Skip to main content

Table 5 Proportions of cases correctly predicted (sensitivity and specificity) for various classification cut-offs

From: Identifying high-need patients with multimorbidity from their illness perceptions and personal resources to manage their health and care: a longitudinal study

 Frequent contact with general practiceUse of general practice out-of-office serviceUnplanned hospitalisationPoor health related quality of life
Final modelChi2(3) = 21.512
(P < .001)
Chi2(3) = 16.037
(P = .001)
Chi2(1) = 9.654
(P = .002)
Chi2(7) = 137.288
(P < .001)
N552577580541
AUC.626.612.609.837
Classification cut-off:      Sens.aSpec.b
 .10      90.857.2
 .15      81.767.6
 .16      80.768.1
 .17      79.869.7
 .20      74.375.2
 .25      67.982.2
 .50      43.194.0
  1. a Sens. = Sensitivity: number of cases predicted with adverse outcome / total number of cases observed with adverse outcome
  2. b Spec. = Specificity: number of cases not predicted with adverse outcome / total number of cases not observed with adverse outcome