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

Efficacy of Pregabalin and Duloxetine in Patients with Painful Diabetic Peripheral Neuropathy (PDPN): A Multi-Centre Phase IV Clinical Trial-BLOSSOM

INTRODUCTION

Our trial (ClinicalTrials.gov Identifier: NCT04246619) evaluates the efficacy of two generic medications, pregabalin and duloxetine, for treating pain in PDPN patients.

METHODS

The patients were randomised either into the pregabalin (99) or the duloxetine (102) arm. Pain was evaluated using the DN-4 questionnaire, and visual analogue scales (VASs, 0-100 mm) were used to measure the average pain intensity (API), worst pain intensity (WPI) in the last 24 h and current pain intensity (CPI).

RESULTS

The proportion of patients with a clinically significant improvement in the API at Week 12 was 88.3% [CI 81.7%, 94.8%] in the pregabalin arm and 86.9% [CI 76.7%, 97.1%] in the duloxetine arm. After 12 weeks, the CPI, API, and WPI decreased by -35.3 [-40.5, -30.0], -37.0 [-41.4, -32.6], and -41.6 [-46.6, -36.5] in the pregabalin arm, and by -35.0 [-39.2, -30.7], -36.9 [-41.5, -32.3], and -40.0 [-44.8, -35.2] in the duloxetine arm (all in mm, all p < 0.001).

CONCLUSION

Our results demonstrate that pregabalin and duloxetine are effective medications for treating pain in PDPN in more than 86% of all randomised patients.

Efficacy and safety of Mudan granules for painful diabetic peripheral neuropathy: A protocol for a double-blind randomized controlled trial

BACKGROUND

As one of the most challenging complications in the management of diabetes mellitus, painful diabetic peripheral neuropathy (PDPN) is accompanied by various clinical manifestations, including numbness, burning, coldness, and other sensory abnormalities in the extremities. Meanwhile, PDPN seriously affects the life quality of patients and causes great pain. Western medicine mostly provides symptomatic treatments, such as antioxidants, aldose reductase inhibitors, nerve nutrition, microcirculation improvement, and analgesic drugs on the basis of blood sugar control. Although certain efficacy has been achieved, the problem has not been solved at root. Mudan granules have some advantages in the treatment of PDPN, but there is insufficient high-quality clinical studies to verify this. Therefore, the purpose of this study was to evaluate the efficacy and safety of Mudan granules in treating PDPN.

METHODS

A randomized, double-blind, placebo, and parallel-controlled trial design was used to study the efficacy and safety of Mudan granules in the treatment of PDPN. In this study, 93 patients with painful diabetic neuropathy were recruited and randomly divided into a treatment group and a placebo group based on 1:1. The treatment group was given Mudan granules and the control group accepted placebo treatment, and the basic treatment was performed according to the recommended guidelines. During the treatment period, the patients' visual analog scores, clinical efficacy, Medical Outcomes Study 36-item Short-Form Health Survey (SF-36) scores, nerve conduction velocity, and drug-induced adverse reactions were observed at baseline after 8 and 10 weeks.

DISCUSSION

This study will evaluate the efficacy and safety of Mudan granules in treating PDPN. The experimental results will provide evidence support to treat PDPN with Mudan granules.

TRIAL REGISTRATION

DOI 10.17605/OSF.IO/5CE32.

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.