Artificial Intelligence and Computer Aided Diagnosis in Chronic Low Back Pain: A Systematic Review

Abstract

Low Back Pain (LBP) is currently the first cause of disability in the world, with a significant socioeconomic burden. Diagnosis and treatment of LBP often involve a multidisciplinary, individualized approach consisting of several outcome measures and imaging data along with emerging technologies. The increased amount of data generated in this process has led to the development of methods related to artificial intelligence (AI), and to computer-aided diagnosis (CAD) in particular, which aim to assist and improve the diagnosis and treatment of LBP. In this manuscript, we have systematically reviewed the available literature on the use of CAD in the diagnosis and treatment of chronic LBP. A systematic research of PubMed, Scopus, and Web of Science electronic databases was performed. The search strategy was set as the combinations of the following keywords: “Artificial Intelligence”, “Machine Learning”, “Deep Learning”, “Neural Network”, “Computer Aided Diagnosis”, “Low Back Pain”, “Lumbar”, “Intervertebral Disc Degeneration”, “Spine Surgery”, etc. The search returned a total of 1536 articles. After duplication removal and evaluation of the abstracts, 1386 were excluded, whereas 93 papers were excluded after full-text examination, taking the number of eligible articles to 57. The main applications of CAD in LBP included classification and regression. Classification is used to identify or categorize a disease, whereas regression is used to produce a numerical output as a quantitative evaluation of some measure. The best performing systems were developed to diagnose degenerative changes of the spine from imaging data, with average accuracy rates >80%. However, notable outcomes were also reported for CAD tools executing different tasks including analysis of clinical, biomechanical, electrophysiological, and functional imaging data. Further studies are needed to better define the role of CAD in LBP care.

Natural language processing in low back pain and spine diseases: A systematic review

“…AI and CS systems have already been shown to be a great support to physicians in the task of diagnosing and treating LBP and related pathologies in humans [ 8 , 9 ]. With this work, we aimed to provide a comprehensive review of the literature regarding the described applications of NLP-related methods to the care of patients affected by LBP.…”

“…In recent years, the most ground-breaking technologies have been explored in the care of LBP, including Artificial Intelligence (AI) and Computer Science (CS), which have seen their application in the care of LBP in several studies [ 8 , 9 ]. A promising trend in this field involves Natural Language Processing (NLP), a discipline at the intersection between CS, AI, and Linguistics.…”

Understanding Medical Students’ Perceptions of and Behavioral Intentions toward Learning Artificial Intelligence: A Survey Study

“…Artificial intelligence (AI) is developing rapidly with faster computing, advancement in hardware (e.g., fifth-generation mobile networks) and the advent of deep learning and artificial neural networks [ 1 ]. AI is found to be broadly benefitting modern medicine and clinical practice [ 2 ]. A range of AI-based applications, such as clinical and genomic diagnostics [ 3 , 4 ], chronic disease management [ 5 ], blockchain technology [ 6 ] and sophisticated surgical robots [ 7 ] have deeply reshaped medical practice in the 21st century.…”

Feature Modeling for Interpretable Low Back Pain Classification Based on Surface EMG

“…The advancements and an ever-increasing interest in machine learning (ML) and artificial intelligence (AI) approaches, with their applicability to different domains, were also reflected in different research efforts tackling LBP problems. In the recent period (2020-2022), several review studies have been presented focusing on the applications of ML and AI in the detection, classification, treatment, or management of LBP [8], [17], [18]. Although the respective review studies examined a large number of publications and research works within the LBP domain, it was observed that the number of papers tackling the LBP by exploiting ML and AI techniques, based on sEMG only, is still relatively small.…”

“…Among these, only two papers were reported to deal with LBP by utilizing sEMG exclusively, whereas the additional three papers where combining sEMG with other types of information. In the most recent review study, by D'Antoni et al [18], the AI in the context of computer-aided diagnosis (CAD) in CLBP was reviewed. Similarly, only two studies were reported to deal with LBP by employing sEMG only [21], [22], and one study combined sEMG with kinematic variables [23].…”