Ethics code: IR.SBMU.PHNS.REC.1404.063
Safety Promotion and Injury Prevention Research Center, Research Institute for Health Sciences and Environment, Shahid Beheshti University of Medical Sciences, Tehran, Ira , asalehi529@gmail.com
Abstract: (10 Views)
Background and aims: Ergonomics and human factors have increasingly attracted attention as essential domains for improving workplace safety, productivity, and health. With the rapid growth of artificial intelligence (AI), researchers have begun to explore its potential to predict and assess ergonomic risks. This review aims to systematically evaluate existing studies addressing AI applications in ergonomic risk prediction and assessment.
Methods: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a structured search was conducted in Web of Science, Scopus, ScienceDirect, and PubMed for the years 2000–2024 using relevant keywords. Inclusion criteria comprised original research articles—experimental or laboratory-based—published in English or Persian that investigated AI in ergonomic risk prediction or assessment. Exclusion criteria included review articles, books, editorials, letters, or irrelevant topics.
Results: A total of 32 studies were included. Research activity significantly increased after 2021, peaking in 2024. Machine learning, computer vision, expert systems, and natural language processing were the most frequently applied approaches. Machine learning accounted for the majority of methods, demonstrating superior accuracy and predictive capabilities. Geographically, Europe contributed the highest share of studies (44%), while Africa had the lowest (3%).
Conclusion: The evidence indicates that AI, particularly machine learning algorithms and computer vision, can substantially improve the accuracy, efficiency, and real-time capacity of ergonomic risk assessments compared to traditional methods. This highlights AI’s transformative potential in occupational health and ergonomics.
Methods: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a structured search was conducted in Web of Science, Scopus, ScienceDirect, and PubMed for the years 2000–2024 using relevant keywords. Inclusion criteria comprised original research articles—experimental or laboratory-based—published in English or Persian that investigated AI in ergonomic risk prediction or assessment. Exclusion criteria included review articles, books, editorials, letters, or irrelevant topics.
Results: A total of 32 studies were included. Research activity significantly increased after 2021, peaking in 2024. Machine learning, computer vision, expert systems, and natural language processing were the most frequently applied approaches. Machine learning accounted for the majority of methods, demonstrating superior accuracy and predictive capabilities. Geographically, Europe contributed the highest share of studies (44%), while Africa had the lowest (3%).
Conclusion: The evidence indicates that AI, particularly machine learning algorithms and computer vision, can substantially improve the accuracy, efficiency, and real-time capacity of ergonomic risk assessments compared to traditional methods. This highlights AI’s transformative potential in occupational health and ergonomics.
Type of Study: Review Article |
Subject:
Ergonomics
Received: 2025/09/16 | Accepted: 2026/05/27 | Published: 2026/06/27
Received: 2025/09/16 | Accepted: 2026/05/27 | Published: 2026/06/27
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
