• Joe Alexander, Roger A Edwards, Marina Brodsky, Alberto Savoldelli, Luigi Manca, Roberto Grugni, Birol Emir, Ed Whalen, Steve Watt, and Bruce Parsons.
• Pfizer Inc, New York, NY, USA.
• Clin Drug Investig. 2019 Aug 1; 39 (8): 775-786.

Background And ObjectiveTreatment challenges necessitate new approaches to customize care to individual patient needs. Integrating data from randomized controlled trials and observational studies may reduce potential covariate biases, yielding information to improve treatment outcomes. The objective of this study was to predict pregabalin responses, in individuals with painful diabetic peripheral neuropathy, by examining time series data (lagged inputs) collected after treatment initiation vs. baseline using microsimulation.MethodsThe platform simulated pregabalin-treated patients to estimate hypothetical future pain responses over 6 weeks based on six distinct time series regressions with lagged variables as inputs (hereafter termed "time series regressions"). Data were from three randomized controlled trials (N = 398) and an observational study (N = 3159). Regressions were derived after performing a hierarchical cluster analysis with a matched patient dataset from coarsened exact matching. Regressions were validated using unmatched (observational study vs. randomized controlled trial) patients. Predictive implications (of 6-week outcomes) were compared using only baseline vs. 1- to 2-week prior data.ResultsTime series regressions for pain performed well (adjusted R2 0.85-0.91; root mean square error 0.53-0.57); those with only baseline data performed less well (adjusted R2 0.13-0.44; root mean square error 1.11-1.40). Simulated patient distributions yielded positive predictive values for > 50% pain score improvements from baseline for the six clusters (287-777 patients each; range 0.87-0.98).ConclusionsEffective prediction of pregabalin response for painful diabetic peripheral neuropathy was accomplished through combining cluster analyses, coarsened exact matching, and time series regressions, reflecting distinct patterns of baseline and "on-treatment" variables. These results advance the understanding of microsimulation to predict patient treatment responses through integration and inter-relationships of multiple, complex, and time-dependent characteristics.

19 keywords...

hide…