TY - JOUR JF - RJMS JO - RJMS VL - 20 IS - 115 PY - 2014 Y1 - 2014/1/01 TI - Application of multilevel model in determining the effective factors in the length of stay among appendectomy patients TT - کاربرد مدل چندسطحی در تعیین عوامل موثر بر طول مدت اقامت بیماران آپاندکتومی N2 -  Background: Because of the limitations concerning health centers and hospitals in Iran, the length of stays at the hospitals is of high importance. The purpose of this research is to investigate the factors affecting the length of stay among appendectomy patients at Social Security Organization hospitals using a multilevel model. Methods: We presented an applied-analytical study which investigated the relation between length of stay among appendectomy patients at Social Security Organization hospitals and variables namely, age, gender, type of insurance and the inpatient bed count at hospital. The information of patients who were hospitalized in hospitals for appendectomy during the first 6 months of 2009, were gathered from HIS system of the hospitals. The three-level regression statistical method was used to analyze the data. All analyses were conducted in SAS 9.1 software. Results: The findings show that the average length of stay among patients was 2.4 days and gender, age, type of insurance and the number of inpatient bed count at the hospital had no effect on the length of stay at hospital. The results also indicated that there is a significant difference between the lengths of stay in different hospitals but no significant difference was observed between different provinces. Conclusion: Considering the dependence between the data and using the multi-level regression model led to concluding the significant difference between the length of stay in different hospitals.  SP - 70 EP - 77 AU - mohamadali Noruzi, Marzieh AU - Hosseni, Agha Fatemeh AU - Gohari, Mahmood Reza AD - Iran University of Medical Sciences KW - Multilevel regression KW - Length of stay KW - Appendectomy KW - Inpatient UR - http://rjms.iums.ac.ir/article-1-2927-en.html ER -