Using time series analysis approaches for improved prediction of pain outcomes in subgroups of patients with painful diabetic peripheral neuropathy

Abstract

Prior work applied hierarchical clustering, coarsened exact matching (CEM), time series regressions with lagged variables as inputs, and microsimulation to data from three randomized clinical trials (RCTs) and a large German observational study (OS) to predict pregabalin pain reduction outcomes for patients with painful diabetic peripheral neuropathy. Here, data were added from six RCTs to reduce covariate bias of the same OS and improve accuracy and/or increase the variety of patients for pain response prediction. Using hierarchical cluster analysis and CEM, a matched dataset was created from the OS (N = 2642) and nine total RCTs (N = 1320). Using a maximum likelihood method, we estimated weekly pain scores for pregabalin-treated patients for each cluster (matched dataset); the models were validated with RCT data that did not match with OS data. We predicted novel 'virtual' patient pain scores over time using simulations including instance-based machine learning techniques to assign novel patients to a cluster, then applying cluster-specific regressions to predict pain response trajectories. Six clusters were identified according to baseline variables (gender, age, insulin use, body mass index, depression history, pregabalin monotherapy, prior gabapentin, pain score, and pain-related sleep interference score). CEM yielded 1766 patients (matched dataset) having lower covariate imbalances. Regression models for pain performed well (adjusted R-squared 0.90-0.93; root mean square errors 0.41-0.48). Simulations showed positive predictive values for achieving >50% and >30% change-from-baseline pain score improvements (range 68.6-83.8% and 86.5-93.9%, respectively). Using more RCTs (nine vs. the earlier three) enabled matching of 46.7% more patients in the OS dataset, with substantially reduced global imbalance vs. not matching. This larger RCT pool covered 66.8% of possible patient characteristic combinations (vs. 25.0% with three original RCTs) and made prediction possible for a broader spectrum of patients. Trial Registration: www.clinicaltrials.gov (as applicable): NCT00156078, NCT00159679, NCT00143156, NCT00553475.

Conflict of interest statement

Joe Alexander Jr., Birol Emir, Ed Whalen, Steve Watt, and Bruce Parsons are employees of Pfizer. Marina Brodsky is a former employee of Pfizer and was employed by Pfizer at the time the study was conducted. Roger A. Edwards is an employee of Health Services Consulting Corporation, who was a paid consultant (by Pfizer) in connection with this study and development of this manuscript. Luigi Manca, Roberto Grugni, Alberto Savoldelli, and Gianluca Bonfanti are employees of Fair Dynamics Consulting, who were paid subcontractors to Health Services Consulting Corporation in connection with this study and development of this manuscript. Pregabalin is a product marketed by Pfizer under the trade name Lyrica. This does not alter our adherence to all the PLOS ONE policies on sharing data and materials, as detailed online in the guide for authors.

Figures

Fig 1. Simulation steps.

OS, observational study; PDF, probability density function; RCT, randomized controlled trial.

Fig 2. Plots of observed vs. predicted pain scores and residuals in validation dataset.

RMSE, root mean square error.

Fig 3

A) Monotonicity results. N = 106 for decreased pain, N = 762 for maintained pain response from weeks 6 to 12–13 (358 responders + 404 non-responders), N = 71 for increased pain. B) ROC curves for monotonicity prediction of pain beyond 6 weeks. Correct prediction based on majority of simulated patient outcomes.

Fig 4. Simulation output.