The Analysis of Pain Research through the Lens of Artificial Intelligence and Machine Learning

Background: Traditional pain assessment methods have significant limitations due to the high variability in patient reported pain scores and perception of pain by different individuals. There is a need for generalized and automatic pain detection and recognition methods. In this paper, stateof-the-art machine learning (ML) and deep learning methods in this field are analyzed as well as pain management techniques. Objective: The objective of the study is to analyze the current use of artificial intelligence (AI) and ML in the analysis and management of pain and to disseminate this knowledge prompting future utilization by medical professionals. Study Design: A narrative review of the literature focusing on the latest algorithms in AI and ML for pain assessment and management. Methods: Research studies were collected using a literature search on PubMed, Science Direct and IEEE Xplore between 2018 and 2020. Results: The results of our assessment resulted in the identification of 47 studies meeting inclusion criteria. Pain assessment was the most studied subject with 11 studies, followed by automated measurements with 10 studies, spinal diagnosis with 8 studies, facial expression with 7 studies, pain assessment in special settings evaluated in 5 studies, 4 studies described treatment algorithms, and 2 studies assessed neonatal pain. These studies varied from simple to highly complex methodology. The majority of the studies suffered from inclusion of a small number of patients and without replication of results. However, considering AI and ML are dynamic and emerging specialties, the results shown here are promising. Consequently, we have described all the available literature in summary formats with commentary. Among the various assessments, facial expression and spinal diagnosis and management appear to be ready for inclusion as we continue to progress. Limitations: This review is not a systematic review of ML and AI applications in pain research. This review only provides a general idea of the upcoming techniques but does not provide an authoritative evidence-based conclusive opinion of their clinical application and effectiveness. Conclusion: While a majority of the studies focused on classification tasks, very few studies have explored the diagnosis and management of pain. Usage of ML techniques as support tools for clinicians holds an immense potential in the field of pain management.

Automated summary

This article analyzes the application of artificial intelligence and machine learning in pain analysis and management, and suggests that facial expression and spinal diagnosis and management are ready for implementation. The article summarizes the available literature and proposes further research directions.