Journals / Bilgi Teknolojileri ve İletişim Dergisi / 2026 / Cilt: 4 Sayı: 1

Artificial Intelligence (AI)-Based Risk Analysis in Occupational Health and Safety: An Integrated Architectural Approach Proposal

İş Sağlığı ve Güvenliğinde Yapay Zekâ Tabanlı Risk Analizi: Bütünleşik Bir Mimari Yaklaşım Önerisi

Cemre Çınar(ANKARA YILDIRIM BEYAZIT ÜNİVERSİTESİ)0009-0004-1645-7133
Saniye Yavuz(Aile ve Sosyal Hizmetler Bakanlığı)0009-0000-1488-0422
Pages
123–146
Publication Date
2026-06-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

By clarifying both the technical and governance-related limitations of current approaches, the study offers a comprehensive reference model for the design and implementation of AI-supported OHS systems, addressing the needs of both researchers and practitioners.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study systematically maps the existing body of knowledge on artificial intelligence–based risk analysis approaches in the field of occupational health and safety (OHS) through a two-stage methodological design that integrates a narrative literature review with conceptual framework development.
📊
Key Findings & Data:In response to these gaps, the study synthesizes the literature and proposes an integrated system architecture consisting of five structural layers and four design principles.
💡
Conclusion & Impact:By clarifying both the technical and governance-related limitations of current approaches, the study offers a comprehensive reference model for the design and implementation of AI-supported OHS systems, addressing the needs of both researchers and practitioners.
🔬Design:Review & Systematic Survey
📍Scope:Comprehensive Sample
⚙️Variables:Yapay Zekâ (YZ) · İş Sağlığı ve Güvenliği (İSG) · IoT

Abstract

This study systematically maps the existing body of knowledge on artificial intelligence–based risk analysis approaches in the field of occupational health and safety (OHS) through a two-stage methodological design that integrates a narrative literature review with conceptual framework development. Findings derived from both national and international literature indicate that expert systems, machine learning models, and Internet of Things (IoT)–based sensor networks are increasingly adopted in OHS applications. However, critical dimensions such as explainability, data governance, model lifecycle management, and organizational compliance are not addressed holistically in the majority of existing studies. In response to these gaps, the study synthesizes the literature and proposes an integrated system architecture consisting of five structural layers and four design principles. The proposed architecture combines data collection, data processing, analytical modeling, decision support, and organizational integration processes within a governance framework grounded in Explainable Artificial Intelligence (XAI) and Machine Learning Operations (MLOps). In doing so, it provides a methodological foundation for scalable, transparent, and auditable AI integration in OHS contexts. By clarifying both the technical and governance-related limitations of current approaches, the study offers a comprehensive reference model for the design and implementation of AI-supported OHS systems, addressing the needs of both researchers and practitioners.

Özet

Bu çalışma, yapay zekâ tabanlı risk analizi yaklaşımlarının iş sağlığı ve güvenliği (İSG) alanındaki konumunu literatür incelemesi (narrative literature review) ve kavramsal çerçeve geliştirme yaklaşımının birlikte kullanıldığı iki aşamalı bir metodolojik yapı üzerinde inceleyerek mevcut bilgi birikimini sistematik biçimde haritalamaktadır. Ulusal ve uluslararası literatürden elde edilen bulgular, İSG uygulamalarında uzman sistemler, makine öğrenmesi modelleri ve IoT tabanlı sensör ağlarının giderek yaygınlaştığını; ancak açıklanabilirlik, veri yönetişimi, model yaşam döngüsü yönetimi ve kurumsal uyum gerekliliklerinin çoğu çalışmada bütüncül biçimde ele alınmadığını göstermektedir. Bu eksiklikler doğrultusunda çalışma, literatürden türetilen bulguları sentezleyerek beş katmanlı yapısal bileşenden ve dört tasarım ilkesinden oluşan bütünleşik bir sistem mimarisi önermektedir. Önerilen mimari; veri toplama, veri işleme, analitik modelleme, karar destek ve kurumsal entegrasyon süreçlerini açıklanabilir yapay zekâ ve makine öğrenmesi operasyonları (Machine Learning Operations-MLOps) temelli yönetişim ilkeleriyle bir araya getirerek İSG’de ölçeklenebilir, şeffaf ve denetlenebilir bir yapay zekâ entegrasyonu için metodolojik bir çerçeve sunmaktadır. Çalışma, mevcut yaklaşımlardaki teknik ve yönetişimsel sınırlılıkları netleştirirken hem araştırmacılar hem de uygulayıcı kurumlar için yapay zekâ destekli İSG sistemlerinin tasarımına yönelik bütüncül bir referans modeli ortaya koymaktadır.

🔖

Cite This Article

Çınar, C., Yavuz, S. (2026). Artificial Intelligence (AI)-Based Risk Analysis in Occupational Health and Safety: An Integrated Architectural Approach Proposal. Bilgi Teknolojileri ve İletişim Dergisi, Cilt: 4 Sayı: 1, 123–146. https://doi.org/10.66643/btkdergi.1939549

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (24)

  1. Adadi, A., & Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6, 52138–52160. https://doi.org/10.1109/ACCESS.2018.2870052
  2. Aslan, T., & Yağımlı, M. (2023). İş Sağlığı ve Güvenliğinde Derin Öğrenme Tabanlı Risk Tespit ve Analizi. The Journal of International Scientific Researches, 8(2), 223-236. https://dergipark.org.tr/tr/pub/isrjournal/issue/78902/1288496
  3. Ayan, B., Taşçı, S., & Köksal, E. B. M. (2024). İş Sağlığı ve Güvenliği Alanında Kullanılan Yapay Zeka Teknolojilerine İlişkin İnceleme. Çalışma İlişkileri Dergisi, 15(2), 20-33. https://dergipark.org.tr/tr/pub/cider/issue/86465/1496402
  4. Azadeh, A., Fam, I. M., Khoshnoud, M., & Nikafrouz, M. (2008). Design and implementation of a fuzzy expert system for performance assessment of an integrated health, safety, environment (HSE) and ergonomics system: The case of a gas refinery. Information Sciences, 178(22), 4280–4300. https://doi.org/10.1016/j.ins.2008.06.026
  5. Barredo A. A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., … Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115. https://doi.org/10.1016/j.inffus.2019.12.012
  6. Beriha, G. S., Patnaik, B., Mahapatra, S. S., & Padhee, S. (2012). Assessment of safety performance in Indian industries using fuzzy approach. Expert Systems with Applications, 39(3), 3311–3323. https://doi.org/10.1016/j.eswa.2011.09.018
  7. El-Bouchikhi, M., Weerts, S., & Clavien, C. (2024). The internet of things deployed for occupational health and safety purposes: A qualitative study of opportunities and ethical issues. Frontiers in Public Health, 12, 1468646, 1-15. https://doi.org/10.3389/fpubh.2024.1468646
  8. El-Helaly, M. (2024). Artificial intelligence and occupational health and safety, benefits and drawbacks. La Medicina del Lavoro, 115(2), 91–104. https://doi.org/10.23749/mdl.v115i2.15835
  9. Erol, M., & Eraslan, E. (2024). Nesnelerin İnterneti, Uygulama Alanları ve İş Sağlığı ve Güvenliği ile Etkileşimi. Journal of Turkish Operations Management, 8(1), 73-89. https://doi.org/10.56554/jtom.1258262
  10. Hadjimichael, M. (2009). A fuzzy expert system for aviation risk assessment. Expert Systems with Applications, 36(3), 6512–6519. https://doi.org/10.1016/j.eswa.2008.07.081
  11. Hoenigsberger, F., Saranti, A., Jalali, A., Stampfer, K., & Holzinger, A. (2024). Explainable Artificial Intelligence to Support Work Safety in Forestry: Insights from Two Large Datasets, Open Challenges, and Future Work. Applied Sciences, 14(9), 3911. https://doi.org/10.3390/app14093911
  12. İçen, D., & Günay, S. (2014). Uzman Sistemler ve İstatistik. İstatistikçiler Dergisi: İstatistik ve Aktüerya, 7(2), 37–45. https://dergipark.org.tr/tr/pub/jssa/issue/36636/417059
  13. Kabir, S., Hossain, M. S., & Andersson, K. (2025). A Review of Explainable Artificial Intelligence from the Perspectives of Challenges and Opportunities. Algorithms, 18(9), 556. https://doi.org/10.3390/a18090556
  14. Koç, K., Ekmekcioğlu, Ö., & Gürgün, A. P., (2022). Accident prediction in construction using hybrid wavelet-machine learning. Automation in Construction, vol.133. https://doi.org/10.1016/j.autcon.2021.103987
  15. Lilić, N., Obradović, I., & Cvjetić, A. (2010). An intelligent hybrid system for surface coal mine safety analysis. Engineering Applications of Artificial Intelligence, 23(4), 453–462. https://doi.org/10.1016/j.engappai.2010.01.025
  16. Olcay, Z. F. (2021). İş Sağlığı ve Güvenliği Kültürü Ölçeği; Geçerlik ve Güvenirlik Çalışması. Avrupa Bilim ve Teknoloji Dergisi (23), 678-685. https://doi.org/10.31590/ejosat.892845
  17. Park, J., & Kang, D. (2024). Artificial Intelligence and Smart Technologies in Safety Management: A Comprehensive Analysis Across Multiple Industries. Applied Sciences, 14(24), 1-22. https://doi.org/10.3390/app142411934
  18. Pavlovic-Veselinovic, S., Hedge, A., & Veselinovic, M. (2016). An ergonomic expert system for risk assessment of work-related musculoskeletal disorders. International Journal of Industrial Ergonomics, 53, 130–139. https://doi.org/10.1016/j.ergon.2015.11.008
  19. Peters, M. D. J., Marnie, C., Tricco, A. C., Pollock, D., Munn, Z., Alexander, L., … Khalil, H. (2020). Updated methodological guidance for the conduct of scoping reviews. JBI Evidence Synthesis, 18(10), 2119–2126. https://doi.org/10.11124/JBIES-20-00167
  20. Shah, I. A., & Mishra, S. (2024). Artificial intelligence in advancing occupational health and safety: An encapsulation of developments. Journal of Occupational Health, 66(1), 1-12 https://doi.org/10.1093/joccuh/uiad017
  21. Şengöz, T. E., & Bozkurt, Y. (2025). İş Sağlığı ve Güvenliği Kapsamında Sektörel İş Kazalarının Yapay Zekâ Teknolojileri ve Uzman Sistem Uygulamaları Yönünden İncelenmesi. Sürdürülebilir Mühendislik Uygulamaları ve Teknolojik Gelişmeler Dergisi, 8(1), 17-44. https://doi.org/10.51764/smutgd.1678632
  22. Tricco, A. C., Lillie, E., Zarin, W., O’Brien, K. K., Colquhoun, H., Levac, D., … Straus, S. E. (2018). PRISMA extension for scoping reviews (PRISMA-ScR): Checklist and explanation. Annals of Internal Medicine, 169(7), 467–473. https://doi.org/10.7326/M18-0850
  23. Vivian, N., Maheshwari, U., Yeboah, R. (2025). A comprehensive survey on machine learning for workplace injury analysis: Risk prediction, return to work strategies, and demographic insights. Journal of Big Data, 12, 167, 1-26. https://doi.org/10.1186/s40537-025-01229-z
  24. World Health Organization & International Labour Organization. (2021). WHO/ILO joint estimates of the work-related burden of disease and injury, 2000–2016: Global monitoring report. World Health Organization & International Labour Organization. https://www.who.int/publications/i/item/9789240034945