Abstract
Music interventions are effective for physical, psychological, cognitive and social well-being [1-3]. Artificial Intelligence (AI) can generate personalised therapeutic music instantly, creating a novel, accessible intervention. However, the effectiveness of these AI-generated interventions has not been systematically reviewed [4, 5]. This systematic review aimed to evaluate the efficacy of AI-generated music interventions for improving health outcomes.
A systematic search was conducted across eight electronic databases (Cochrane, Medline, APA PsycINFO, PubMed, Scopus, Web of Science, IEEE Xplore, ACM Digital Library) from inception to September 2025. After screening, eight studies (N=1,267 participants) met the inclusion criteria, comprising four randomised controlled trials (RCTs) and four quasi-experimental studies. Data selection, extraction, and methodological quality assessment using the Effective Public Health Practice Project tool were performed independently by two reviewers. The quality appraisal rated four studies as 'moderate' and four as 'weak'. This study was registered on PROSPERO (ID: CRD420251182309).
AI-generated music interventions demonstrated positive effects on psychological, cognitive, and physiological outcomes. AI-style-transferred and personalised music significantly reduced anxiety scores (Mean change = 3.85, SD =3.99, p < 0.001), in some cases outperforming preferred (5.6 vs 2.4 points STAI reduction) and standard therapeutic music (5.6 vs 4.05 points). AI-composed natural hypnotic music also significantly improved sleep quality compared to general sleep music (2.85±1.36 vs. 3.87±1.25). Cognitive benefits included improved frontal lobe function and memory in older adults and enhanced attention in children with attention deficit disorder (p<0.05). Physiological markers of relaxation, such as increased heart rate variability and EEG alpha power, further supported these findings.
AI-generated music provides nurses with innovative tools for personalised, music-based interventions. Nurses can leverage these tools to implement therapeutic care, offering tailored music for anxiety reduction, sleep promotion, and cognitive stimulation in diverse clinical and community settings. Future nursing research should focus on integrating these technologies into routine care and evaluating their long-term efficacy, cost-effectiveness, and implementation. More rigorous studies are warranted to explore the impact of AI music on other health outcomes.
Notes
References:
1. Bleibel M, El Cheikh A, Sadier NS, Abou-Abbas L (2023) The effect of music therapy on cognitive functions in patients with Alzheimer’s disease: a systematic review of randomized controlled trials. Alzheimers Res Ther 15: 65
2. Bradt J, Dileo C, Myers-Coffman K, Biondo J (2021) Music interventions for improving psychological and physical outcomes in people with cancer. Cochrane Database Syst Rev 10
3. Navarro L, Mallah NEZ, Nowak W, Pardo-Seco J, Gómez-Carballa A, Pischedda S, Martinón-Torres F, Salas A (2025) The effect of music interventions in autism spectrum disorder: A systematic review and meta-analysis. Front Integr Neurosci. 19: 1673618
4. Santos N, Bernardes G (2025) A Scoping Review of Emerging AI Technologies in Mental Health Care: Towards Personalized Music Therapy. In Proceedings of Conference on Sonification of Health and Environmental Data (SoniHED 2025).
5. Shen L, Zhang H, Zhu C, Li R, Qian K, Meng W, Tian F, Hu B, Schuller BW, Yamamoto Y (2024) A First Look at Generative Artificial Intelligence Based Music Therapy for Mental Disorders. IEEE Trans Consum Electron: 1-1
Sigma Membership
Non-member
Type
Presentation
Format Type
Text-based Document
Study Design/Type
Systematic Review
Research Approach
Other
Keywords:
Implementation Science, Stress and Coping, Artificial Intelligence, Music Therapy, Treatment Outcomes
Recommended Citation
Khanh, Nguyen Thi; Nguyen, Huu-Thanh; Nhat, Vi Do Pham; and Chan, Carmen Wing Han, "Can AI-Generated Music Interventions Improve Health Outcomes? A Systematic Review" (2026). International Nursing Research Congress (INRC). 248.
https://www.sigmarepository.org/inrc/2026/presentations_2026/248
Conference Name
37th International Nursing Research Congress
Conference Host
Sigma Theta Tau International
Conference Location
Toronto, Ontario, Canada
Conference Year
2026
Rights Holder
All rights reserved by the author(s) and/or publisher(s) listed in this item record unless relinquished in whole or part by a rights notation or a Creative Commons License present in this item record. All permission requests should be directed accordingly and not to the Sigma Repository. All submitting authors or publishers have affirmed that when using material in their work where they do not own copyright, they have obtained permission of the copyright holder prior to submission and the rights holder has been acknowledged as necessary.
Review Type
Abstract Review Only: Reviewed by Event Host
Acquisition
Proxy-submission
Date of Issue
2026-08-30
Can AI-Generated Music Interventions Improve Health Outcomes? A Systematic Review
Toronto, Ontario, Canada
Music interventions are effective for physical, psychological, cognitive and social well-being [1-3]. Artificial Intelligence (AI) can generate personalised therapeutic music instantly, creating a novel, accessible intervention. However, the effectiveness of these AI-generated interventions has not been systematically reviewed [4, 5]. This systematic review aimed to evaluate the efficacy of AI-generated music interventions for improving health outcomes.
A systematic search was conducted across eight electronic databases (Cochrane, Medline, APA PsycINFO, PubMed, Scopus, Web of Science, IEEE Xplore, ACM Digital Library) from inception to September 2025. After screening, eight studies (N=1,267 participants) met the inclusion criteria, comprising four randomised controlled trials (RCTs) and four quasi-experimental studies. Data selection, extraction, and methodological quality assessment using the Effective Public Health Practice Project tool were performed independently by two reviewers. The quality appraisal rated four studies as 'moderate' and four as 'weak'. This study was registered on PROSPERO (ID: CRD420251182309).
AI-generated music interventions demonstrated positive effects on psychological, cognitive, and physiological outcomes. AI-style-transferred and personalised music significantly reduced anxiety scores (Mean change = 3.85, SD =3.99, p < 0.001), in some cases outperforming preferred (5.6 vs 2.4 points STAI reduction) and standard therapeutic music (5.6 vs 4.05 points). AI-composed natural hypnotic music also significantly improved sleep quality compared to general sleep music (2.85±1.36 vs. 3.87±1.25). Cognitive benefits included improved frontal lobe function and memory in older adults and enhanced attention in children with attention deficit disorder (p<0.05). Physiological markers of relaxation, such as increased heart rate variability and EEG alpha power, further supported these findings.
AI-generated music provides nurses with innovative tools for personalised, music-based interventions. Nurses can leverage these tools to implement therapeutic care, offering tailored music for anxiety reduction, sleep promotion, and cognitive stimulation in diverse clinical and community settings. Future nursing research should focus on integrating these technologies into routine care and evaluating their long-term efficacy, cost-effectiveness, and implementation. More rigorous studies are warranted to explore the impact of AI music on other health outcomes.
Description
This systematic review provides evidence that AI-generated music interventions effectively improve anxiety, sleep, cognition, and physiological relaxation. Nurses can adopt this innovative, personalised tool in therapeutic practice.