Performance of a statistical model to predict stroke outcome in the context of a large, simple, randomized, controlled trial of feeding


Dennis M.

STROKE, cilt.34, sa.1, ss.127-133, 2003 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 34 Sayı: 1
  • Basım Tarihi: 2003
  • Doi Numarası: 10.1161/01.str.0000044165.41303.50
  • Dergi Adı: STROKE
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.127-133
  • İstanbul Üniversitesi Adresli: Hayır

Özet

Background and Purpose-Statistical models to predict the outcome of stroke patients have several uses. Their utility depends on their predictive accuracy in patients other than those on whom they were developed (ie, external validity). We sought to test the external validity of some recently described models in patients enrolled in the FOOD (Feed Or Ordinary Diet) trial: a large randomized trial evaluating feeding policies in patients with stroke.

Background and Purpose-Statistical models to predict the outcome of stroke patients have several uses. Their utility depends on their predictive accuracy in patients other than those on whom they were developed (ie, external validity). We sought to test the external validity of some recently described models in patients enrolled in the FOOD (Feed Or Ordinary Diet) trial: a large randomized trial evaluating feeding policies in patients with stroke. 

Methods-The predictive variables were collected during a telephone call to randomize the patient a median of 5 days after stroke onset. Patients were followed up 6 months later to establish their survival, functional status, and residence. Charts were plotted to demonstrate the discrimination and calibration of the models. 

Results-The models performed well in the first 2955 patients enrolled and followed up in the FOOD trial. The area under the receiver operating characteristic curves varied between 0.78 and 0.81 (with 0.5 indicating no discrimination and 1.0 indicating perfect discrimination). The discrimination was marginally better for patients enrolled within the first day of stroke than later. The models tended to provide rather pessimistic predictions in all groups except those predicted to have a high likelihood of surviving free of dependency. 

Conclusions-As one might predict, the discriminatory power in the selected cohort of trial patients was marginally less good than in previously studied unselected cohorts used to test their external validity. These models provide a well-tested tool for stratification in trials, comparing outcomes in different cohorts and examining the additional predictive power of novel factors.