Developing Action Plans Based on Machine Learning Analysis to Prevent Sick Leave in a Manufacturing Plant.

OBJECTIVE: We aimed to develop action plans for employees' health promotion based on a machine learning model to predict sick leave at a Japanese manufacturing plant. METHODS: A random forest model was developed to predict sick leave. We developed plans for workers' health promotion based on variable importance and partial dependence plots. RESULTS: The model showed an area under the receiving operating characteristic curve of 0.882. The higher scores on the Brief Job Stress Questionnaire stress response, younger age, and certain departments were important predictors for sick leave due to mental disorders. We proposed plans to effectively use the Brief Job Stress Questionnaire and provide more support for younger workers and managers of high-risk departments. CONCLUSIONS: We described a process of action plan development using a machine learning model, which may be beneficial for occupational health practitioners.

[The US Government's effort in decreasing the cost of sleep-related problems and its outcome].

Sleepiness and inattention caused by sleep and circadian rhythm disorders or inadequate sleep habits adversely affect workers in many industries as well as the general public, and these disorders are likely to lead to public health and safety problems and adversely affect civilian life. Evidence is accumulating that these sleep related problems are contributing factors not only in many errors of judgement and accidents, but also related to some highly prevalent diseases, such as diabetes, obesity and hypertension. For each of these societal concerns, sleep science must be translated to the general public and to those in policy positions for improving public policy and public health awareness. In the United State, the National Commission for Sleep Disorders Research (established by the US Congress in 1998) completed a comprehensive report of its findings in 1993 to address these problems. The commission estimated that sleep disorders and sleepiness cost the United States $50 billion and called for permanent and concentrated efforts in expanding basic and clinical research on sleep disorders as well as in improving public awareness of the dangers of inadequate sleep hygiene. As a result of these efforts, the number of sleep centers has increased steadily and the total of the NIH (National Institutes of Health) funding for sleep research has also grown. In response to this progress in the US (together with appeals by Japanese Sleep Specialists), the Science Council of Japan published "The Recommendation of Creation of Sleep Science and Progression of Research" in 2002. In this article, we introduce and detail to the Japanese readers the US Government's efforts focusing on the report of the National Commission for Sleep Disorders Research, and we believe that the US Government's effort is a good example for the Japanese society to follow.

CSF histamine levels in rats reflect the central histamine neurotransmission.

Reduced cerebrospinal fluid (CSF) histamine levels were found in human hypersomnia. To evaluate the functional significance of changes in CSF histamine levels, we measured the levels in rats across 24h, after the administration of wake-promoting compounds modafinil, amphetamine, and thioperamide, and after sleep deprivation and food deprivation. Thioperamide significantly increased CSF histamine levels with little effects on locomotor activation. Both modafinil and amphetamine markedly increased the locomotor activity, but had no effects on histamine. The levels are high during active period and are markedly elevated by sleep deprivation, but not by food deprivation. Our study suggests that CSF histamine levels in rats reflect the central histamine neurotransmission and vigilance state changes, providing deeper insight into the human data.