Assessing the Value of Time Series Real-World and Clinical Trial Data vs. Baseline-Only Data in Predicting Responses to Pregabalin Therapy for Patients with Painful Diabetic Peripheral Neuropathy.

BACKGROUND AND OBJECTIVE: Treatment 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. METHODS: The 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. RESULTS: Time 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). CONCLUSIONS: Effective 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.

WHY COMBINE DIFFERENT DATA SOURCES?: Analyzing the tremendous amount of patient data can provide meaningful insights to improve healthcare quality. Using statistical methods to combine data from clinical trials with real-world studies can improve overall data quality (e.g., reducing biases related to real-world patient variability). WHY CONSIDER A TIME SERIES ANALYSIS?: The best predictor of future outcomes is past outcomes. A "time series" collects data at regular intervals over time. Statistical analyses of time series data allow us to discern time-dependent patterns to predict future clinical outcomes. Modeling and simulation make it possible to combine enormous amounts of data from clinical trial databases to predict a patient's clinical response based on data from similar patients. This approach improves selecting the right drug/dose for the right patient at the right time (i.e., personalized medicine). Using modeling and simulation, we predicted which patients would show a positive response to pregabalin (a neuropathic pain drug) for painful diabetic peripheral neuropathy. WHAT ARE THE MAJOR FINDINGS AND IMPLICATIONS?: For pregabalin-treated patients, a time series analysis had substantially more predictive value vs. analysis only of baseline data (i.e., data collected at treatment initiation). The ability to best predict which patients will respond to therapy has the overall implication of better informing drug treatment decisions. For example, an appropriate modeling and simulation platform complete with relevant historical clinical data could be integrated into a stand-alone device used to monitor and also predict a patient's response to therapy based on daily outcome measures (e.g., smartphone apps, wearable technologies).

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

[This corrects the article DOI: 10.1371/journal.pone.0207120.].

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

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.

Integrating data from randomized controlled trials and observational studies to predict the response to pregabalin in patients with painful diabetic peripheral neuropathy.

BACKGROUND: More patient-specific medical care is expected as more is learned about variations in patient responses to medical treatments. Analytical tools enable insights by linking treatment responses from different types of studies, such as randomized controlled trials (RCTs) and observational studies. Given the importance of evidence from both types of studies, our goal was to integrate these types of data into a single predictive platform to help predict response to pregabalin in individual patients with painful diabetic peripheral neuropathy (pDPN). METHODS: We utilized three pivotal RCTs of pregabalin (398 North American patients) and the largest observational study of pregabalin (3159 German patients). We implemented a hierarchical cluster analysis to identify patient clusters in the Observational Study to which RCT patients could be matched using the coarsened exact matching (CEM) technique, thereby creating a matched dataset. We then developed autoregressive moving average models (ARMAXs) to estimate weekly pain scores for pregabalin-treated patients in each cluster in the matched dataset using the maximum likelihood method. Finally, we validated ARMAX models using Observational Study patients who had not matched with RCT patients, using t tests between observed and predicted pain scores. RESULTS: Cluster analysis yielded six clusters (287-777 patients each) with the following clustering variables: gender, age, pDPN duration, body mass index, depression history, pregabalin monotherapy, prior gabapentin use, baseline pain score, and baseline sleep interference. CEM yielded 1528 unique patients in the matched dataset. The reduction in global imbalance scores for the clusters after adding the RCT patients (ranging from 6 to 63% depending on the cluster) demonstrated that the process reduced the bias of covariates in five of the six clusters. ARMAX models of pain score performed well (R 2 : 0.85-0.91; root mean square errors: 0.53-0.57). t tests did not show differences between observed and predicted pain scores in the 1955 patients who had not matched with RCT patients. CONCLUSION: The combination of cluster analyses, CEM, and ARMAX modeling enabled strong predictive capabilities with respect to pain scores. Integrating RCT and Observational Study data using CEM enabled effective use of Observational Study data to predict patient responses.

Building knowledge driven and dynamically networked communities within European healthcare systems.

COCOON is an innovative project developed in the e-health area of the Sixth Framework Programme co-financed by European Commission. It is an Integrated Project aimed at supporting health care professional in reducing risk management in their daily practices by building knowledge driven and dynamically adaptive networked communities within European healthcare systems.