Predicting Outcome After Acute and Subacute Stroke: Development and Validation of New Prognostic Models

Background and Purpose— Statistical models to predict the outcome of patients with acute and subacute stroke could have several uses, but no adequate models exist. We therefore developed and validated new models. Methods— Regression models to predict survival to 30 days after stroke and survival in a nondisabled state at 6 months were produced with the use of established guidelines on 530 patients from a stroke incidence study. Three models were produced for each outcome with progressively more detailed sets of predictor variables collected within 30 days of stroke onset. The models were externally validated and compared on 2 independent cohorts of stroke patients (538 and 1330 patients) by calculating the area under receiver operating characteristic curves (AUC) and by plotting calibration graphs. Results— Models that included only 6 simple variables (age, living alone, independence in activities of daily living before the stroke, the verbal component of the Glasgow Coma Scale, arm power, ability to walk) generally performed as well as more complex models in both validation cohorts (AUC 0.84 to 0.88). They had good calibration but were overoptimistic in patients with the highest predicted probabilities of being independent. There were no differences in AUCs between patients seen within 48 hours of stroke onset and those seen later; between ischemic and hemorrhagic strokes; and between those with and without a previous stroke. Conclusions— The simple models performed well enough to be used for epidemiological purposes such as stratification in trials or correction for case mix. However, clinicians should be cautious about using these models, especially in hyperacute stroke, to influence individual patient management until they have been further evaluated. Further research is required to test whether additional information from brain imaging improves predictive accuracy.

[1]  D. Madigan,et al.  Bayesian Model Averaging in Proportional Hazard Models: Assessing the Risk of a Stroke , 1997 .

[2]  N. Taub,et al.  Assessment of Scales of Disability and Handicap for Stroke Patients , 1991, Stroke.

[3]  C. Metz Basic principles of ROC analysis. , 1978, Seminars in nuclear medicine.

[4]  C. Granger,et al.  The stroke rehabilitation outcome study: Part II. Relative merits of the total Barthel index score and a four-item subscore in predicting patient outcomes. , 1989, Archives of physical medicine and rehabilitation.

[5]  R L Hewer,et al.  Recovery after stroke--the first 3 months. , 1985, Journal of neurology, neurosurgery, and psychiatry.

[6]  A. Laupacis,et al.  Clinical prediction rules. A review and suggested modifications of methodological standards. , 1997, JAMA.

[7]  Michael R. Chernick,et al.  Analysis of Survival Times , 2003 .

[8]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[9]  R. Prescott,et al.  Predicting functional outcome following acute stroke using a standard clinical examination. , 1982, Stroke.

[10]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[11]  G. Kwakkel,et al.  Predicting disability in stroke--a critical review of the literature. , 1996, Age and ageing.

[12]  J. Concato,et al.  Importance of events per independent variable in proportional hazards regression analysis. II. Accuracy and precision of regression estimates. , 1995, Journal of clinical epidemiology.

[13]  S. Tuhrim,et al.  Validation and comparison of models predicting survival following intracerebral hemorrhage. , 1995, Critical care medicine.

[14]  P. Sandercock,et al.  Long‐term Survival After First‐Ever Stroke: The Oxfordshire Community Stroke Project , 1993, Stroke.

[15]  G. Lenzi,et al.  Is visible infarction on computed tomography associated with an adverse prognosis in acute ischemic stroke? , 1998, Stroke.

[16]  C. Anderson,et al.  Ascertaining the true incidence of stroke: experience from the Perth Community Stroke Study, 1989–1990 , 1993, The Medical journal of Australia.

[17]  J. Concato,et al.  A simulation study of the number of events per variable in logistic regression analysis. , 1996, Journal of clinical epidemiology.

[18]  M. Dennis,et al.  Systematic Review of Prognostic Models in Patients with Acute Stroke , 2001, Cerebrovascular Diseases.

[19]  J. Concato,et al.  The Risk of Determining Risk with Multivariable Models , 1993, Annals of Internal Medicine.

[20]  E L Hannan,et al.  Benefits and hazards of reporting medical outcomes publicly. , 1996, The New England journal of medicine.

[21]  J. Wyatt,et al.  Commentary: Prognostic models: clinically useful or quickly forgotten? , 1995 .

[22]  Peter Fayers,et al.  Can overall results of clinical trials be applied to all patients? , 1995, The Lancet.

[23]  P Peduzzi,et al.  Importance of events per independent variable in proportional hazards analysis. I. Background, goals, and general strategy. , 1995, Journal of clinical epidemiology.

[24]  G. D. Liveing,et al.  The University of Cambridge , 1897, British medical journal.

[25]  J Bamford,et al.  A prospective study of acute cerebrovascular disease in the community: the Oxfordshire Community Stroke Project 1981-86. 1. Methodology, demography and incident cases of first-ever stroke. , 1988, Journal of neurology, neurosurgery, and psychiatry.

[26]  J. Hanley,et al.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases. , 1983, Radiology.

[27]  David W. Hosmer,et al.  Best subsets logistic regression , 1989 .

[28]  R Tibshirani,et al.  A plain man's guide to the proportional hazards model. , 1982, Clinical and investigative medicine. Medecine clinique et experimentale.

[29]  Douglas G Altman,et al.  The relation between treatment benefit and underlying risk in meta-analysis , 1996, BMJ.

[30]  L. Jongbloed Prediction of function after stroke: a critical review. , 1986, Stroke.

[31]  F. Harrell,et al.  Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors , 2005 .

[32]  S. Ricci,et al.  SEPIVAC: a community-based study of stroke incidence in Umbria, Italy. , 1991, Journal of neurology, neurosurgery, and psychiatry.

[33]  J. Slattery,et al.  Interobserver Reliability of a Clinical Classification of Acute Cerebral Infarction , 1993, Stroke.

[34]  Frank Davidoff,et al.  Predicting Clinical States in Individual Patients , 1996, Annals of Internal Medicine.

[35]  A. Ellrodt,et al.  The principle of parsimony: Glasgow Coma Scale score predicts mortality as well as the APACHE II score for stroke patients. , 1990, Stroke.

[36]  N. Weir,et al.  Towards a National System for Monitoring the Quality of Hospital-Based Stroke Services , 2001, Stroke.

[37]  H. Sox,et al.  Clinical prediction rules. Applications and methodological standards. , 1985, The New England journal of medicine.

[38]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[39]  Douglas G. Altman,et al.  Practical statistics for medical research , 1990 .

[40]  J. Whisnant,et al.  Disability and use of rehabilitation services following stroke in Rochester, Minnesota, 1975-1979. , 1987, Stroke.