Combining Postural Sway Parameters and Machine Learning to Assess Biomechanical Risk Associated with Load-Lifting Activities
<b>Background/Objectives</b>: Long-term work-related musculoskeletal disorders are predominantly influenced by factors such as the duration, intensity, and repetitive nature of load lifting. Although traditional ergonomic assessment tools can be effective, they are often challenging and...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/1/105 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549248080904192 |
|---|---|
| author | Giuseppe Prisco Maria Agnese Pirozzi Antonella Santone Mario Cesarelli Fabrizio Esposito Paolo Gargiulo Francesco Amato Leandro Donisi |
| author_facet | Giuseppe Prisco Maria Agnese Pirozzi Antonella Santone Mario Cesarelli Fabrizio Esposito Paolo Gargiulo Francesco Amato Leandro Donisi |
| author_sort | Giuseppe Prisco |
| collection | DOAJ |
| description | <b>Background/Objectives</b>: Long-term work-related musculoskeletal disorders are predominantly influenced by factors such as the duration, intensity, and repetitive nature of load lifting. Although traditional ergonomic assessment tools can be effective, they are often challenging and complex to apply due to the absence of a streamlined, standardized framework. Recently, integrating wearable sensors with artificial intelligence has emerged as a promising approach to effectively monitor and mitigate biomechanical risks. This study aimed to evaluate the potential of machine learning models, trained on postural sway metrics derived from an inertial measurement unit (IMU) placed at the lumbar region, to classify risk levels associated with load lifting based on the Revised NIOSH Lifting Equation. <b>Methods</b>: To compute postural sway parameters, the IMU captured acceleration data in both anteroposterior and mediolateral directions, aligning closely with the body’s center of mass. Eight participants undertook two scenarios, each involving twenty consecutive lifting tasks. Eight machine learning classifiers were tested utilizing two validation strategies, with the Gradient Boost Tree algorithm achieving the highest accuracy and an Area under the ROC Curve of 91.2% and 94.5%, respectively. Additionally, feature importance analysis was conducted to identify the most influential sway parameters and directions. <b>Results</b>: The results indicate that the combination of sway metrics and the Gradient Boost model offers a feasible approach for predicting biomechanical risks in load lifting. <b>Conclusions</b>: Further studies with a broader participant pool and varied lifting conditions could enhance the applicability of this method in occupational ergonomics. |
| format | Article |
| id | doaj-art-16f82ba2da2848de89f222542ef9d68c |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-16f82ba2da2848de89f222542ef9d68c2025-01-10T13:16:44ZengMDPI AGDiagnostics2075-44182025-01-0115110510.3390/diagnostics15010105Combining Postural Sway Parameters and Machine Learning to Assess Biomechanical Risk Associated with Load-Lifting ActivitiesGiuseppe Prisco0Maria Agnese Pirozzi1Antonella Santone2Mario Cesarelli3Fabrizio Esposito4Paolo Gargiulo5Francesco Amato6Leandro Donisi7Department of Medicine and Health Sciences, University of Molise, 86100 Campobasso, ItalyDepartment of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, 80138 Naples, ItalyDepartment of Medicine and Health Sciences, University of Molise, 86100 Campobasso, ItalyDepartment of Engineering, University of Sannio, 82100 Benevento, ItalyDepartment of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, 80138 Naples, ItalyInstitute of Biomedical and Neural Engineering, Reykjavik University, 102 Reykjavik, IcelandDepartment of Information Technology and Electrical Engineering, University of Naples Federico II, 80125 Naples, ItalyDepartment of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, 80138 Naples, Italy<b>Background/Objectives</b>: Long-term work-related musculoskeletal disorders are predominantly influenced by factors such as the duration, intensity, and repetitive nature of load lifting. Although traditional ergonomic assessment tools can be effective, they are often challenging and complex to apply due to the absence of a streamlined, standardized framework. Recently, integrating wearable sensors with artificial intelligence has emerged as a promising approach to effectively monitor and mitigate biomechanical risks. This study aimed to evaluate the potential of machine learning models, trained on postural sway metrics derived from an inertial measurement unit (IMU) placed at the lumbar region, to classify risk levels associated with load lifting based on the Revised NIOSH Lifting Equation. <b>Methods</b>: To compute postural sway parameters, the IMU captured acceleration data in both anteroposterior and mediolateral directions, aligning closely with the body’s center of mass. Eight participants undertook two scenarios, each involving twenty consecutive lifting tasks. Eight machine learning classifiers were tested utilizing two validation strategies, with the Gradient Boost Tree algorithm achieving the highest accuracy and an Area under the ROC Curve of 91.2% and 94.5%, respectively. Additionally, feature importance analysis was conducted to identify the most influential sway parameters and directions. <b>Results</b>: The results indicate that the combination of sway metrics and the Gradient Boost model offers a feasible approach for predicting biomechanical risks in load lifting. <b>Conclusions</b>: Further studies with a broader participant pool and varied lifting conditions could enhance the applicability of this method in occupational ergonomics.https://www.mdpi.com/2075-4418/15/1/105biomechanical risk assessmentmachine learningphysical ergonomicspostural swayRevised NIOSH Lifting Equationwearable inertial sensors |
| spellingShingle | Giuseppe Prisco Maria Agnese Pirozzi Antonella Santone Mario Cesarelli Fabrizio Esposito Paolo Gargiulo Francesco Amato Leandro Donisi Combining Postural Sway Parameters and Machine Learning to Assess Biomechanical Risk Associated with Load-Lifting Activities Diagnostics biomechanical risk assessment machine learning physical ergonomics postural sway Revised NIOSH Lifting Equation wearable inertial sensors |
| title | Combining Postural Sway Parameters and Machine Learning to Assess Biomechanical Risk Associated with Load-Lifting Activities |
| title_full | Combining Postural Sway Parameters and Machine Learning to Assess Biomechanical Risk Associated with Load-Lifting Activities |
| title_fullStr | Combining Postural Sway Parameters and Machine Learning to Assess Biomechanical Risk Associated with Load-Lifting Activities |
| title_full_unstemmed | Combining Postural Sway Parameters and Machine Learning to Assess Biomechanical Risk Associated with Load-Lifting Activities |
| title_short | Combining Postural Sway Parameters and Machine Learning to Assess Biomechanical Risk Associated with Load-Lifting Activities |
| title_sort | combining postural sway parameters and machine learning to assess biomechanical risk associated with load lifting activities |
| topic | biomechanical risk assessment machine learning physical ergonomics postural sway Revised NIOSH Lifting Equation wearable inertial sensors |
| url | https://www.mdpi.com/2075-4418/15/1/105 |
| work_keys_str_mv | AT giuseppeprisco combiningposturalswayparametersandmachinelearningtoassessbiomechanicalriskassociatedwithloadliftingactivities AT mariaagnesepirozzi combiningposturalswayparametersandmachinelearningtoassessbiomechanicalriskassociatedwithloadliftingactivities AT antonellasantone combiningposturalswayparametersandmachinelearningtoassessbiomechanicalriskassociatedwithloadliftingactivities AT mariocesarelli combiningposturalswayparametersandmachinelearningtoassessbiomechanicalriskassociatedwithloadliftingactivities AT fabrizioesposito combiningposturalswayparametersandmachinelearningtoassessbiomechanicalriskassociatedwithloadliftingactivities AT paologargiulo combiningposturalswayparametersandmachinelearningtoassessbiomechanicalriskassociatedwithloadliftingactivities AT francescoamato combiningposturalswayparametersandmachinelearningtoassessbiomechanicalriskassociatedwithloadliftingactivities AT leandrodonisi combiningposturalswayparametersandmachinelearningtoassessbiomechanicalriskassociatedwithloadliftingactivities |