Frontiers in Health Informatics
Volume:4 Issue: 4, 2015

Evaluation of hospital information systems (HIS) are payed attention in different aspects such as educational, clinical, research and financial but among these, financial and economic impact of these systems on healthcare organizations is one of the most important concerns of managers. This study is a systematic review to identify the effect of hospital information systems in decreasing cost and increasing effectiveness according to available evidence in Iran. At the first stage the specific keywords of health information systems were searched in Iranian databases such as Magiran, Iranmedex, SID, Medlib, and Irandoc. Then the studies were found and those related to the topic were selected. At the end, the studies was appraised using Critical Appraisal Skill Program (CASP) checklist. Among 1197 article, 36 article about hospital information systems evaluation were selected. About 50% of these article were conducted by using questionnaire and 30% of them have evaluated hospital information systems by observation, interview or qualitative methods. Although these studies answer whether the systems are or are not cost effectiveness but their answer is based on people’s viewpoint and just two articles found cost and effectiveness of HIS with accountable criteria. After quality assessment, none of articles matched the pattern of economic evaluation. Despite of Persian articles, there is not any good evidence to judge about cost effectiveness of HIS. Although these articles express some hypothesis about cost effectiveness of HIS but it is necessary to prove this claim through exact and scientific ways. because of managers’ need to know about the quality of HISs in organizations and the necessity of using guidelines, perhaps there is a good suggestion that related institutions try to develop guidelines and standards to facilitate these types of studies.

Controlling vital signs is crucial for patients in an intensive care unit (ICU) who need safe diagnostic and therapeutic interventions. The devices used in ICU should ensure accuracy, reliability and safety of alarms. The goal of personalized medicine in the ICU is to predict which diagnostic tests, monitoring interventions and treatments are necessary. In this study, we propose an intelligent approach based on artificial neural networks which is able to automatically learn the features of a patient and consequently send the required alarms in order to reduce the number of wrong alarms in ICU. Six of the most important risk factors are used and the importance of input variables is quantified by weighting according to expert’s knowledge. The data chosen for this study have been provided in a real ICU environment in the University of Queensland in Australia. The results demonstrate that the proposed neural approach can be used as an efficient method for controlling vital signs in a real ICU environment.

The Length of Stay (LOS) is an important indicator that can be useful for financial and management of hospital planning. If identify the patients after admission who will have a long stay at hospital, suitable resources can be available in order to accelerating health care at the primary time. This research is a kind of descriptive retrospective study. The samples are consist of 4120 computerized patients’ medical records (each data had 12 variables) from 2014 February to 2015 March at Sina Hospital and Maternity in Mashhad, Iran. After data cleaning, for determination of correlated ingredients to LOS, we use the single variable analysis consist of Chi-square tests, unilateral variance analysis and so use CHAID Decision Tree algorithm in SPSS software, version 19. The average and median of LOS in the mentioned hospital were 2.3 and 1 day respectively. Between 12 variables that entered to decision Tree, 8 of them recognized as correlated ingredients to LOS. These variables consist of primary diagnosis, age, occupation, attending physician, habitat place, marriage status, previous hospitalization history and clinical insurance. According to clinical and demographic variables at the time of patient admission, could predict patient Length of Stay, however the result of Decision Tree can be different due to entered data. Therefore, in order to create a LOS prediction model, we have to use special hospital data separately from each other in Decision Tree and use the result of them in the same care center.