Aplicaciones de la Inteligencia Artificial en la Prevención de Accidentes Laborales en Entornos Industriales: Revisión Sistemática y Perspectivas para América Latina
DOI:
https://doi.org/10.69639/arandu.v13i2.2252Palabras clave:
desarrollo de software, agentes de inteligencia artificial, todologías ágiles, ingeniería de prompts, KPIsResumen
La inteligencia artificial (IA) ha demostrado potencial significativo en la predicción, detección y prevención de accidentes laborales en entornos industriales. Esta revisión sistemática, realizada conforme al protocolo PRISMA 2020, analiza 42 artículos científicos publicados entre 2019 y 2024 para sintetizar la evidencia disponible sobre aplicaciones de IA en seguridad industrial, con énfasis en su transferibilidad a contextos latinoamericanos. Se identifican las técnicas de IA dominantes (aprendizaje automático en el 71 % de los estudios, aprendizaje profundo en el 50 %), sus aplicaciones por sector (manufactura 55 %, análisis multisectoriales 29 %, minería 12 %), y las barreras sistémicas que limitan su adopción en América Latina (financiera, de datos, regulatoria, de capital humano y organizacional). El análisis revela que sistemas de bajo costo basados en visión por computador y sensores IoT, así como entrenamientos en realidad virtual, son viables para pymes industriales ecuatorianas. Las conclusiones señalan que América Latina enfrenta una brecha estructural en producción científica propia y que Ecuador, como caso ilustrativo, puede avanzar estratégicamente mediante la adopción de soluciones documentadas, el aprovechamiento de registros históricos de incidentes y el desarrollo de marco normativo propio.
Descargas
Citas
Antwi-Afari, M. F., Li, H., Anwer, S., y Yevu, S. K. (2023). Machine learning-based identification and classification of physical fatigue levels. International Journal of Industrial Ergonomics, 90, 103404. https://doi.org/10.1016/j.ergon.2022.103404
Arana-Landín, G., Laskurain-Iturbe, I., Arana, G., y Landín, G. (2023). Assessing the influence of Industry 4.0 technologies on occupational health and safety. Heliyon, 9(2), e13720. https://doi.org/10.1016/j.heliyon.2023.e13720
Boadu, E. F., Asante, K. O., y Ennin, S. A. (2023). Work-related respiratory health conditions: Systematic review of AI-assisted detection in industrial environments. BMJ Open Respiratory Research, 10, e001736. https://doi.org/10.1136/bmjresp-2023-001736
Chadyiwa, M., Okello, G., y Naicker, N. (2022). Investigating machine learning applications in the prediction of occupational injuries. Machine Learning and Knowledge Extraction, 4(3), 737–752. https://doi.org/10.3390/make4030037
Cotrim, T., Castelo Branco, J., y Conceiçao, C. (2022). Frontiers in occupational health and safety management. International Journal of Environmental Research and Public Health, 19(17), 10759. https://doi.org/10.3390/ijerph191710759
Davoudi Kakhki, F., Freeman, S. A., y Mosher, G. A. (2020). Predictive modeling for occupational safety outcomes and days away from work analysis in mining. International Journal of Environmental Research and Public Health, 17(19), 7054. https://doi.org/10.3390/ijerph17197054
Deng, J., Li, S., y Zhang, W. (2022). Classifying safety accident reports automatically using deep learning. Automation in Construction, 134, 104087. https://doi.org/10.1016/j.autcon.2021.104087
Di, Y., y Wang, E. (2021). Rock burst precursor recognition method based on recurrent neural networks. Rock Mechanics and Rock Engineering, 54, 1297–1308. https://doi.org/10.1007/s00603-020-02314-w
Duan, P., Li, H., Zheng, J., y Skitmore, M. (2023). Risk events recognition using smartphone and machine learning in industrial material handling. Engineering, Construction and Architectural Management, 30(8), 3461–3481. https://doi.org/10.1108/ECAM-10-2021-0937
Fang, W., Love, P. E., Luo, H., y Ding, L. (2022). Physiological computing for occupational health and safety in manufacturing. Advanced Engineering Informatics, 51, 101504. https://doi.org/10.1016/j.aei.2021.101504
Ganguli, R., Sturgul, J., y Arora, P. (2021). Effectiveness of NLP-based machine learning in analyzing incident narratives at a mine. Minerals, 11(7), 776. https://doi.org/10.3390/min11070776
Gihleb, R., Giuntella, O., Stella, L., y Wang, T. (2022). Industrial robots and occupational safety: Evidence from US manufacturing. Labour Economics, 78, 102205. https://doi.org/10.1016/j.labeco.2022.102205
Hashim, M., Taha, Z., y Mukherjee, T. (2021). Occupational health and safety risk assessment using IoT and machine learning in oil and gas. Process Safety and Environmental Protection, 149, 50–62. https://doi.org/10.1016/j.psep.2020.11.027
Hector, I., y Panjanathan, R. (2024). Predictive maintenance in Industry 4.0: A survey of planning models and machine learning techniques. PeerJ Computer Science, 10, e2016. https://doi.org/10.7717/peerj-cs.2016
Instituto Ecuatoriano de Seguridad Social (IESS). (2023). Estadísticas de accidentes de trabajo y enfermedades profesionales 2022. IESS. https://www.iess.gob.ec/es/seguro-de-riesgos-del-trabajo
Isailovic, V., Savic, S., Tadic, D., y Arsovski, S. (2021). Intelligent platform based on smart PPE for safety in industrial workplaces. Sensors, 21(14), 4652. https://doi.org/10.3390/s21144652
Isailovic, V., Savic, S., Arsovski, S., y Tadic, D. (2022). The compliance of head-mounted industrial PPE by using deep learning object detectors. Scientific Reports, 12, 15778. https://doi.org/10.1038/s41598-022-20282-9
Jan, Z., Ahamed, F., Mayer, W., Patel, N., Grossmann, G., Stumptner, M., y Kuusk, A. (2023). Artificial intelligence for industry 4.0: Systematic review of applications, challenges and opportunities. Expert Systems with Applications, 216, 119456. https://doi.org/10.1016/j.eswa.2022.119456
Jarota, M. (2023). Artificial intelligence in the work process: Reflection on EU AI regulations from OHS perspective. Computer Law & Security Review, 49, 105822. https://doi.org/10.1016/j.clsr.2023.105822
Khairuddin, M. Z. F., Othman, M., Ismail, N. H., y Yaakob, R. (2022a). Occupational injury risk mitigation: Machine learning approach and feature optimization for smart workplace surveillance. International Journal of Environmental Research and Public Health, 19(21), 13962. https://doi.org/10.3390/ijerph192113962
Khairuddin, M. Z. F., Othman, M., Ismail, N. H., y Yaakob, R. (2022b). Predicting occupational injury causal factors using text-based analytics. Frontiers in Public Health, 10, 984099. https://doi.org/10.3389/fpubh.2022.984099
Khairuddin, M. Z. F., Othman, M., Ismail, N. H., y Yaakob, R. (2023). Contextualizing injury severity from occupational accident reports using deep learning. PeerJ Computer Science, 9, e1985. https://doi.org/10.7717/peerj-cs.1985
Lema, D. G., Molina, F., Rogado, E., y Merino, J. (2022). AI-driven environmental monitoring for hazardous gas detection in industrial facilities. Process Safety and Environmental Protection, 162, 736–745. https://doi.org/10.1016/j.psep.2022.01.015
Lema, D. G., Molina, F., Rogado, E., y Merino, J. (2023). Low-cost system for real-time verification of PPE in industrial facilities using edge computing. Journal of Real-Time Image Processing, 20, 45. https://doi.org/10.1007/s11554-023-01280-w
Lingard, H., Cooke, T., y Gharaie, E. (2022). Machine learning for predicting worker injuries from accident reports in industry. Safety Science, 148, 105796. https://doi.org/10.1016/j.ssci.2022.105796
Mohapatra, P., Mishra, A., y Bhatt, R. (2024). Wearable network for multilevel physical fatigue prediction in manufacturing workers. PNAS Nexus, 3(10), pgae421. https://doi.org/10.1093/pnasnexus/pgae421
Nti, I. K., Quarcoo, J. A., Aning, J., y Fosu, G. K. (2022). Applications of artificial intelligence in engineering and manufacturing: A systematic review. Journal of Intelligent Manufacturing, 33, 1947–1968. https://doi.org/10.1007/s10845-021-01771-6
Organización Internacional del Trabajo. (2022). Declaración de la OIT relativa a los principios y derechos fundamentales en el trabajo (1998, enmendada en 2022). OIT. https://www.ilo.org/es/resource/otro/declaracion-de-1998-de-la-oit-relativa-los-principios-y-derechos
Paleyes, A., Urma, R. G., y Lawrence, N. D. (2022). Challenges in deploying machine learning: A survey of case studies. ACM Computing Surveys, 55(6), 1–29. https://doi.org/10.1145/3533378
Perez-Cerrolaza, J., Abella, J., Wartel, F., Farrall, M., y Cazorla, F. J. (2024). AI for safety-critical systems in industrial and transportation domains: A survey. ACM Computing Surveys, 56(6), 1–36. https://doi.org/10.1145/3626314
Pishgar, M., Hamid, M., Shabani, S., y Parsaei, H. (2021). REDECA: A novel framework to review artificial intelligence and its applications in occupational safety and health. Safety Science, 141, 105614. https://doi.org/10.1016/j.ssci.2021.105614
Reyes-López, A., Cantú-Quintanilla, G., y Sepúlveda-Guzmán, J. (2022). Factores de riesgo laboral en la industria manufacturera de México: Una revisión sistemática. Salud Pública de México, 64(3), 312–321. https://doi.org/10.21149/13456
Sai, L. S., Maheshwari, P., y Prasad, V. (2023). Machine learning approach for prediction of mining-induced stress in underground mines. Geomechanics and Geophysics for Geo-Energy and Geo-Resources, 9, 54. https://doi.org/10.1007/s40948-023-00701-5
Sarkar, S., Vinay, S., Raj, R., Maiti, J., y Mitra, P. (2019). Application of optimized machine learning techniques for prediction of occupational accidents. Computers and Operations Research, 106, 210–224. https://doi.org/10.1016/j.cor.2018.02.021
Scorgie, D., Olatunji, S., y Olatunji, O. (2023). Digital twin applications for worker safety monitoring in smart manufacturing. Computers & Industrial Engineering, 180, 109180. https://doi.org/10.1016/j.cie.2023.109180
Scorgie, D., Olatunji, S., y Olatunji, O. (2024). Virtual reality for safety training: A systematic literature review and meta-analysis. Safety Science, 171, 106372. https://doi.org/10.1016/j.ssci.2023.106372
Shah, I. A., y Mishra, S. (2024). Artificial intelligence in advancing occupational health and safety: An encapsulation of developments. Journal of Occupational Health, 66(1), uiad017. https://doi.org/10.1093/joccuh/uiad017
Sharma, M., Agarwal, S., y Singh, R. (2022). Analyzing occupational heat stress using sensor-based monitoring: A wearable approach with environmental ergonomics perspective. Applied Ergonomics, 100, 103584. https://doi.org/10.1016/j.apergo.2021.103584
Silva, A., Rodrigues, F., y Costa, M. (2024). Exploring AI applications in occupational safety: A bibliometric perspective on accident prevention. International Journal of Sustainability Management and Information Technologies, 10(2), 11. https://doi.org/10.11648/j.ijsmit.20241002.11
Tang, K. H. D. (2024). Artificial intelligence in occupational health and safety risk management of construction, mining and oil and gas. Journal of Engineering Research and Reports, 26(6), 241–253. https://doi.org/10.9734/jerr/2024/v26i61177
Wang, Y., y Chung, S. H. (2022). Artificial intelligence in safety-critical systems: A systematic review. Computers & Industrial Engineering, 164, 108209. https://doi.org/10.1016/j.cie.2022.108209
Woschank, M., Rauch, E., y Zsifkovits, H. (2020). A review of further directions for AI, machine learning and deep learning in smart logistics. Sustainability, 12(9), 3760. https://doi.org/10.3390/su12093760
Yang, S., Gao, Y., y Li, X. (2022a). Robot application and occupational injuries: Are robots necessarily safer? Safety Science, 147, 105623. https://doi.org/10.1016/j.ssci.2021.105623
Yang, C., Liu, Y., Li, H., y Wu, H. (2022b). AI-based anomaly detection in industrial IoT systems for predictive safety management. IEEE Transactions on Industrial Informatics, 18(8), 5255–5264. https://doi.org/10.1109/TII.2022.3155848
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2026 Hernán Alejandro Ortiz Carrasco , Rosa Maricela Ormaza Hugo
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Deprecated: json_decode(): Passing null to parameter #1 ($json) of type string is deprecated in /var/www/revista/revista.ojs/plugins/generic/citations/CitationsPlugin.inc.php on line 49
Esta publicación está bajo una 