The TAXINOMISIS Project: A multidisciplinary approach for the development of a new risk stratification model for patients with asymptomatic carotid artery stenosis

INTRODUCTION

Asymptomatic carotid artery stenosis (ACAS) may cause future stroke and therefore patients with ACAS require best medical treatment. Patients at high risk for stroke may opt for additional revascularization (either surgery or stenting) but the future stroke risk should outweigh the risk for peri/post-operative stroke/death. Current risk stratification for patients with ACAS is largely based on outdated randomized-controlled trials that lack the integration of improved medical therapies and risk factor control. Furthermore, recent circulating and imaging biomarkers for stroke have never been included in a risk stratification model. The TAXINOMISIS Project aims to develop a new risk stratification model for cerebrovascular complications in patients with ACAS and this will be tested through a prospective observational multicentre clinical trial performed in six major European vascular surgery centres.

METHODS AND ANALYSIS

The risk stratification model will compromise clinical, circulating, plaque and imaging biomarkers. The prospective multicentre observational study will include 300 patients with 50%-99% ACAS. The primary endpoint is the three-year incidence of cerebrovascular complications. Biomarkers will be retrieved from plasma samples, brain MRI, carotid MRA and duplex ultrasound. The TAXINOMISIS Project will serve as a platform for the development of new computer tools that assess plaque progression based on radiology images and a lab-on-chip with genetic variants that could predict medication response in individual patients.

CONCLUSION

Results from the TAXINOMISIS study could potentially improve future risk stratification in patients with ACAS to assist personalized evidence-based treatment decision-making.

Integrating Machine Learning With Microsimulation to Classify Hypothetical, Novel Patients for Predicting Pregabalin Treatment Response Based on Observational and Randomized Data in Patients With Painful Diabetic Peripheral Neuropathy

Purpose

Variability in patient treatment responses can be a barrier to effective care. Utilization of available patient databases may improve the prediction of treatment responses. We evaluated machine learning methods to predict novel, individual patient responses to pregabalin for painful diabetic peripheral neuropathy, utilizing an agent-based modeling and simulation platform that integrates real-world observational study (OS) data and randomized clinical trial (RCT) data.

Patients and methods

The best supervised machine learning methods were selected (through literature review) and combined in a novel way for aligning patients with relevant subgroups that best enable prediction of pregabalin responses. Data were derived from a German OS of pregabalin (N=2642) and nine international RCTs (N=1320). Coarsened exact matching of OS and RCT patients was used and a hierarchical cluster analysis was implemented. We tested which machine learning methods would best align candidate patients with specific clusters that predict their pain scores over time. Cluster alignments would trigger assignments of cluster-specific time-series regressions with lagged variables as inputs in order to simulate "virtual" patients and generate 1000 trajectory variations for given novel patients.

Results

Instance-based machine learning methods (k-nearest neighbor, supervised fuzzy c-means) were selected for quantitative analyses. Each method alone correctly classified 56.7% and 39.1% of patients, respectively. An "ensemble method" (combining both methods) correctly classified 98.4% and 95.9% of patients in the training and testing datasets, respectively.

Conclusion

An ensemble combination of two instance-based machine learning techniques best accommodated different data types (dichotomous, categorical, continuous) and performed better than either technique alone in assigning novel patients to subgroups for predicting treatment outcomes using microsimulation. Assignment of novel patients to a cluster of similar patients has the potential to improve prediction of patient outcomes for chronic conditions in which initial treatment response can be incorporated using microsimulation.

Clinical trial registries

www.clinicaltrials.gov: NCT00156078, NCT00159679, NCT00143156, NCT00553475.

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.

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.

Dose Titration of Pregabalin in Patients with Painful Diabetic Peripheral Neuropathy: Simulation Based on Observational Study Patients Enriched with Data from Randomized Studies

INTRODUCTION

Achieving a therapeutic response to pregabalin in patients with painful diabetic peripheral neuropathy (pDPN) requires adequate upward dose titration. Our goal was to identify relationships between titration and response to pregabalin in patients with pDPN.

METHODS

Data were integrated from nine randomized, placebo-controlled clinical trials as well as one 6-week open-label observational study conducted by 5808 physicians (2642 patients with pDPN) in standard outpatient settings in Germany. These studies evaluated pregabalin for treatment of pDPN. Using these data, we examined "what if" scenarios using a microsimulation platform that integrates data from randomized and observational sources as well as autoregressive-moving-average with exogenous inputs models that predict pain outcomes, taking into account weekly changes in pain, sleep interference, dose, and other patient characteristics that were unchanging.

RESULTS

Final pain levels were significantly different depending on dose changes (P < 0.0001), with greater proportions improving with upward titration regardless of baseline pain severity. Altogether, 78.5% of patients with pDPN had 0-1 dose change, and 15.2% had ≥ 2 dose changes. Simulation demonstrated that the 4.8% of inadequately titrated patients who did not improve/very much improve their pain levels would have benefited from ≥ 2 dose changes. Patient satisfaction with tolerability (range 90.3-96.2%) was similar, regardless of baseline pain severity, number of titrations, or extent of improvement, suggesting that tolerability did not influence treatment response patterns.

CONCLUSION

Upward dose titration reduced pain in patients with pDPN who actually received it. Simulation also predicted pain reduction in an inadequately titrated nonresponder subgroup of patients had they actually received adequate titration. The decision not to uptitrate must have been driven by factors other than tolerability.

FUNDING

Pfizer, Inc.

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.