sadi banar

neurosurgery reoperation that occurs for various reasons such as complications of primary surgery, planned reoperation, emergency or unplanned reoperation, and increase the financial burden of the hospital and the patient, poor prognosis, and increase the length of stay in hospital and intensive care unit for the patient. Neurosurgery patients are among the patients in whom reoperations need to be evaluated. Determining the factors leading to reoperations in the Neurosurgery Intensive Care Unit determines the causes and improves the quality of the system to prevent preventable reoperations.

In this cross-sectional retrospective study, the information of patients undergoing reoperation including the type of disease and initial surgery, reasons for reoperation were identified. The frequency of each of the three variables was examined in pairs. All reoperations and returns to the operating room during 5 consecutive years were reviewed. Information of all patients including demographic information, underlying disease, smoking and alcohol, cause of primary and reoperation surgery, medical history, type of operation, complications of the surgery, postoperative care were examined.

In this study, it was found that age, sex, initial diagnosis, the distance between surgery and readmission, underlying disease, ICU admission, were not associated with the occurrence of neurosurgery reoperation. Variables associated with the occurrence of neurosurgery reoperation include open surgery, surgical disease including Cerebrovascular, duration of the first surgery, first emergency surgery, duration of further anesthesia in the first operation, bleeding rate and need for a packed cell, Need to receive FFP, some hospital complications

Determining the factors that cause neurosurgery re-operation, prevent such surgeries if possible and reduce costs and hospital load, and also patients suffer fewer complications and mortality

Similar to industrial units, hospitals comprise of production factors including capital, human resource, technology and management. Successful performance of hospitals depends upon the way in which resources and in particular beds are allocated to patients. Thus it is necessary to implement an effective bed management so that on-demand healthcare services are accessible. In the same vein, hospitals need business intelligence tools to increase productivity, predict resource and equipment capacity and upgrade the healthcare service level so that they can achieve an effective bed management. Thus present research aimed to design a business intelligence model for bed allocation based on patient prioritization and allocation of equipment and services.

First the primary model was provided for bed allocation based on prioritization in a business intelligence concept framework. Then according to the conceptual model, required data were collected from various databases of neurosurgical intensive care units (ICUs) of Loqhman Hakim hospital by using ETL process and building data warehouse. In the next step, data mining classification algorithms were used to classify patients and develop prediction model. Then, patient classes were prioritized and simulation model was used to identify the effect of this prioritization. At last, the final model was provided.

The primary model for bed allocation based on prioritization in business intelligence concept framework was tested by data collection from 420 patients, data mining to classify them using decision tree technique with %87.02accuracy, prioritization of patient classes using PROMETHEE technique and simulation of 14 ICU beds based on collected data. Finally, it was estimated that the monthly number of hospitalized patients with and without prioritization were 76 and 86 respectively, Discussion and

After observing the positive results of the primary model for bed allocation based on prioritization including a 13 percent increase in monthly admission numbers and in turn, increased productivity proving model effectiveness, the next step was to develop a comprehensive business intelligence model for bed allocation based on prioritization of patients. The model was designed in business intelligence framework using online data collected from patients. The information provided by this model cAan be an effective decision making support for physicians and healthcare service providers in choosing patients in admission process.

The length of hospital stay is an important indicator that can be useful for financial and management planning of hospitals. If patients who are going to stay in the hospital for a long time can be identified immediately after admission, Appropriate resources can be made available to try to speed up health care right from the start. Therefore, due to aging and on the other hand, the long queue for using ICU beds, the present study was conducted to determine the factors related to the length of stay of patients in the neurosurgery ICU of Loghman Hakim Hospital.

This is a retrospective descriptive study. The studied samples were extracted from 543 computer files of patients admitted to the ICU of Neurosurgery of Loghman Hakim Hospital affiliated to Shahid Beheshti University of Medical Sciences in the period 2016-2017. Then, using Spss software version 25, the relationship between each of the variables and the length of stay was analyzed using the chi-square test.

Based on the results of the study, the statistical population consisted of 543 patients with a mean age of 18.07±43.34, including 42.4% female and 57.6% male. The mean length of stay was 5/86±6/33days and the factors related to the length of stay of the 15 variables included: diagnosis, hypertension, type of surgery and postoperative complications: pneumonia, meningitis, epilepsy.

Using the information obtained from the analysis of the patient length of stay in hospitals, the goal of better allocation of resources and hospital beds and optimal productivity of existing beds can be achieved. According to the findings of this study and by better identifying and managing factors related to length of stay, the length of stay index can be improved and steps can be taken to reduce costs and waste resources.