Objective: To explore the risk factors of neck work-related musculoskeletal disorders (WMSDs) among automobile manufacturing enterprise workers, and construct the risk prediction model. Methods: In May 2022, a cluster convenience sampling method was used to selet all front-line workers from an automobile manufacturing factory in Xiangyang City as the research objects. And a questionnaire survey was conducted using the modified Musculoskeletal Disorders Questionnaire to analyze the occurrence and exposure to risk factors of neck WMSDs. Logistic regression was used to analyze the influencing factors of workers' neck WMSDs symptoms, and Nomogram column charts was used to construct the risk prediction model. The accuracy of the model was evaluated by the receiver operating characteristic (ROC) curve, the Bootstrap resampling method was used to verify the model, Hosmer-Lemeshow goodness of fit test was used to evaluate the model, and the Calibration curve was drawn. Results: A total of 1783 workers were surveyed, and the incidence of neck WMSDs symptoms was 24.8% (442/1783). Univariate logistic regression showed that age, female, smoking, working in uncomfortable postures, repetitive head movement, feeling constantly stressed at work, and completing conflicting tasks in work could increase the risk of neck WMSDs symptoms in automobile manufacturing enterprise workers (OR=1.37, 95%CI: 1.16-1.62; OR=2.85, 95%CI: 1.56-5.20; OR=1.50, 95%CI: 1.18-1.91; OR=1.18, 95%CI: 1.02-1.37; OR=1.34, 95%CI: 1.04-1.72; OR=1.62, 95%CI: 1.21-2.17; OR=1.48, 95%CI: 1.13-1.92; P<0.05). While adequate rest time could reduce the risk of neck WMSDs symptoms (OR=0.56, 95%CI: 0.52-0.86, P<0.05). The risk prediction model of neck WMSDs of workers in automobile manutacturing factory had good prediction efficiency, and the area under the ROC curve was 0.72 (95%CI: 0.70-0.75, P<0.001) . Conclusion: The occurrence of neck WMSDs symptoms of workers in automobile manufacturing factory is relatively high. The risk prediction model constructed in this study can play a certain auxiliary role in predicting neck WMSDs symptoms of workers in automobile manufacturing enterprise workers.
目的： 探讨汽车制造业工人颈部工作相关肌肉骨骼疾患（WMSDs）的影响因素，并构建风险预测模型。 方法： 于2022年5月，采用方便抽样法，选取襄阳市1家汽车制造厂所有一线工人作为研究对象，采用改良《肌肉骨骼疾患调查问卷》调查其颈部WMSDs症状发生情况及危险因素暴露情况，采用logistic回归分析工人颈部WMSDs症状发生的影响因素，用Nomogram列线图构建风险预测模型。通过受试者工作特征（ROC）曲线评价模型准确性，运用Bootstrap重抽样的方法进行模型验证，Hosmer-Lemeshow拟合优度检验评价模型，绘制校准曲线（Calibration curve）。 结果： 共调查1 783名工人，颈部WMSDs症状发生率为24.8%（442/1 783）。多因素logistic回归分析显示，年龄、女性、吸烟、以不舒服姿势工作、头部重复动作、总是感到工作压力大、完成有矛盾的工作会增加汽车制造业工人颈部WMSDs症状的发生风险（OR=1.37，95%CI：1.16~1.62；OR=2.85，95%CI：1.56~5.20；OR=1.50，95%CI：1.18~1.91；OR=1.18，95%CI：1.02~1.37；OR=1.34，95%CI：1.04~1.72；OR=1.62，95%CI：1.21~2.17；OR=1.48，95%CI：1.13~1.92；P<0.05），而休息时间充足会降低颈部WMSDs症状的发生风险（OR=0.56，95%CI：0.52~0.86，P<0.05）。该汽车制造厂工人颈部WMSDs风险预测模型具有较好的预测效能，ROC曲线下面积（AUC）为0.72（95%CI：0.70~0.75，P<0.001）。 结论： 该汽车制造厂工人颈部WMSDs症状发生率较高，本研究构建的风险预测模型可以对汽车制造业工人颈部WMSDs症状发生起到一定的辅助预测作用。.
Keywords: Automobile manufacturer; Musculoskeletal disorders; Musculoskeletal pain; Neck; Prediction model.