Table 4.

Performance measures of model without interactions, after leave-one-out cross-validations

	Values
% False positive	13
% False negative	21
% Correct	35
Sensitivity	0.57
Specificity	0.73
Area under the curve (AUC)	0.71

The values included in the table were: proportion of false positive (FP) and false negative (FN), proportion of correctly classified observations, and area under the curve (AUC) in the analyses of women in Sweden < 65 years with a first breast cancer diagnosis in 2010 (N = 2954)

1 Women not at risk of a new SA spell at date of breast cancer diagnosis were not included (that is, those already on (nearly) full-time SA or DP (75–100%)