Bahadir Geniş; Behcet Cosar
Abstract
Background: Mental disorders are generally a significant reason for increased morbidity. They constitute a serious disease burden. One of the main reasons for this disease burden is long hospitalization periods. Objective: The current study investigated the length of hospital stay and the variables affecting ...
Read More
Background: Mental disorders are generally a significant reason for increased morbidity. They constitute a serious disease burden. One of the main reasons for this disease burden is long hospitalization periods. Objective: The current study investigated the length of hospital stay and the variables affecting it in patients treated in the Gazi University Hospital Psychiatry Department between 2005-2016. Methods: Patient diagnoses were analyzed according to the International Classification of Diseases 10th Revision (ICD-10). Data was obtained for 7027 hospitalizations over a 12-year period. Records of repeated hospitalizations, non-psychiatric primary diagnoses, and missing data were not included in the analysis. As a result, data from 5129 hospitalizations were included in the analysis. Results: Mean age of the sample was 45.27±14.69, and 62.5% (n=3204) of the patients were male. Mean hospitalization period was 28.66±17.25 days. Schizophrenia and depressive disorder significantly prolonged hospital stay, while substance addiction shortened the duration of hospitalization (P < 0.001). It was found that the duration of hospitalization decreased significantly over the years (P < 0.001). Advanced age (P < 0.001), recurrent admission (P < 0.001), and female gender (P = 0.029) were other variables affecting this period. Conclusion: Schizophrenia and depression are the most common psychiatric disorders in the inpatient service, and these disorders prolong hospitalization periods. The duration of hospital stay is considerably less in substance addiction than in other psychiatric disorders. Non-clinical variables, such as year of hospitalization, may affect the length of hospital stay.
Samaneh Aghajani; Mehrdad Kargari
Abstract
Background: Length of stay is one of the most important indicators in assessing hospital performance. A shorter stay can reduce the costs per discharge and shift care from inpatient to less expensive post-acute settings. It can lead to a greater readmission rate, better resource management, and more ...
Read More
Background: Length of stay is one of the most important indicators in assessing hospital performance. A shorter stay can reduce the costs per discharge and shift care from inpatient to less expensive post-acute settings. It can lead to a greater readmission rate, better resource management, and more efficient services. Objective: This study aimed to identify the factors influencing length of hospital stay and predict length of stay in the general surgery department. Methods: In this study, patient information was collected from 327 records in the surgery department of Shariati Hospital using data mining techniques to determine factors influencing length of stay and to predict length of stay using three algorithms, namely decision tree, Naïve Bayes, and k-nearest neighbor algorithms. The data was split into a training data set and a test data set, and a model was built for the training data. A confusion matrix was obtained to calculate accuracy. Results: Four factors presented: surgery type (hemorrhoid), average number of visits per day, number of trials, and number of days of hospitalization before surgery; the most important of these factors was length of stay. The overall accuracy of the decision tree was 88.9% for the training data set. Conclusions: This study determined that all three algorithms can predict length of stay, but the decision tree performs the best.