ABSTRACT
BACKGROUND: The present study describes the burden of occupational diseases in Iran based on the results of the Global Burden of Disease study conducted in 2010 (GBD 2010). This study aimed to determine the burden of occupational diseases in Iran based on the results of GBD 2010. It is a cross-sectional study. METHODS: Disability-adjusted life years (DALYs) of occupational diseases were calculated based on the prevalence rates obtained through model estimation, as well as GBD 2010 disability weights and mortality rates obtained from different data registry systems of Iran. Causal association criteria application to select risk outcome pairs, estimation of exposure to each risk factor in the population, estimation of etiological effect size, selection of a counterfactual exposure distribution, risk assessment, and identification of burden attributable to each risk factor were the main conducted statistical steps. RESULTS: There was an increasing trend of DALYs (710.08/100,000 people in 1990 and 833.00/100,000 people in 2005) followed by a slight decrease (833.00/100,000 in 2005-784.55/100,000 people in 2010). A total of 50.4% and 36% of total DALYs per 100,000 people were due to the adverse effects of musculoskeletal disorders and work-related injuries, respectively. CONCLUSIONS: Musculoskeletal disorders and work-related injuries are the most important adverse consequences of work-related risks that require urgent interventions to be controlled. Male workers (15-25 years and over 60) with the highest DALYs and mortality rates need more training programs, safety regulations, and higher level of protection support. In spite the decreasing trend of occupational disease related DALYs and death rates in Iran in recent years, a long-term effort is required to maintain the currently decreasing trend.
ABSTRACT
OBJECTIVES: Accurate prediction of patients' length of stay is highly important. This study compared the performance of artificial neural network and adaptive neuro-fuzzy system algorithms to predict patients' length of stay in intensive care units (ICU) after cardiac surgery. METHODS: A cross-sectional, analytical, and applied study was conducted. The required data were collected from 311 cardiac patients admitted to intensive care units after surgery at three hospitals of Shiraz, Iran, through a non-random convenience sampling method during the second quarter of 2016. Following the initial processing of influential factors, models were created and evaluated. RESULTS: The results showed that the adaptive neuro-fuzzy algorithm (with mean squared error [MSE] = 7 and R = 0.88) resulted in the creation of a more precise model than the artificial neural network (with MSE = 21 and R = 0.60). CONCLUSIONS: The adaptive neuro-fuzzy algorithm produces a more accurate model as it applies both the capabilities of a neural network architecture and experts' knowledge as a hybrid algorithm. It identifies nonlinear components, yielding remarkable results for prediction the length of stay, which is a useful calculation output to support ICU management, enabling higher quality of administration and cost reduction.
