Characterized by persistent fatigue, pain, cognitive impairment and sleep difficulties, Chronic Fatigue Syndrome (CFS) have been common in clinical practice in the last decades. Studies indicate multiple factors that contribute to CFS development: poor sleep, dehydration, psychological stress, hormonal dysfunction, infections, nutrient deficiencies, among others. In work conditions of risk, development of CFS increases significantly the chance of fatal accidents, like the work on shifts of mines, for instance. The work environment of shift workers on mines suggests the presence of factors that increase the risk of developing CFS. This study aims to assess the risk of chronic fatigue by means of whether individuals had an occurrence of absenteeism. A cross-sectional study collected data on 621 shift workers, measuring 8 anthropometric and 11 biochemical variables as well as age and gender, mounting 21 variables. After imputing missing data, logistic regression was fitted by three approaches: Stepwise selection as well as Lasso and Elastic-Net regularization. Each model was compared between imputed and complete-cases datasets as well as with each other. Results suggest that the models do not discriminate very well due to noise inherent to the dependent variable’s nature. However, all models agree on indicating effects of Sodium and Total Cholesterol on the risk of skipping work. The Stepwise model also indicates LDL and Triglycerides as significative factors on absenteeism while both Lasso and Elastic-Net show effects for LDL instead. The Elastic-Net model alone suggests an effect os Potassium on the risk of skipping work, though inconclusive according to the literature.