Framework to construct and interpret latent class trajectory modelling

• Published in: BMJ open Vol. 8; no. 7; p. e020683
• Main Authors: Lennon, Hannah, Kelly, Scott, Sperrin, Matthew, Buchan, Iain, Cross, Amanda J, Leitzmann, Michael, Cook, Michael B, Renehan, Andrew G
• Format: Journal Article
• Language: English
• Published: England BMJ Publishing Group LTD 07.07.2018; BMJ Publishing Group
• Subjects: Adolescent; Adult; Body Mass Index; Body Weight; Cohort Studies; Diet; Epidemiology; Female; Humans; Latent Class Analysis; Life Style; Male; Mental Recall; Middle Aged; Mortality; Obesity; Research Methods; Risk Factors; Surveys and Questionnaires; United States; Young Adult; United States; United States > US; growth mixture models; latent class models; lifetime obesity; trajectories; growth curves
• ISSN: 2044-6055; 2044-6055
• DOI: 10.1136/bmjopen-2017-020683

ObjectivesLatent class trajectory modelling (LCTM) is a relatively new methodology in epidemiology to describe life-course exposures, which simplifies heterogeneous populations into homogeneous patterns or classes. However, for a given dataset, it is possible to derive scores of different models based on number of classes, model structure and trajectory property. Here, we rationalise a systematic framework to derive a ‘core’ favoured model.MethodsWe developed an eight-step framework: step 1: a scoping model; step 2: refining the number of classes; step 3: refining model structure (from fixed-effects through to a flexible random-effect specification); step 4: model adequacy assessment; step 5: graphical presentations; step 6: use of additional discrimination tools (‘degree of separation’; Elsensohn’s envelope of residual plots); step 7: clinical characterisation and plausibility; and step 8: sensitivity analysis. We illustrated these steps using data from the NIH-AARP cohort of repeated determinations of body mass index (BMI) at baseline (mean age: 62.5 years), and BMI derived by weight recall at ages 18, 35 and 50 years.ResultsFrom 288 993 participants, we derived a five-class model for each gender (men: 177 455; women: 111 538). From seven model structures, the favoured model was a proportional random quadratic structure (model F). Favourable properties were also noted for the unrestricted random quadratic structure (model G). However, class proportions varied considerably by model structure—concordance between models F and G were moderate (Cohen κ: men, 0.57; women, 0.65) but poor with other models. Model adequacy assessments, evaluations using discrimination tools, clinical plausibility and sensitivity analyses supported our model selection.ConclusionWe propose a framework to construct and select a ‘core’ LCTM, which will facilitate generalisability of results in future studies.