M, Abraham WT, Albert NM, Greenberg BH, O’Connor CM, She L, et al. Systolic blood pressure at admission, clinical characteristics, and outcomes in patients hospitalized with acute heart failure. Jama. 2006;296(18):2217-26. https://doi:10.1001/jama.296.18.2217.
Canepa M, Siri G, Puntoni M, Latini R, Tavazzi L, Maggioni AP. Testing longitudinal data for prognostication in ambulatory heart failure patients with reduced ejection fraction. A proof of principle from the GISSI-HF database. International Journal of Cardiology. 2020;313(15):89-96. https://doi.org/10.1016/j.ijcard.2020.03.064.
Stevens SL, Wood S, Koshiaris C, Law K, Glasziou P, Stevens RJ, et al. Blood pressure variability and cardiovascular disease: systematic review and meta-analysis. bmj. 2016;354:i4098. https://doi.org/10.1136/bmj.i4098.
Ohkuma T, Woodward M, Jun M, Muntner P, Hata J, Colagiuri S, et al. Prognostic value of variability in systolic blood pressure related to vascular events and premature death in type 2 diabetes mellitus: the ADVANCE-ON study. Hypertension. 2017;70(2):461-8. https://doi.org/10.1161/HYPERTENSIONAHA.117.09359.
Lacson RC, Baker B, Suresh H, Andriole K, Szolovits P, Lacson Jr E. Use of machine-learning algorithms to determine features of systolic blood pressure variability that predict poor outcomes in hypertensive patients. Clinical kidney journal. 2019;12(2):206-12. https://doi.org/10.1093/ckj/sfy049.
Böhm M, Robertson M, Borer J, Ford I, Komajda M, Mahfoud F, et al. Effect of Visit‐to‐Visit Variation of Heart Rate and Systolic Blood Pressure on Outcomes in Chronic Systolic Heart Failure: Results From the Systolic Heart Failure Treatment With the I f Inhibitor Ivabradine Trial (SHIFT) Trial. Journal of the American Heart Association. 2016;5(2):e002160. https://doi.org/10.1161/JAHA.115.002160.
Biton Y, Moss AJ, Kutyifa V, Mathias A, Sherazi S, Zareba W, et al. Inverse relationship of blood pressure to long-term outcomes and benefit of cardiac resynchronization therapy in patients with mild heart failure: a multicenter automatic defibrillator implantation trial with cardiac resynchronization therapy long-term follow-up substudy. Circulation: Heart Failure. 2015;8(5):921-6. https://doi.org/10.1161/CIRCHEARTFAILURE.115.002208.
Nuotio J, Suvila K, Cheng S, Langén V, Niiranen T. Longitudinal blood pressure patterns and cardiovascular disease risk. Annals of Medicine. 2020;52(3-4):43-54. https://doi.org/10.1080/07853890.2020.1733648.
Hedeker D, Gibbons RD. Longitudinal data analysis: John Wiley & Sons; 2006.
Amiri MM, Tapak L, Faradmal J, Hosseini J, Roshanaei G. Prediction of Serum Creatinine in Hemodialysis Patients Using a Kernel Approach for Longitudinal Data. Healthcare Informatics Research. 2020;26(2):112-8. https://doi.org/10.4258/hir.2020.26.2.112.
Moqaddasi Amiri M, Tapak L, Faradmal J. A mixed-effects least square support vector regression model for three-level count data. Journal of Statistical Computation and Simulation. 2019;89(15):2801-12. https://doi.org/10.1080/00949655.2019.1636991.
Cho D. Mixed-effects LS-SVM for longitudinal data. Journal of the Korean Data & Information Science Society. 2010;21:363-9.
Shah SJ, Katz DH, Selvaraj S, Burke MA, Yancy CW, Gheorghiade M, et al. Phenomapping for novel classification of heart failure with preserved ejection fraction. Circulation. 2015;131(3):269-79. https://doi.org/10.1161/CIRCULATIONAHA.114.010637.
Ahmad T, Lund LH, Rao P, Ghosh R, Warier P, Vaccaro B, et al. Machine learning methods improve prognostication, identify clinically distinct phenotypes, and detect heterogeneity in response to therapy in a large cohort of heart failure patients. Journal of the American Heart Association. 2018;7(8):e008081. https://doi.org/10.1161/JAHA.117.008081.
Jing L, Cerna AEU, Good CW, Sauers NM, Schneider G, Hartzel DN, et al. A Machine Learning Approach to Management of Heart Failure Populations. JACC: Heart Failure. 2020;8(7):578-87.
Seok KH, Shim J, Cho D, Noh G-J, Hwang C. Semiparametric mixed-effect least squares support vector machine for analyzing pharmacokinetic and pharmacodynamic data. Neurocomputing. 2011;74(17):3412-9. https://doi.org/10.1016/j.neucom.2011.05.012.
Zhang H, Singer BH. Recursive partitioning and applications: Springer Science & Business Media; 2010.
Sacks FM, Campos H. Dietary therapy in hypertension. New England journal of medicine. 2010;362(22):2102-12. https://doi.org/10.1056/NEJMct0911013.
Svetkey L, Erlinger T, Vollmer W, Feldstein A, Cooper L, Appel L, et al. Effect of lifestyle modifications on blood pressure by race, sex, hypertension status, and age. Journal of human hypertension. 2005;19(1):21-31.
Grillo A, Salvi L, Coruzzi P, Salvi P, Parati G. Sodium intake and hypertension. Nutrients. 2019;11(9):1970. https://doi.org/10.3390/nu11091970.
Aronow WS, Shamliyan TA. Dietary sodium interventions to prevent hospitalization and readmission in adults with congestive heart failure. The American Journal of Medicine. 2018;131(4):365-70. https://doi.org/10.1016/j.amjmed.2017.12.014
Poorolajal J, Farbakhsh F, Mahjub H, Bidarafsh A, Babaee E. How much excess body weight, blood sugar, or age can double the risk of hypertension? Public Health. 2016;133:14-8. https://doi.org/10.1016/j.puhe.2015.10.014.
Drøyvold W, Midthjell K, Nilsen T, Holmen J. Change in body mass index and its impact on blood pressure: a prospective population study. International journal of obesity. 2005;29(6):650-5.
Ji H, Kim A, Ebinger JE, Niiranen TJ, Claggett BL, Merz CNB, et al. Sex differences in blood pressure trajectories over the life course. JAMA cardiology. 2020;5(3):19-26. https://doi.org/10.1001/jamacardio.2019.5306.
Huldani SK, Adiputro DL, Achmad H, Sukmana BI, Putri DKT, Wasiaturrahmah Y. Effect of Total Cholesterol Levels and Triglycerides on Blood Pressure Hypertension Patients Overview against Puskesmas Banjar Ethnic Group in Cempaka Banjarmasin. Systematic Reviews in Pharmacy. 2020;11(4):384-9.
Xu L, Huang J, Zhang Z, Qiu J, Guo Y, Zhao H, et al. Bioinformatics Study on Serum Triglyceride Levels for Analysis of a Potential Risk Factor Affecting Blood Pressure Variability. Current Bioinformatics. 2019;14(5):376-85. https://doi.org/10.2174/1574893614666190109152809.
O'Neill S, O'Driscoll L. Metabolic syndrome: a closer look at the growing epidemic and its associated pathologies. Obesity reviews. 2015;16(1):1-12. https://doi.org/10.1111/obr.12229.
Shim J, Sohn I, Hwang C. Kernel-based random effect time-varying coefficient model for longitudinal data. Neurocomputing. 2017;267:500-7. https://doi.org/10.1016/j.neucom.2017.06.039.