Cost-Effectiveness of Artificial Intelligence Interventions for Musculoskeletal Disorders: Systematic Review
Author(s)
Tadesse Gebrye, MPH, MSc1, Chidozie Emmanuel Mbada, PhD1, Faatihah Niyi-Odumosu, PhD2, Clara Toyin Fatoye, BSc, MA3, Marufat Odetunde, PhD4, Zalmai Hakimi, PharmD, PhD5, Ushotanefe Useh, PhD6, Francis Fatoye, BSc, MBA, MSc, PhD1.
1Manchester Metropolitan University, Manchester, United Kingdom, 2University of the West of England, Bristol, United Kingdom, 3University Campus Oldham (UCO), Manchester, United Kingdom, 4Obafemi Awolowo University, Ile-Ife, Nigeria, 5Sobi, Amsterdam, Netherlands, 6North West University, Potchefstroom, South Africa.
1Manchester Metropolitan University, Manchester, United Kingdom, 2University of the West of England, Bristol, United Kingdom, 3University Campus Oldham (UCO), Manchester, United Kingdom, 4Obafemi Awolowo University, Ile-Ife, Nigeria, 5Sobi, Amsterdam, Netherlands, 6North West University, Potchefstroom, South Africa.
OBJECTIVES: This systematic review assessed the cost-effectiveness of Artificial intelligence (AI) used in the treatment and management of Musculoskeletal disorders (MSDs).
METHODS: A systematic search was conducted across PubMed, Medline, CINAHL, Cochrane Central Register of Controlled Trials, and Web of Science databases from inception to 6th April 2025. Inclusion criteria encompassed studies that involved AI-powered interventions for individuals with MSDs. Data were extracted on resource use, costs, cost-effectiveness ratios, sample characteristics, and study design. The methodological quality was assessed using the Quality of Health Economic Studies (QHES) instrument.
RESULTS: A total of 233 studies were identified, with 32 duplicates removed and 176 excluded based on title and abstract. After full-text review, 5 studies met the inclusion criteria and were included. These studies represented five countries, and they are from the United States (n=1), Germany (n=1), Denmark (n=1), Australia (n=1) and South Korea (n=1). The included studies adopted healthcare perspective (n=3), societal perspective (n=1) and healthcare and societal perspective (n=1). The AI components of the interventions encompassed a range of technologies, including a deep learning-based diagnostic and exercise prescription platform, the self-BACK application, standardised Magnetic Resonance Imaging (MRI) protocols, the Back Pain Choices online decision support tool, and the Kaia back pain application. The time horizons for these interventions varied from as short as four weeks to three years. Findings from cost-effectiveness analyses demonstrated that AI-based interventions consistently exhibited both clinical and economic advantages across all included studies. Furthermore, the methodological quality was high in the majority of studies, with 90.2% receiving elevated scores on the QHES instrument.
CONCLUSIONS: AI interventions for MSDs revealed potential economic viability, with a majority of studies reporting both clinical effectiveness and cost savings.The evidence supports the integration of AI-powered technologies in the management of MSDs, although further high-quality studies are necessary to refine economic evaluations and explore long-term impacts.
METHODS: A systematic search was conducted across PubMed, Medline, CINAHL, Cochrane Central Register of Controlled Trials, and Web of Science databases from inception to 6th April 2025. Inclusion criteria encompassed studies that involved AI-powered interventions for individuals with MSDs. Data were extracted on resource use, costs, cost-effectiveness ratios, sample characteristics, and study design. The methodological quality was assessed using the Quality of Health Economic Studies (QHES) instrument.
RESULTS: A total of 233 studies were identified, with 32 duplicates removed and 176 excluded based on title and abstract. After full-text review, 5 studies met the inclusion criteria and were included. These studies represented five countries, and they are from the United States (n=1), Germany (n=1), Denmark (n=1), Australia (n=1) and South Korea (n=1). The included studies adopted healthcare perspective (n=3), societal perspective (n=1) and healthcare and societal perspective (n=1). The AI components of the interventions encompassed a range of technologies, including a deep learning-based diagnostic and exercise prescription platform, the self-BACK application, standardised Magnetic Resonance Imaging (MRI) protocols, the Back Pain Choices online decision support tool, and the Kaia back pain application. The time horizons for these interventions varied from as short as four weeks to three years. Findings from cost-effectiveness analyses demonstrated that AI-based interventions consistently exhibited both clinical and economic advantages across all included studies. Furthermore, the methodological quality was high in the majority of studies, with 90.2% receiving elevated scores on the QHES instrument.
CONCLUSIONS: AI interventions for MSDs revealed potential economic viability, with a majority of studies reporting both clinical effectiveness and cost savings.The evidence supports the integration of AI-powered technologies in the management of MSDs, although further high-quality studies are necessary to refine economic evaluations and explore long-term impacts.
Conference/Value in Health Info
2025-11, ISPOR Europe 2025, Glasgow, Scotland
Value in Health, Volume 28, Issue S2
Code
EE236
Topic
Economic Evaluation, Epidemiology & Public Health, Health Service Delivery & Process of Care
Disease
Musculoskeletal Disorders (Arthritis, Bone Disorders, Osteoporosis, Other Musculoskeletal)