Related Experiment Video
Updated: Aug 6, 2026
Determining Pain Detection and Tolerance Thresholds Using an Integrated, Multi-Modal Pain Task Battery
Published on: April 14, 2016
Artificial intelligence for prediction of clinical response and therapeutic value in interventional pain management:
Mariana González Garcés1, Jerónimo Cárdenas Montoya1, Valeria Concha Fernández1
1School of Medicine, Universidad de La Sabana, Chía, Colombia.
Introduction:
Interventional pain management is characterised by substantial variability in clinical response, durability of benefit and risk of adverse events, which limits traditional decision-making approaches based on empirical procedure selection. In this context, artificial intelligence has been increasingly explored as a methodological approach to examine predictive strategies and value-oriented decision frameworks in complex interventional settings.
Objective:
To map and characterise the available scientific evidence on the application of artificial intelligence techniques for predicting clinical response, procedural risk and dimensions of therapeutic value in adult patients undergoing interventional pain procedures.
Methods:
A scoping review was conducted in accordance with the Joanna Briggs Institute methodology and reported following the PRISMA-ScR guidelines. A systematic search was performed in PubMed, Scopus, Web of Science and IEEE Xplore for studies published between 2015 and 2026. Eligible studies applied artificial intelligence or machine learning models to explore outcome prediction in interventional pain management.
Results:
Twenty-five studies were included. Most investigations examined predictive applications in epidural injections, radiofrequency procedures, vertebral augmentation and spinal cord stimulation. Across these domains, artificial intelligence models were used to explore patterns associated with clinical response, durability of benefit and procedural risk. Additional outcome domains included opioid use trajectories, functional recovery and identification of scenarios associated with potentially low therapeutic value. The majority of studies were retrospective in design and relied primarily on internal validation, with limited external validation reported.
Conclusions:
The available evidence indicates that artificial intelligence has been applied across multiple interventional pain domains to explore predictive approaches related to clinical response and therapeutic value. However, methodological heterogeneity, retrospective study designs and limited external validation restrict the interpretability and clinical transferability of these findings. Further prospective studies with robust external validation are required before routine clinical implementation can be considered.
Systematic Review Registration:
https://osf.io/a8esc/.
