Does group-based trajectory modeling estimate spurious trajectories?
Ontology highlight
ABSTRACT: Background
Group-based trajectory modelling (GBTM) is increasingly used to identify subgroups of individuals with similar patterns. In this paper, we use simulated and real-life data to illustrate that GBTM is susceptible to generating spurious findings in some circumstances. Methods
Six plausible scenarios, two of which mimicked published analyses, were simulated. Models with 1 to 10 trajectory subgroups were estimated and the model that minimized the Bayes criterion was selected. For each scenario, we assessed whether the method identified the correct number of trajectories, the correct shapes of the trajectories, and the mean number of participants of each trajectory subgroup. The performance of the average posterior probabilities, relative entropy and mismatch criteria to assess classification adequacy were compared. Results
Among the six scenarios, the correct number of trajectories was identified in two, the correct shapes in four and the mean number of participants of each trajectory subgroup in only one. Relative entropy and mismatch outperformed the average posterior probability in detecting spurious trajectories. Conclusion
Researchers should be aware that GBTM can generate spurious findings, especially when the average posterior probability is used as the sole criterion to evaluate model fit. Several model adequacy criteria should be used to assess classification adequacy. Supplementary Information
The online version contains supplementary material available at 10.1186/s12874-022-01622-9.
SUBMITTER: Mesidor M
PROVIDER: S-EPMC9281109 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Existing studies of quantitative electroencephalography (qEEG) as a prognostic tool after cardiac arrest (CA) use methods that ignore the longitudinal pattern of qEEG data, resulting in significant information loss and precluding analysis of clinically important temporal trends. We tested the utility of group-based trajectory modeling (GBTM) for qEEG classification, focusing on the specific example of suppression ratio (SR).We included comatose CA patients hospitalized from April 2010 to October 2014, excluding CA from trauma or neurological catastrophe. We used Persyst®v12 to generate SR trends and used semi-quantitative methods to choose appropriate sampling and averaging strategies. We used GBTM to partition SR data into different trajectories and regression associate trajectories with outcome. We derived a multivariate logistic model using clinical variables without qEEG to predict survival, then added trajectories and/or non-longitudinal SR estimates, and assessed changes in model performance.Overall, 289 CA patients had ?36 h of EEG yielding 10,404 h of data (mean age 57 years, 81 % arrested out-of-hospital, 33 % shockable rhythms, 31 % overall survival, 17 % discharged to home or acute rehabilitation). We identified 4 distinct SR trajectories associated with survival (62, 26, 12, and 0 %, P < 0.0001 across groups) and CPC (35, 10, 4, and 0 %, P < 0.0001 across groups). Adding trajectories significantly improved model performance compared to adding non-longitudinal data.Longitudinal analysis of continuous qEEG data using GBTM provides more predictive information than analysis of qEEG at single time-points after CA.
| S-EPMC5045751 | biostudies-literature
Project description:BackgroundAs many local municipality and medical workers were involved in disaster recovery duties following the Great East Japan Earthquake (GEJE) on March 11, 2011, the aim of this work was to elucidate the distinct trajectories for post-traumatic stress disorder (PTSD) symptoms and associated factors among these personnel. They confronted a diverse range of stressors both as survivors and as relief workers; however, little is known about their longitudinal PTSD symptoms.MethodsThe participants were 745 local municipality and hospital medical workers [average age: 43.6 ± 9.5 years, range: 20 – 66 years; 306 (59%) women] involved in disaster recovery duties following the GEJE. PTSD symptoms were measured using the Japanese version of the PTSD Checklist Specific Version (PCL-S) at four time points: 14, 30, 43, and 54 months after the GEJE. Using group-based trajectory modeling, distinct trajectories were elucidated.ResultsWe identified five distinct PTSD symptoms profiles: resistance (n = 467, 62.7%), subsyndromal (n = 181, 24.3%), recovery (n = 47, 6.3%), fluctuating (n = 26, 3.5%), and chronic (n = 24, 3.2%). The trajectories differed according to the post-disaster working conditions and personal disaster experiences.LimitationsPotential selection bias resulting from the limited number of participants who completed all waves. The survey was conducted in one region of the disaster area.ConclusionsThe majority of participants remained stable, with a relatively small group classified as chronic and fluctuating. Our results highlight the importance of improved working conditions and sustained monitoring of workers responding to natural disasters.
| S-EPMC7261355 | biostudies-literature
Project description:BackgroundProportion of days covered (PDC), a commonly used adherence metric, does not provide information about the longitudinal course of adherence to treatment over time. Group-based trajectory model (GBTM) is an alternative method that overcomes this limitation.MethodsThe statistical principles of GBTM and PDC were applied to assess adherence during a 12-month follow-up in psoriasis patients starting treatment with a biologic. The optimal GBTM model was determined on the basis of the balance between each model's Bayesian information criterion and the percentage of patients in the smallest group in each model. Variables potentially predictive of adherence were evaluated.ResultsIn all, 3,249 patients were included in the analysis. Four GBTM adherence groups were suggested by the optimal model, and patients were categorized as demonstrating continuously high adherence, high-then-low adherence, moderate-then-low adherence, or consistently moderate adherence during follow-up. For comparison, four PDC groups were constructed: PDC Group 4 (PDC ?75%), PDC Group 3 (25%? PDC <50%), PDC Group 2 (PDC <25%), and PDC Group 1 (50%? PDC <75%). Our findings suggest that the majority of patients (97.9%) from PDC Group 2 demonstrated moderate-then-low adherence, whereas 96.4% of patients from PDC Group 4 showed continuously high adherence. The remaining PDC-based categorizations did not capture patients with uniform adherence behavior based on GBTM. In PDC Group 3, 25.3%, 17.2%, and 57.5% of patients exhibited GBTM-defined consistently moderate adherence, moderate-then-low adherence, or high-then-low adherence, respectively. In PDC Group 1, 70.8%, 23.6%, and 5.7% of patients had consistently moderate adherence, high-then-low adherence, and continuously high adherence, respectively. Additional analyses suggested GBTM-based categorization was best predicted by patient age, sex, certain comorbidities, and particular drug use.ConclusionGBTM is a more appropriate way to model dynamic behaviors and offers researchers an alternative to more traditional drug adherence measurements.
| S-EPMC3986333 | biostudies-literature
Project description:ObjectivesInflammatory bowel disease (IBD) is a heterogeneous group of chronic inflammatory gastrointestinal conditions with variable disease courses often requiring significant healthcare expenditures. We aimed to identify disease trajectory patterns based on longitudinal financial expenditures and to assess the association of classic disease activity parameters with financial charges.MethodsThis was an analysis of a consented, prospective, natural history IBD registry (2009-2013) from a tertiary IBD center of 2,203 patients and their associated medical charges excluding pharmacy expenses. We applied group-based trajectory modeling to longitudinal healthcare financial charges to determine patterns of charges. We assessed the association between charge patterns and disease activity, quality of life, healthcare utilization, and medication requirement.ResultsThe final model included 1,600 IBD patients with 5-year charges. We identified six distinct trajectories over the study period. Consistently High charges were associated with Crohn's disease (66.0% Consistently High patients, P<0.01), perianal involvement (22.6%, P<0.01), ulcerative colitis extent (89.7% extensive, P=0.01), prior IBD surgery (52.5%, P<0.01), and depression/anxiety (36.2%, P<0.01). Compared with other trajectories, Consistently High charges had higher 5-year disease activity indices (Harvey-Bradshaw P<0.01; ulcerative colitis activity index P<0.01), elevated C-reactive protein rates (72.3%, P<0.01), IBD surgery (64.5%, P<0.01), hospitalization (97.2%, P<0.01), corticosteroid (70.9%, P<0.01) and antitumor necrosis factor requirement (50.4%, P<0.01), and worse quality of life (P<0.01). Annual trends in parameters were reflected in temporal changes in financial charges. The majority of financial burden stemmed from inpatient care.ConclusionsHealthcare financial charges represent a novel phenotype in IBD that reflect trends in classic disease activity parameters and allow for subgroup identification of temporal disease trajectories.
| S-EPMC5543483 | biostudies-literature
Project description:BACKGROUND:Retention in HIV treatment must be improved to advance the HIV response, but research to characterize gaps in retention has focused on estimates from single time points and population-level averages. These approaches do not assess the engagement patterns of individual patients over time and fail to account for both their dynamic nature and the heterogeneity between patients. We apply group-based trajectory analysis-a special application of latent class analysis to longitudinal data-among new antiretroviral therapy (ART) starters in Zambia to identify groups defined by engagement patterns over time and to assess their association with mortality. METHODS AND FINDINGS:We analyzed a cohort of HIV-infected adults who newly started ART between August 1, 2013, and February 1, 2015, across 64 clinics in Zambia. We performed group-based multi-trajectory analysis to identify subgroups with distinct trajectories in medication possession ratio (MPR, a validated adherence metric based on pharmacy refill data) over the past 3 months and loss to follow-up (LTFU, >90 days late for last visit) among patients with at least 180 days of observation time. We used multinomial logistic regression to identify baseline factors associated with belonging to particular trajectory groups. We obtained Kaplan-Meier estimates with bootstrapped confidence intervals of the cumulative incidence of mortality stratified by trajectory group and performed adjusted Poisson regression to estimate adjusted incidence rate ratios (aIRRs) for mortality by trajectory group. Inverse probability weights were applied to all analyses to account for updated outcomes ascertained from tracing a random subset of patients lost to follow-up as of July 31, 2015. Overall, 38,879 patients (63.3% female, median age 35 years [IQR 29-41], median enrollment CD4 count 280 cells/?l [IQR 146-431]) were included in our cohort. Analyses revealed 6 trajectory groups among the new ART starters: (1) 28.5% of patients demonstrated consistently high adherence and retention; (2) 22.2% showed early nonadherence but consistent retention; (3) 21.6% showed gradually decreasing adherence and retention; (4) 8.6% showed early LTFU with later reengagement; (5) 8.7% had early LTFU without reengagement; and (6) 10.4% had late LTFU without reengagement. Identified groups exhibited large differences in survival: after adjustment, the "early LTFU with reengagement" group (aIRR 3.4 [95% CI 1.2-9.7], p = 0.019), the "early LTFU" group (aIRR 6.4 [95% CI 2.5-16.3], p < 0.001), and the "late LTFU" group (aIRR 4.7 [95% CI 2.0-11.3], p = 0.001) had higher rates of mortality as compared to the group with consistently high adherence/retention. Limitations of this study include using data observed after baseline to identify trajectory groups and to classify patients into these groups, excluding patients who died or transferred within the first 180 days, and the uncertain generalizability of the data to current care standards. CONCLUSIONS:Among new ART starters in Zambia, we observed 6 patient subgroups that demonstrated distinctive engagement trajectories over time and that were associated with marked differences in the subsequent risk of mortality. Further efforts to develop tailored intervention strategies for different types of engagement behaviors, monitor early engagement to identify higher-risk patients, and better understand the determinants of these heterogeneous behaviors can help improve care delivery and survival in this population.
| S-EPMC6818762 | biostudies-literature
Project description:BackgroundCo-occurrence of mental and somatic symptoms is common, and recent longitudinal studies have identified single trajectories of these symptoms, but it is poorly known whether the symptom trajectories can also co-occur and change across the lifespan. We aimed to examine co-occurring symptoms and their joint trajectories from adolescence to midlife.MethodsLongitudinal data were derived from Northern Sweden, where 506 girls and 577 boys aged 16 years participated at baseline in 1981 (99.7% of those initially invited), and have been followed up in four waves until the age of 43. Survey data were collected about depressive, anxiety, and somatic symptoms. Potential joint development of this three-component symptom set was examined with multiple response trajectory analysis, a method that has not been previously used to study co-occurrence of these symptoms.ResultsWe identified a five trajectory solution as the best: "very low" (19%), "low" (31%), "high" (22%), "late sharply increasing" (16%) and a "very high increasing" (12%). In the "late sharply increasing" and "very high increasing" groups the scores tended to increase with age, while in the other groups the levels were more stable. Overall, the results indicated that depressive, anxiety, and somatic symptoms co-exist from adolescence to midlife.ConclusionsThe multiple response trajectory analysis confirmed high stability in the co-occurrence of depressive, anxiety, and somatic symptoms from adolescence to midlife. Clinicians should consider these findings to detect symptoms in their earliest phase in order to prevent the development of co-occurring high levels of symptoms.
| S-EPMC6670180 | biostudies-literature
Project description:Hearing loss and cognitive impairments are both highly prevalent neurological complications for older adults. While there is growing evidence to suggest that these two conditions are interrelated, little research has been conducted that directly examines the progression and developmental trajectories of these complications contemporaneously. The aim of the study is to identify the distinct trajectory profiles for hearing loss and cognitive function in an older population over a 10-year period. Through dual trajectory modeling, the interrelationship, co-occurring movements, and overlaps between these two complications were examined. We also investigated the influence of hearing aid ownership on cognitive function trajectories. We utilized longitudinal data from 1,445 participants in the Blue Mountains Hearing Study (aged 55+ years) involving repeated measures from a population-based survey with audiometric hearing assessments. Cognitive function was assessed using the Mini-Mental State Examination (MMSE). The group-based trajectory modeling (GBTM) identified three trajectory profiles for both hearing loss and cognitive function in two older age groups (55-69 years and 70+ years). The outputs from the dual trajectories models showed the conditional probability for "no hearing loss" trajectories to be around 90% more likely to have "high-normal" cognitive function, demonstrating co-occurring overlap. In contrast, for "moderate to severe hearing loss" trajectories, the conditional probability drops to 65% and 79% for the 55-69 age group and 70+ age group respectively. There was also an increasing probability for "cognitive decline" conditional on the severity of hearing loss with 6.7%, 7.5%, and 8.7% for no hearing loss, mild hearing loss, and moderate to severe hearing loss trajectory groups. While we did not find any statistically significant difference in the influence of hearing aid use in the cognitive function trajectories, there was a consistent greater representation of non-hearing aid users in the trajectories with poorer cognitive function. This study found GBTM to identify trajectories that were in agreement with our current understanding of hearing loss and cognitive impairment in older adults. This study also adds to the existing evidence-base as dual trajectories demonstrated co-occurrence in developmental changes in these two common neurological complications for the older population.
| S-EPMC8740280 | biostudies-literature
Project description:Abstract Background Group?based trajectory modeling has been applied to identify distinct trajectories of growth across the life course. Objectives of this study were to describe the methodological approaches for group?based modeling of growth across the life course and to summarize outcomes across studies. Methods A scoping review with a systematic search of Medline, EMBASE, CINAL, and Web of Science was conducted. Studies that used a group?based procedure to identify trajectories on any statistical software were included. Data were extracted on trajectory methodology, measures of growth, and association with outcomes. Results A total of 59 studies were included, and most were published from 2013 to 2020. Body mass index was the most common measure of growth (n = 43). The median number of identified trajectories was 4 (range: 2–9). PROC TRAJ in SAS was used by 33 studies, other procedures used include TRAJ in STATA, lcmm in R, and Mplus. Most studies evaluated associations between growth trajectories and chronic disease outcomes (n = 22). Conclusions Group?based trajectory modeling of growth in adults is emerging in epidemiologic research, with four distinct trajectories observed somewhat consistently from all studies. Understanding life course growth trajectories may provide further insight for population health interventions.
| S-EPMC7909593 | biostudies-literature
Project description:BackgroundTo explore the long-term trajectories considering pneumonia volumes and lymphocyte counts with individual data in COVID-19.MethodsA cohort of 257 convalescent COVID-19 patients (131 male and 126 females) were included. Group-based multi-trajectory modelling was applied to identify different trajectories in terms of pneumonia lesion percentage and lymphocyte counts covering the time from onset to post-discharge follow-ups. We studied the basic characteristics and disease severity associated with the trajectories.ResultsWe characterised four distinct trajectory subgroups. (1) Group 1 (13.9%), pneumonia increased until a peak lesion percentage of 1.9% (IQR 0.7-4.4) before absorption. The slightly decreased lymphocyte rapidly recovered to the top half of the normal range. (2) Group 2 (44.7%), the peak lesion percentage was 7.2% (IQR 3.2-12.7). The abnormal lymphocyte count restored to normal soon. (3) Group 3 (26.0%), the peak lesion percentage reached 14.2% (IQR 8.5-19.8). The lymphocytes continuously dropped to 0.75 × 109/L after one day post-onset before slowly recovering. (4) Group 4 (15.4%), the peak lesion percentage reached 41.4% (IQR 34.8-47.9), much higher than other groups. Lymphopenia was aggravated until the lymphocytes declined to 0.80 × 109/L on the fourth day and slowly recovered later. Patients in the higher order groups were older and more likely to have hypertension and diabetes (all P values < 0.05), and have more severe disease.ConclusionsOur findings provide new insights to understand the heterogeneous natural courses of COVID-19 patients and the associations of distinct trajectories with disease severity, which is essential to improve the early risk assessment, patient monitoring, and follow-up schedule.
| S-EPMC8276845 | biostudies-literature
Project description:BackgroundPremenstrual dysphoric disorder (PMDD) is a new Diagnostic and Statistical Manual of Mental Disorders (DSM)-5 diagnosis characterized by the cyclical emergence of emotional and physical symptoms in the luteal phase of the menstrual cycle, with symptom remission in the follicular phase. Converging evidence highlights the possibility of distinct subtypes of PMDD with unique pathophysiologies, but temporal subgroups have yet to be explored in a systematic way.MethodsIn the current work, we use group-based trajectory modeling to identify unique trajectory subgroups of core emotional and total PMDD symptoms across the perimenstrual frame (days -14 to +9, where day 0 is menstrual onset) in a sample of 74 individuals prospectively diagnosed with DSM-5 PMDD.ResultsFor the total daily symptom score, the best-fitting model was comprised of three groups: a group demonstrating moderate symptoms only in the premenstrual week (65%), a group demonstrating severe symptoms across the full 2 weeks of the luteal phase (17.5%), and a group demonstrating severe symptoms in the premenstrual week that were slow to resolve in the follicular phase (17.5%).ConclusionsThese trajectory groups are discussed in the context of the latest work on the pathophysiology of PMDD. Experimental work is needed to test for the presence of possible pathophysiologic differences in trajectory groups, and whether unique treatment approaches are needed.
| S-EPMC8168625 | biostudies-literature