Table 4 Issues in model development^a

Sample size, median (IQR)

   Development cohort^b

2,562 (1,426 to 4,965)

   Validation cohorts^c

1,895 (1,253 to 4,398)

Treatment of continuous risk predictors, n (%)

   All kept continuous

13 (30%)

   All categorised/dichotomised

21 (49%)

   Some categorised, some not

6 (14%)

   Unclear

3 (7%)

Treatment of missing data, n (%)

   Not mentioned

16 (41%)

   Complete case

21 (54%)

   Multiple imputation

1 (3%)

   Other (for example, surrogate splitter for regression trees)

1 (3%)

Model-building strategy, n (%)

   Stepwise, forward selection, backward elimination

20 (51%)

   All significant in univariate analysis

2 (5%)

   Other

12 (31%)

   Unclear

5 (13%)

Overfitting mentioned or discussed, n (%)

5 (13%)