Disability status at 1 month is a reliable proxy for final ischemic stroke outcome

Abstract

Background: Three months is the standard timepoint for assessing final functional status after acute ischemic stroke in phase 3 clinical trials. Earlier reliable timepoints for outcome ascertainment would facilitate care quality improvement programs that employ administrative datasets and reduce the loss to follow-up observed in many stroke clinical trials. We assessed whether day 30 global disability status reliably predicts final 3-month disability outcome among acute stroke patients.

Methods: Data of 5,997 subjects in acute stroke trials conducted between 1998 and 2006 from the Virtual International Stroke Trials Archive dataset were partitioned into a derivation cohort (n = 4,051) and a validation cohort (n = 1,946). Global disability was assessed with modified Rankin Scale (mRS). To evaluate the association of day 30 vs day 90 mRS, weighted kappa agreement was computed and then adjusted using multivariable ordinal logistic modeling.

Results: Overall, mean age was 67.6 +/- 12.4 years; 2,541 (45.2%) were women. Day 30 mRS score correlated strongly with day 90 (r = 0.87, p < 0.001); weighted kappa agreement was 0.86 (95% confidence interval 0.85-0.87, p < 0.001). In multivariable logistic regression analysis, day 30 mRS was the dominant variable associated with day 90 mRS, accounting for 65.6% of the variance. Nine other baseline variables were associated with outcome, but collectively explained only an additional 1.8% of the variance.

Conclusions: After an index ischemic stroke, global disability status at 1 month reliably estimates final 3-month disability outcomes. One-month disability status alone may be dependable and efficient as an outcome measure in stroke quality improvement programs and select clinical trials.

Figure 1 Frequency distributions for differences between observed vs predicted day 90 modified Rankin Scale score (mRS) Model I (day 30 mRS score alone), Model II (adjusted logistic regression), Model III (adjusted classification and regression tree). Values above each box are count, percentage. Values on the X axis are differences: observed − predicted day 90 mRS. Categories −2 and 2 include observations for which observed and predicted value differ by 2 units or more.