In medical research, missing data is common. In acute diseases, such as traumatic brain injury (TBI), even well-conducted prospective studies may suffer from missing data in baseline... Show moreIn medical research, missing data is common. In acute diseases, such as traumatic brain injury (TBI), even well-conducted prospective studies may suffer from missing data in baseline characteristics and outcomes. Statistical models may simply drop patients with any missing values, potentially leaving a selected subset of the original cohort. Imputation is widely accepted by methodologists as an appropriate way to deal with missing data. We aim to provide practical guidance on handling missing data for prediction modeling. We hereto propose a five-step approach, centered around single and multiple imputation: 1) explore the missing data patterns; 2) choose a method of imputation; 3) perform imputation; 4) assess diagnostics of the imputation; and 5) analyze the imputed data sets. We illustrate these five steps with the estimation and validation of the IMPACT (International Mission on Prognosis and Analysis of Clinical Trials in Traumatic Brain Injury) prognostic model in 1375 patients from the CENTER-TBI database, included in 53 centers across 17 countries, with moderate or severe TBI in the prospective European CENTER-TBI study. Future prediction modeling studies in acute diseases may benefit from following the suggested five steps for optimal statistical analysis and interpretation, after maximal effort has been made to minimize missing data. Show less
Loss to follow-up and missing outcomes data are important issues for longitudinal observational studies and clinical trials in traumatic brain injury. One popular solution to missing 6-month... Show moreLoss to follow-up and missing outcomes data are important issues for longitudinal observational studies and clinical trials in traumatic brain injury. One popular solution to missing 6-month outcomes has been to use the last observation carried forward (LOCF). The purpose of the current study was to compare the performance of model-based single-imputation methods with that of the LOCF approach. We hypothesized that model-based methods would perform better as they potentially make better use of available outcome data. The Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study (n = 4509) included longitudinal outcome collection at 2 weeks, 3 months, 6 months, and 12 months post-injury; a total of 8185 Glasgow Outcome Scale extended (GOSe) observations were included in the database. We compared single imputation of 6-month outcomes using LOCF, a multiple imputation (MI) panel imputation, a mixed-effect model, a Gaussian process regression, and a multi-state model. Model performance was assessed via cross-validation on the subset of individuals with a valid GOSe value within 180 +/- 14 days post-injury (n = 1083). All models were fit on the entire available data after removing the 180 +/- 14 days post-injury observations from the respective test fold. The LOCF method showed lower accuracy (i.e., poorer agreement between imputed and observed values) than model-based methods of imputation, and showed a strong negative bias (i.e., it imputed lower than observed outcomes). Accuracy and bias for the model-based approaches were similar to one another, with the multi-state model having the best overall performance. All methods of imputation showed variation across different outcome categories, with better performance for more frequent outcomes. We conclude that model-based methods of single imputation have substantial performance advantages over LOCF, in addition to providing more complete outcome data. Show less
Loss to follow-up or patient attrition is common in longitudinal studies of traumatic brain injury (TBI). Lack of understanding exists between the relation of study design and patient attrition.... Show moreLoss to follow-up or patient attrition is common in longitudinal studies of traumatic brain injury (TBI). Lack of understanding exists between the relation of study design and patient attrition. This review aimed to identify features of study design that are associated with attrition. We extended the analysis of a previous systematic review on missing data in 195 TBI studies using the Glasgow Outcome Scale Extended (GOSE) as an outcome measure. Studies that did not report attrition or had heterogeneous methodology were excluded, leaving 148 studies. Logistic regression found seven of the 14 design features studied to be associated with patient attrition. Four features were associated with an increase in attrition: greater follow-up frequency (odds ratio [OR]: 1.2, 95% confidence interval [CI]: 1.0-1.3), single rather than multi-center design (OR: 1.6, 95% CI: 1.2-2.2), enrollment of exclusively mild TBI patients (OR: 2.8, 95% CI: 1.6-4.9), and collection of the GOS by post or telephone without face-to-face contact (OR: 1.6, 95% CI:1.1-2.4). Conversely, two features were associated with a reduction in attrition: recruitment in an acute care setting defined as the ward or intensive care unit (OR: 0.58, 95% CI: 0.47-0.72) and a greater duration of time between injury and follow-up (OR: 0.93, 95% CI: 0.88-0.99). This review highlights design features that are associated with attrition and could be considered when planning for patient retention. Further work is needed to establish the mechanisms between the observed associations and potential remedies. Show less