Personalized Pain Therapy: Artificial Intelligence (AI) Utilized to Predict Patient Response to OTC Topical Analgesics

Purpose: Topical analgesics have shown efficacy for patients experiencing mild and moderate pain. Due to high variability in patient demographics, clinical profile, and analgesic response, identifying the most suitable treatment for pain patients is difficult. Artificial intelligence and machine learning techniques have shown promise in individualizing treatments. This analysis reviews an interpretable machine learning method to individualize treatment. Due to adverse effects associated with many analgesics, the ability to predict treatment response has a tremendous benefit to clinicians and patients. Patients and methods: Data were evaluated from 186 pain patients enrolled in an Institutional Review Board approved study (RELIEF) after use of a topical pain-relieving analgesic patch for 14 days. A novel interpretable machine learning method was developed based on a multi-objective ensemble classification/regression technique. Data was expanded to increase predictive accuracy with pre- and post-modeling techniques to raise interpretability. 85 features were identified that allowed calculation of data between testing and training groups. Data were split into training (n=152) and testing (n=34) patient sets in a stratified manner. Three basic endpoints were examined for the prediction models: total BPI Severity scores, total BPI Interference scores, and changes in the total drugs. Results: Results demonstrated that the machine learning models were able to predict endpoints with extremely high accuracy, with the AUC exceeding 90% and Spearman correlation metric exceeding 0.4 for all endpoints, far exceeding the test set performance of other benchmark models. The machine learning method reduced the number of significant features from 85 to 19 and defined well characterized groups of responders and non-responders. Conclusion: The machine learning model demonstrated that predictions of positive response could have been made prospectively for patients that benefited from the topical pain-relieving patch. This predictive analytic methodology can be applied to separate and larger datasets and used retrospectively to analyze whether a certain treatment might be effective in a given population.