Statistical Methods for Longitudinal Cardiovascular Disease Research Design: A Narrative Review

Abstract

Cardiovascular disease develops through gradual accumulation of risk factors and progressive vascular damage. Longitudinal studies are well suited to determine when and how these changes occur, but they introduce several analytic challenges, including repeated measurements on the same individuals, irregular or sparse follow-up schedules, missing data, and non-linear trajectories. We conducted a narrative, application-focused review categorizing methods into five major classes: traditional or marginal models, mixed-effect models, joint models, trajectory and mixture models, and functional or machine-learning approaches. For each class, we provide intuitive descriptions, typical cardiovascular applications, and a balanced discussion of assumptions, strengths, limitations, and recommended sensitivity analyses. We emphasize practical guidance for method selection, model validation, and transparent reporting. In summary, no single method addresses every research goal. The analytic strategy should fit both the clinical question and data characteristics, with clear definition of objectives, careful assessment of assumptions, appropriate handling of missing data, and validation on independent samples whenever possible. Future methodological development should focus on making hybrid models more accessible, improving integration of sparse and dense data sources, and advancing reporting standards for longitudinal cardiovascular research.

Keywords

Cardiovascular disease / Longitudinal design / Traditional marginal models / Mixed-effects regression / Joint models / Trajectory analytic methods / Functional and machine-learning approaches

References

[1] Global Burden of Cardiovascular Diseases andRisks 2023 Collaborators. Global, regional, and national burden of cardiovascular diseases and risk factors in 204 countries and territories, 1990-2023. J Am Coll Cardiol. 2025. Vol. 86(22):2167-243

[2] Mensah GA, Fuster V, Murray CJL, Roth GA; Risks Collaborators. Global Burden of Cardiovascular Diseases and Global burden of cardiovascular diseases and risks, 1990-2022. J Am Coll Cardiol. 2023. Vol. 82(25):2350-473

[3] Meng Y, Sharman JE, Koskinen JS, Juonala M, Viikari JSA, Buscot MJ, et al.. Blood pressure at different life stages over the early life course and intima-media thickness. JAMA Pediatr. 2024. Vol. 178(2):133-41

[4] Shang X, Zhang X, Huang Y, Zhu Z, Zhang X, Liu S, et al.. Temporal trajectories of important diseases in the life course and premature mortality in the UK Biobank. BMC Med. 2022. Vol. 20(1):185

[5] Flores M, Wolfe BL. The influence of early-life health conditions on life course health. Demography. 2023. Vol. 60(2):431-59

[6] VanderWeele TJ, Jackson JW, Li S. Causal inference and longitudinal data: a case study of religion and mental health. Soc Psychiatry Psychiatr Epidemiol. 2016. Vol. 51(11):1457-66

[7] Jones L, Barnett A, Vagenas D. Common misconceptions held by health researchers when interpreting linear regression assumptions, a cross-sectional study. PLoS One. 2025. Vol. 20(6):e0299617

[8] Rabe-Hesketh S, Skrondal A.Ignoring non-ignorable missingness. Psychometrika. 2023. Vol. 88(1):31-50

[9] Yang X, Li J, Shoptaw S. Imputation-based strategies for clinical trial longitudinal data with nonignorable missing values. Stat Med. 2008. Vol. 27(15):2826-49

[10] Pullenayegum EM, Lim LS. Longitudinal data subject to irregular observation: a review of methods with a focus on visit processes, assumptions, and study design. Stat Methods Med Res. 2016. Vol. 25(6):2992-3014

[11] Chen Y, Ning J, Cai C. Regression analysis of longitudinal data with irregular and informative observation times. Biostatistics. 2015. Vol. 16(4):727-39

[12] Schober P, Vetter TR. Repeated measures designs and analysis of longitudinal data: if at first you do not succeed-try, try again. Anesth Analg. 2018. Vol. 127(2):569-75

[13] Carr GJ, Chi EM. Analysis of variance for repeated measures. Data: a generalized estimating equations approach. Stat Med. 1992. Vol. 11(8):1033-40

[14] Keselman HJ, Algina J, Kowalchuk RK. The analysis of repeated measures designs: a review. Br J Math Stat Psychol. 2001. Vol. 54(Pt 1):1-20

[15] Ludbrook J. Repeated measurements and multiple comparisons in cardiovascular research. Cardiovasc Res. 1994. Vol. 28(3):303-11

[16] Saraf-Bank S, Esmaillzadeh A, Faghihimani E, Azadbakht L. Effects of legume-enriched diet on cardiometabolic risk factors among individuals at risk for diabetes: a crossover study. J Am Coll Nutr. 2016. Vol. 35(1):31-40

[17] Zeger SL, Liang KY, Albert PS. Models for longitudinal data: a generalized estimating equation approach. Biometrics. 1988. Vol. 44(4):1049-60

[18] Chang YC. Residuals analysis of the generalized linear models for longitudinal data. Stat Med. 2000. Vol. 19(10):1277-93

[19] Prentice RL. Correlated binary regression with covariates specific to each binary observation. Biometrics. 1988. Vol. 44(4):1033-48

[20] Lipsitz SR, Fitzmaurice GM, Orav EJ, Laird NM. Performance of generalized estimating equations in practical situations. Biometrics. 1994. Vol. 50(1):270-8

[21] Wang C, Liu S, Miao W, Ye N, Xie Z, Qiao L, et al.. Intensive blood pressure control in isolated systolic hypertension: a post hoc analysis of a cluster randomized trial. Lancet Reg Health West Pac. 2024. Vol. 48:101127

[22] Laird NM, Ware JH.Random-effects models for longitudinal data. Biometrics. 1982. Vol. 38(4):963-74

[23] Li G, Xu S, Pan S, Shao H, Gaskins AJ, Zhang Y, et al.. Hypertension and semen quality among 1381 young men: a cohort study with repeated measurements. Innov Med. 2024. Vol. 2(4):100099

[24] Breslow NE, Clayton DG. Approximate inference in generalized linear mixed models. J Am Stat Assoc. 1993. Vol. 88(421):9-25

[25] Tuerlinckx F, Rijmen F, Verbeke G, De Boeck P. Statistical inference in generalized linear mixed models: a review. Br J Math Stat Psychol. 2006. Vol. 59(Pt 2):225-55

[26] Bergeman AT, Lieve KVV, Kallas D, Bos JM, Rosés I, Noguer F, et al.. Flecainide is associated with a lower incidence of arrhythmic events in a large cohort of patients with catecholaminergic polymorphic ventricular tachycardia. Circulation. 2023. Vol. 148(25):2029-37

[27] Pinheiro JC, Bates DM. Mixed-effects models in S and S-PLUS. New York: Springer. 2000

[28] Davidian M, Giltinan DM. Some general estimation methods for nonlinear mixed-effects models. J Biopharm Stat. 1993. Vol. 3(1):23-55

[29] Lindstrom ML, Bates DM. Nonlinear mixed effects models for repeated measures data. Biometrics. 1990. Vol. 46(3):673-87

[30] van Rijn-Bikker PC, Snelder N, Ackaert O, van Hest RM, Ploeger BA, van Montfrans GA, et al.. Nonlinear mixed effects modeling of the diurnal blood pressure profile in a multiracial population. Am J Hypertens. 2013. Vol. 26(9):1103-13

[31] Wulfsohn MS, Tsiatis AA. A joint model for survival and longitudinal data measured with error. Biometrics. 1997. Vol. 53(1):330-9

[32] Ibrahim JG, Chu H, Chen LM. Basic concepts and methods for joint models of longitudinal and survival data. J Clin Oncol. 2010. Vol. 28(16):2796-801

[33] Fisher LD, Lin DY. Time-dependent covariates in the Cox proportional-hazards regression model. Annu Rev Public Health. 1999. Vol. 20:145-57

[34] Putter H, van Houwelingen HC. Understanding landmarking and its relation with time-dependent Cox regression. Stat Biosci. 2017. Vol. 9(2):489-503

[35] Henderson R, Diggle P, Dobson A. Joint modelling of longitudinal measurements and event time data. Biostatistics. 2000. Vol. 1(4):465-80

[36] Rizopoulos D. Dynamic predictions and prospective accuracy in joint models for longitudinal and time-to-event data. Biometrics. 2011. Vol. 67(3):819-29

[37] Domanski MJ, Tian X, Wu CO, Reis JP, Dey AK, Gu Y, et al.. Time course of LDL cholesterol exposure and cardiovascular disease event risk. J Am Coll Cardiol. 2020. Vol. 76(13):1507-16

[38] Meredith W, Tisak J.Latent curve analysis. Psychometrika. 1990. Vol. 55:107-22

[39] Felt JM, Depaoli S, Tiemensma J. Latent growth curve models for biomarkers of the stress response. Front Neurosci. 2017. Vol. 11:315

[40] Pai HC, Lai MY, Chen AC, Lin PS. Change in activities of daily living in the year following a stroke: a latent growth curve analysis. Nurs Res. 2018. Vol. 67(4):286-93

[41] Nagin DS. Analyzing developmental trajectories: a semiparametric, group-based approach. Psychol Methods. 1999. Vol. 4(2):139-57

[42] Nagin DS, Odgers CL. Group-based trajectory modeling in clinical research. Annu Rev Clin Psychol. 2010. Vol. 6:109-38

[43] Liu Y, Chen X, Li C, Fan B, Lv J, Qu Y, et al.. Life-course blood pressure trajectories and incident diabetes: a longitudinal cohort in a Chinese population. Front Endocrinol (Lausanne). 2022. Vol. 13:1035890

[44] Muthen B, Shedden K. Finite mixture modeling with mixture outcomes using the EM algorithm. Biometrics. 1999. Vol. 55(2):463-9

[45] Muthen B, Muthén LK. Integrating person-centered and variable-centered analyses: growth mixture modeling with latent trajectory classes. Alcohol Clin Exp Res. 2000. Vol. 24(6):882-91

[46] Tielemans SM, Geleijnse JM, Menotti A, Boshuizen HC, Soedamah-Muthu SS, Jacobs DR Jr, et al.. Ten-year blood pressure trajectories, cardiovascular mortality, and life years lost in 2 extinction cohorts: the Minnesota Business and Professional Men Study and the Zutphen Study. J Am Heart Assoc. 2015. Vol. 4(3):e001378

[47] Proust-Lima C, Phillipps V, Liquet B. Estimation of extended mixed models using latent classes and latent processes: the R Package lcmm. J Stat Softw. 2017. Vol. 78(2):1-56

[48] Fan B, Yang Y, Dayimu A, Zhou G, Liu Y, Li S, et al.. Body mass index trajectories during young adulthood and incident hypertension: a longitudinal cohort in Chinese population. J Am Heart Assoc. 2019. Vol. 8(8):e011937

[49] Ramsay JO, Silverman BW. Principal components analysis for functional dataFunctional data analysis. Springer series in statistics. New York: Springer. 1997

[50] Ramsay JO, Silverman BW. Functional data analysis. 2nd ed. New York: Springer. 2005

[51] Gertheiss J, Rugamer D, Liew BXW, Greven S. Functional data analysis: an introduction and recent developments. Biom J. 2024. Vol. 66(7):e202300363

[52] Guo W. Functional data analysis in longitudinal settings using smoothing splines. Stat Methods Med Res. 2004. Vol. 13(1):49-62

[53] Wrobel J, Muschelli J, Leroux A. Diurnal physical activity patterns across ages in a large UK based cohort: the UK Biobank Study. Sensors (Basel). 2021. Vol. 21(4):1545

[54] Hochreiter S, Schmidhuber J.Long short-term memory. Neural Comput. 1997. Vol. 9(8):1735-80

[55] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al..Attention is all you need. Adv Neural Inf Process Syst. 2017. Vol. 30:5998-6008

[56] Dai J, Xu H, Chen T, Huang T, Liang W, et al.. Artificial intelligence for medicine 2025: navigating the endless frontier. Innov Med. 2025. Vol. 3(1):100120

[57] Diggle P, Heagerty P, Liang K, Zeger S. Analysis of longitudinal data. 2nd ed. Oxford University Press. 2002

[58] Serroyen J, Molenberghs G, Verbeke G, Davidian M.Non-linear models for longitudinal data. Am Stat. 2009. Vol. 63(4):378-88

[59] Rizopoulos D. Joint models for longitudinal and time-to-event data: with applications in R. Boca Raton, FL: Chapman and Hall/CRC Press. 2012

[60] Fitzmaurice GM, Laird NM, Ware JH. Applied longitudinal analysis. 2nd ed. Hoboken, New Jersey: John Wiley & Sons, Inc. 2011

[61] Miettunen J, Nordstrom T, Kaakinen M, Ahmed AO. Latent variable mixture modeling in psychiatric research -a review and application. Psychol Med. 2016. Vol. 46(3):457-67

[62] Slaughter JC, Herring AH, Thorp JM. A Bayesian latent variable mixture model for longitudinal fetal growth. Biometrics. 2009. Vol. 65(4):1233-42

[63] Dhana K, van Rosmalen J, Vistisen D, Ikram MA, Hofman A, Franco OH, et al.. Trajectories of body mass index before the diagnosis of cardiovascular disease: a latent class trajectory analysis. Eur J Epidemiol. 2016. Vol. 31(6):583-92

[64] Girden ER. ANOVA: repeated measures. Newbury Park, CA: Sage. 1992

[65] Field A. Discovering statistics using IBM SPSS statistics: and sex and drugs and rock “N” roll. 4th ed. Los Angeles, London, New Delhi: Sage. 2013

[66] Cnaan A, Laird NM, Slasor P. Using the general linear mixed model to analyse unbalanced repeated measures and longitudinal data. Stat Med. 1997. Vol. 16(20):2349-80

[67] Pan W. Akaike’s information criterion in generalized estimating equations. Biometrics. 2001. Vol. 57(1):120-5

[68] Proust-Lima C, Séne M, Taylor JM, Jacqmin-Gadda H. Joint latent class models for longitudinal and time-to-event data: a review. Stat Methods Med Res. 2014. Vol. 23(1):74-90

[69] Kim SY. Determining the number of latent classes in single-and multi-phase growth mixture models. Struct Equ Modeling. 2014. Vol. 21(2):263-79

[70] Harrell FE. Regression modeling strategies: with applications to linear models, logistic and ordinal regression, and survival analysis. 2nd ed. Cham: Springer. 2015

[71] Steyerberg EW. Clinical prediction models: a practical approach to development, validation, and updating. 2nd ed. Cham: Springer. 2019

[72] Oulhaj A, Aziz F, Suliman A, Iqbal N, Coleman RL, Holman RR, et al.. Joint longitudinal and time-to-event modelling compared with standard Cox modelling in patients with type 2 diabetes with and without established cardiovascular disease: an analysis of the EXSCEL trial. Diabetes Obes Metab. 2023. Vol. 25(5):1261-70

[73] Yang L, Yu M, Gao S. Prediction of coronary artery disease risk based on multiple longitudinal biomarkers. Stat Med. 2016. Vol. 35(8):1299-314

[74] Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, et al.. A guide to deep learning in healthcare. Nat Med. 2019. Vol. 25(1):24-9

[75] Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N, Hardt M, et al.. Scalable and accurate deep learning with electronic health records. NPJ Digit Med. 2018. Vol. 1:18

[76] Hastie T, Tibshirani R, Friedman J. The elements of statistical learning: data mining, inference, and prediction. 2nd ed. New York, NY: Springer. 2009

[77] Beam AL, Kohane IS. Big data and machine learning in health care. JAMA. 2018. Vol. 319(13):1317-8

[78] Van Calster B, McLernon DJ, van Smeden M, Wynants L, Steyerberg EW. Calibration: the Achilles heel of predictive analytics. BMC Med. 2019. Vol. 17:230

[79] Johnson KW, Shameer K, Glicksberg BS, Readhead B, Sengupta PP, Bjorkegren JLM, et al.. Enabling precision cardiology through multiscale biology and systems medicine. JACC Basic Transl Sci. 2017. Vol. 2(3):311-27

[80] Inouye M, Abraham G, Nelson CP, Wood AM, Sweeting MJ, Dudbridge F, et al.. Genomic risk prediction of coronary artery disease in 480,000 adults: implications for primary prevention. J Am Coll Cardiol. 2018. Vol. 72(16):1883-93

[81] Hasin Y, Seldin M, Lusis A.Multi-omics approaches to disease. Genome Biol. 2017. Vol. 18(1):83

[82] Barabasi AL, Gulbahce N, Loscalzo J. Network medicine: a network-based approach to human disease. Nat Rev Genet. 2011. Vol. 12(1):56-68

[83] Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019. Vol. 25(1):44-56

[84] Andersen PK, Keiding N. Multi-state models for event history analysis. Stat Methods Med Res. 2002. Vol. 11(2):91-115

[85] Putter H, Fiocco M, Geskus RB. Tutorial in biostatistics: competing risks and multi-state models. Stat Med. 2007. Vol. 26(1):2389-430

[86] Hougaard P.Multi-state models: a review. Lifetime Data Anal. 1999. Vol. 5(3):239-64