Evaluation of artificial intelligence models and classical statistics models of time Series in forecasting the number of hospital inpatient admissions

Introduction: The study and analysis of each health system has become a necessity for its performance improvement through time. In this context, management and analysis of the number of patients is an important factor in the process of improving managers' decisions. The aims of this study were to explore and evaluate the use of multiple time series forecasting methods to predict monthly hospital inpatient admissions at six public hospitals in Mashhad city and to compare the accuracy performance of these methods

Methods: This cross-sectional modeling study was performed based on monthly data of inpatient admissions at six public hospitals in Mashhad from March 2004 through March 2016. Data were extracted from database of the Statistics Office of Mashhad University of Medical Sciences. Holt-winters, Seasonal Autoregressive Integrated Moving Average [SARIMA], Multilayer Perceptron [MLP] and Generalized Regression Neural Networks [GRNN] models were applied to forecast monthly inpatient numbers at each hospital. The error of the models in regard to the predicted values was reported through Mean Absolute Percentage Error [MAPE]

Results: Holt-Winters method, due to providing the optimal forecasting performance in four hospitals, could be an efficient method for predicting the number of inpatients in hospitals. Totally, the studied models with a MAPE from 2.13 percent to 4.12 percent showed acceptable performance in all six hospitals

Conclusion: Time series analysis is an adequate practical tool for predicting the number of hospital inpatient admissions. Given the unique characteristics of different hospitals, applied methods in this study, including modeling and data analysis can be used in other hospitals to improve their resource allocation and strategic planning

study on the direct and indirect costs of multiple sclerosis based on expanded disability status scale score in Khuzestan, Iran

Multiple sclerosis is a common and chronic neurologic disorder. This disorder imposes physical, economic, and psychosocial burden on individuals, their families and society. This study aims to analyze the costs of multiple sclerosis disease based on the severity of disability. We performed a cross-sectional cost of illness study. This study was conducted in 332 patients of Khuzestan province of Iran. Data were included: Patient's characteristics, disability status, medical, and nonmedical costs and were gathered by using the questionnaire during 3 months period. Costs analysis was performed in the basis of expanded disability status scale [EDSS]. Data were analyzed by using SPSS 18 software. Mean age of the patients was 33.5 [standard deviation [SD]: 9.1] and 70.5% of patients were female. Mean EDSS score of the patients was 2.2 [SD: 1.6]. Most patients [92.1%] had relapsing remitting multiple sclerosis [MS] form of the disease. Costs mean per patients was 8.6 +/- 7.9 million Rial. The direct and indirect costs were 93.1% and 6.9% of total costs, respectively. The major cost of the disease belongs to the pharmaceutical treatment [22% of costs]. The majority costs [approximately 62%] attributed to EDSS of 6-7 and >7. Furthermore, there was strong significant relationship between cost of illness and disability severity of patients [P < 0.05]. Cost mean per MS patients was relatively high. Furthermore, the results showed that cost of disease had positive and significant relationships with EDSS score that is, progression of disability increase costs of patients

Effects of L-carnitine and L-acetyl-carnitine on testicular sperm motility and chromatin quality

Sperm cells extracted from testes [TESE] have poor chromatin quality and motility. Various substances are used in the laboratory to increase sperm motility and improve the ART outcomes; however, there are few research which considered improving both sperm motility and chromatin quality. The aim of this investigation was to evaluate the improvement of the testicular sperm motility and chromatin quality exposed to L-carnitine [LC] and L-acetyl-carnitine [LAC], which are normally concentrated in testis and epididymis, compared with Pentoxifylline [PF], which used for sperm motility enhancement in IVF procedures. TESE samples from 30 male mice divided into four parts. The sperm samples were added to Ham' F10 [control] or the media contained 1.76mM of LC, LAC or PF], then, the samples were kept in the room temperature for 30, 90 and 180 min. At each time step, sperm motility and chromatin quality were assessed. Chromatin quality was evaluated by chromomycin A3 and aniline blue. Statistical analysis was performed using one way analysis of variance [ANOVA]. A p-value less than 0.05 were accepted as a statistically significant difference. The results showed LC, LAC and PF significantly increased the sperm motility. However, sperm chromatin quality only improved significantly by administration of LC and LAC. Administration of LC and LAC to the testicular sperm samples can lead to improve both sperm motility and chromatin quality. It may be because they can mimic in vivo sperm condition during late spermatogenesis