Role of Artificial Intelligence and Machine Learning in the prediction of the pain: A scoping systematic review

Sankaran, Ravi; Kumar, Anand; Parasuram, Harilal

doi:10.1177/09544119221122012

Cited by 9 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…25 However, despite the promising nature of this innovation, it is a growing field, and it is necessary to evaluate and synthesize the available evidence on its current use in the biopsychosocial management of chronic pain. Previous reviews have focused on the use of AI interventions in pain assessment, diagnosis, and prediction, [29][30][31][32][33][34][35][36] while some have explored the management of specific conditions such as low back pain. 35 Zhang et al 21 Moreover, the developing nature of this field implies that research is rapidly ongoing, and newer evidence may now exist.…”

Section: Original Manuscriptmentioning

confidence: 99%

Artificial Intelligence Interventions in Chronic Pain Management: A Scoping Review (Preprint)

Abiodun,

Das,

Taylor

2024

Preprint

View full text Add to dashboard Cite

BACKGROUND Background There are indicators that artificial intelligence may have the potential to improve chronic pain care globally. However, research in this field is still evolving. Hence, it is necessary to synthesize the available evidence and evaluate its current scope. OBJECTIVE Objective This scoping review presents a comprehensive synthesis of the available evidence, highlighting the types and delivery of biopsychosocial AI-based interventions, the chronic pain conditions managed, the population characteristics, and the context of care delivery. METHODS Methods The literature search was conducted using MEDLINE, Embase via Ovid, and AMED (until July 25, 2023) in line with the PRISMA guidelines. Eligible studies were appraised using the relevant JBI checklist for each study type. The results were synthesized and reported through a narrative review. The review included English-language studies of any research design that reported a form of AI-based intervention for chronic pain management. RESULTS Results 32 RCTs and non-RCTs identifying 23 AI-based interventions were included. The results showed that many interventions targeted the management of one or more of the biopsychosocial components of chronic low back pain. These interventions were delivered through mobile apps, chatbots (text messages), computer-based or equipment-based algorithms, and robots. The interventions focused on exercises, CBT, and feedback. CONCLUSIONS Conclusions The use of artificial intelligence in delivering chronic pain interventions is developing rapidly. However, most interventions were not delivered by an interdisciplinary care team as recommended by the IASP. Furthermore, the report of many systems, without sufficient evidence to support effectiveness, may limit translation to practice. Thus, a joint effort of a team of expert pain clinicians and researchers is required to facilitate the uptake of AI-based interventions for chronic pain management.

show abstract

Section: Original Manuscriptmentioning

confidence: 99%

Artificial Intelligence Interventions in Chronic Pain Management: A Scoping Review (Preprint)

Abiodun,

Das,

Taylor

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Different ML models, such as ANNs, linear regression, support vector regression, Support Vector Machines (SVMs), random forest, adaptive boosting, and extreme gradient boosting, are built using extracted features. However, studies showed SVM and DL are more accurate models for the classification of pain [57,58]. Probabilistic models, such as Gaussian Naive Bayes (GNB) classifiers and hidden Markov models (HMMs), can help clinicians assess pain levels with patient self-reports by analyzing physiological information from individuals with chronic pain, including respiration rate, pulse rate, oxygen level, body temperature, and blood pressure [59].…”

Section: Ai-based Pain Assessmentmentioning

confidence: 99%

Utilizing Artificial Intelligence for the Diagnosis, Assessment, and Management of Chronic Pain

Karimi

2023

J Biomed Phys Eng

View full text Add to dashboard Cite

Chronic pain is a prevalent condition and the leading cause of work absenteeism worldwide. This condition involves persistent pain lasting more than three months, significantly impacting the quality of life and social interactions of patients. While the causes of chronic pain can often remain unknown, no definitive cure exists for the various known causes. Furthermore, the evaluation and prediction of pain can be challenging, particularly in unconscious patients receiving care in the intensive care unit. Subjective measures and traditional methods are typically employed for diagnosis, assessment, and treatment to identify the most effective approach. However, recent advancements in Artificial Intelligence (AI) and other computer science fields have revolutionized the medical domain, offering a novel and promising avenue for enhancing pain management. This review provides an overview of the potential benefits, limitations, and prospects associated with the role of AI in the diagnosis, assessment, and management of chronic pain.

show abstract

“…: genetics, environment, patient vitals) and clinical outcomes, learn the relationships that exist, and use this information to predict future outcome in similar patients [16]. In a medical context, AI has been touted to be used in conjunction with electronic medical records (EMR) to help make medical predictions [17][18][19]. Machine learning (ML) is a subset of AI that uses prediction models and algorithms to analyze and draw inferences from patterns of data to learn or adapt.…”

Section: Introductionmentioning

confidence: 99%

Predicting amputation using machine learning: A systematic review

Yao,

Diao,

McMullen

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Amputation is an irreversible, last-line treatment indicated for a multitude of medical problems. Delaying amputation in favor of limb-sparing treatment may lead to increased risk of morbidity and mortality. This systematic review aims to synthesize the literature on how ML is being applied to predict amputation as an outcome. OVID Embase, OVID Medline, ACM Digital Library, Scopus, Web of Science, and IEEE Xplore were searched from inception to March 5, 2023. 1376 studies were screened; 15 articles were included. In the diabetic population, models ranged from sub-optimal to excellent performance (AUC: 0.6–0.94). In trauma patients, models had strong to excellent performance (AUC: 0.88–0.95). In patients who received amputation secondary to other etiologies (e.g.: burns and peripheral vascular disease), models had similar performance (AUC: 0.81–1.0). Many studies were found to have a high PROBAST risk of bias, most often due to small sample sizes. In conclusion, multiple machine learning models have been successfully developed that have the potential to be superior to traditional modeling techniques and prospective clinical judgment in predicting amputation. Further research is needed to overcome the limitations of current studies and to bring applicability to a clinical setting.

show abstract

Role of Artificial Intelligence and Machine Learning in the prediction of the pain: A scoping systematic review

Cited by 9 publications

References 26 publications

Artificial Intelligence Interventions in Chronic Pain Management: A Scoping Review (Preprint)

Artificial Intelligence Interventions in Chronic Pain Management: A Scoping Review (Preprint)

Utilizing Artificial Intelligence for the Diagnosis, Assessment, and Management of Chronic Pain

Predicting amputation using machine learning: A systematic review

Contact Info

Product

Resources

About