We developed an evidence-based practice guideline to support occupational safety and health (OSH) professionals in assessing the risk due to lifting and in selecting effective preventive measures for low back pain (LBP) in the Netherlands. The guideline was developed at the request of the Dutch government by a project team of experts and OSH professionals in lifting and work-related LBP. The recommendations for risk assessment were based on the quality of instruments to assess the risk on LBP due to lifting. Recommendations for interventions were based on a systematic review of the effects of worker- and work directed interventions to reduce back load due to lifting. The quality of the evidence was rated as strong (A), moderate (B), limited (C) or based on consensus (D). Finally, eight experts and twenty-four OSH professionals commented on and evaluated the content and the feasibility of the preliminary guideline. For risk assessment we recommend loads heavier than 25 kg always to be considered a risk for LBP while loads less than 3 kg do not pose a risk. For loads between 3–25 kg, risk assessment shall be performed using the Manual handling Assessment Charts (MAC)-Tool or National Institute for Occupational Safety and Health (NIOSH) lifting equation. Effective work oriented interventions are patient lifting devices (Level A) and lifting devices for goods (Level C), optimizing working height (Level A) and reducing load mass (Level C). Ineffective work oriented preventive measures are regulations to ban lifting without proper alternatives (Level D). We do not recommend worker-oriented interventions but consider personal lift assist devices as promising (Level C). Ineffective worker-oriented preventive measures are training in lifting technique (Level A), use of back-belts (Level A) and pre-employment medical examinations (Level A). This multidisciplinary evidence-based practice guideline gives clear criteria whether an employee is at risk for LBP while lifting and provides an easy-reference for (in)effective risk reduction measures based on scientific evidence, experience, and consensus among OSH experts and practitioners.
Citations
Existing methods for practically evaluating musculoskeletal exposures such as posture and repetition in workplace settings have limitations. We aimed to automate the estimation of parameters in the revised United States National Institute for Occupational Safety and Health (NIOSH) lifting equation, a standard manual observational tool used to evaluate back injury risk related to lifting in workplace settings, using depth camera (Microsoft Kinect) and skeleton algorithm technology.
A large dataset (approximately 22,000 frames, derived from six subjects) of simultaneous lifting and other motions recorded in a laboratory setting using the Kinect (Microsoft Corporation, Redmond, Washington, United States) and a standard optical motion capture system (Qualysis, Qualysis Motion Capture Systems, Qualysis AB, Sweden) was assembled. Error-correction regression models were developed to improve the accuracy of NIOSH lifting equation parameters estimated from the Kinect skeleton. Kinect-Qualysis errors were modelled using gradient boosted regression trees with a Huber loss function. Models were trained on data from all but one subject and tested on the excluded subject. Finally, models were tested on three lifting trials performed by subjects not involved in the generation of the model-building dataset.
Error-correction appears to produce estimates for NIOSH lifting equation parameters that are more accurate than those derived from the Microsoft Kinect algorithm alone. Our error-correction models substantially decreased the variance of parameter errors. In general, the Kinect underestimated parameters, and modelling reduced this bias, particularly for more biased estimates. Use of the raw Kinect skeleton model tended to result in falsely high safe recommended weight limits of loads, whereas error-corrected models gave more conservative, protective estimates.
Our results suggest that it may be possible to produce reasonable estimates of posture and temporal elements of tasks such as task frequency in an automated fashion, although these findings should be confirmed in a larger study. Further work is needed to incorporate force assessments and address workplace feasibility challenges. We anticipate that this approach could ultimately be used to perform large-scale musculoskeletal exposure assessment not only for research but also to provide real-time feedback to workers and employers during work method improvement activities and employee training.
Citations
Citations