Department of Research and Development, Human Total Care, Utrecht, The Netherlands.
Department of Epidemiology and Biostatistics, Amsterdam Public Health Research Institute, Amsterdam UMC, Location VU University Medical Center, Amsterdam, The Netherlands.
Int Arch Occup Environ Health. 2020 Nov;93(8):1007-1012. doi: 10.1007/s00420-020-01548-z. Epub 2020 May 11.
A previously developed prediction model and decision tree were externally validated for their ability to identify occupational health survey participants at increased risk of long-term sickness absence (LTSA) due to mental disorders.
The study population consisted of N = 3415 employees in mobility services who were invited in 2016 for an occupational health survey, consisting of an online questionnaire measuring the health status and working conditions, followed by a preventive consultation with an occupational health provider (OHP). The survey variables of the previously developed prediction model and decision tree were used for predicting mental LTSA (no = 0, yes = 1) at 1-year follow-up. Discrimination between survey participants with and without mental LTSA was investigated with the area under the receiver operating characteristic curve (AUC).
A total of n = 1736 (51%) non-sick-listed employees participated in the survey and 51 (3%) of them had mental LTSA during follow-up. The prediction model discriminated (AUC = 0.700; 95% CI 0.628-0.773) between participants with and without mental LTSA during follow-up. Discrimination by the decision tree (AUC = 0.671; 95% CI 0.589-0.753) did not differ significantly (p = 0.62) from discrimination by the prediction model.
At external validation, the prediction model and the decision tree both poorly identified occupational health survey participants at increased risk of mental LTSA. OHPs could use the decision tree to determine if mental LTSA risk factors should be explored in the preventive consultation which follows after completing the survey questionnaire.
为了评估先前开发的预测模型和决策树在识别因精神障碍而长期病假（LTSA）风险增加的职业健康调查参与者方面的能力，对其进行了外部验证。
研究人群由 Mobility Services 中的 3415 名员工组成，他们于 2016 年受邀参加职业健康调查，包括在线问卷调查，以衡量健康状况和工作条件，随后由职业健康提供者（OHP）进行预防性咨询。先前开发的预测模型和决策树的调查变量用于预测 1 年随访时的精神 LTSA（无=0，有=1）。使用接收者操作特征曲线（AUC）下的面积来研究调查参与者是否存在精神 LTSA 的差异。
共有 n=1736（51%）名非病假员工参加了调查，其中 51 人（3%）在随访期间患有精神 LTSA。预测模型（AUC=0.700；95%CI 0.628-0.773）能够区分随访期间患有和不患有精神 LTSA 的参与者。决策树的区分度（AUC=0.671；95%CI 0.589-0.753）与预测模型的区分度无显著差异（p=0.62）。
在外部验证中，预测模型和决策树均无法很好地识别职业健康调查参与者中精神 LTSA 风险增加的人群。OHP 可以使用决策树来确定在完成问卷调查后的预防性咨询中是否需要探索精神 LTSA 风险因素。
