International Journal of Hospital Research
Volume:12 Issue: 1, Winter 2023

The Intensive Care Unit (ICU) is one of the most stressful places in the hospital; Not only for patients but also for the closest family members of the patient who may experience an emotional crisis. Patients admitted to the intensive care unit experience emotional crises due to the conditions of this ward, the increase of such crises leads to various psychological disorders as well as depression or dementia. Depression and other psychological problems are associated with a variety of other chronic medical conditions and often goes undiagnosed due to the focus of physicians and patients on the underlying disease.

The most common psychological diagnosis among ICU patients is delirium. Numerous factors such as severe depression, postoperative hypoxia, marital status, and the use of opioids and haloperidol have been reported as predictors of delirium. The incidence of delirium in the intensive care unit is not specific to patients with brain injuries or other severe injuries. In cardiovascular patients admitted to the intensive care unit, the prevalence of psychological disorders, including depression, is reported to be about 30%. In this regard, research has shown that depression is very common in patients undergoing treatment for acute coronary syndrome. In addition to the mental disorders caused by admission in the ICU, there are other mental conditions, including post-traumatic stress disorder and preexisting psychiatric disorders, which according to our studies are less prevalent compared to depression and delirium. Early detection and reduction of risk factors affecting delirium requires knowledge and awareness of physicians.

The present study was conducted with the aim of reviewing the prevalence of Psychological disorders in intensive care units

COVID-19, a rapidly spreading virus, has severely challenged all countries worldwide. Various clinical and public health interventions have been in action since its first report in December 2019. This study thus aims to share the lessons learnt and identify the strengths and weaknesses upon the crisis management of Covid_19 in Iran.

This was a qualitative exploratory research including 22 semi-structured, face-to-face, virtual interviews with key informants and decision makers in the management of current epidemic in Tehran University of Medical Sciences since April to December 2020. Data was analyzed using thematic analysis.

There emerged nine themes representing the key pains and gains experienced by the affected health care organizations. They ranged mainly from the multiplicity in the decisions and policies, unfair distribution of resources across the country, resistance to unexpected changes to imbalance in the provision of medical services. As such, the gains mainly included the provision of quarantine facilities outside of hospitals and creating strong advisory team.

The current unprecedented crisis has affected various aspects of human life. Policy makers and managers, especially in health care, worldwide are struggling to abate the consequences of this nasty virus, though facing tough challenges. Some hands-on and real-time experiences from the fight of a developing and highly affected country against this virus is provided which might be of a high value. Whatever approach adopted, it is key to be multifaceted and support all physical, mental and social aspects of health in crises.

In recent years, medicine supply chain management has become more significant, especially after the Covid-19 pandemic. The most important issue is supply chain cost control. Medicine costs include nearly 30% of hospital expenses. If the drug inventory is not properly managed, it will lead to issues such as the lack of inventory of certain drugs, provision of excess inventory, increased costs, and, finally, patient dissatisfaction.

In this study, an attempt has been made to predict and manage the pharmaceutical needs of hospitals using artificial neural networks and deep learning algorithms. The prescription and consumption information of one of the general hospitals in Hamedan city from 2013 until 2017 was extracted from the HIS databases. Since most drugs have different and specific characteristics and it is impossible to create the same prediction model for all drugs, the employed dataset is limited to the category of antibiotics. As a case study, the accuracy of the predictive model is evaluated, especially for cefazolin. We use a deep model to analyze the medical data time series efficiently. This model consists of two parts, a Convolutional Neural Network and a Long Short-Term Memory network (LSTM), which can sufficiently recognize the change history in time series prediction applications. The proposed model with many adjustable parameters in convolutional neural networks will bring good performance to overcome the complexities of the learning problem.

Using deep learning in the training process can increase robustness by reducing the effects of complexity and uncertainty in medical data. Eventually, the prediction evaluation results and analytical criteria such as forecasting error and convergence speed and some statistical tests like R^2, MAE, and RMSE were presented. The average forecasting error for the proposed method is 0.028, and the measured values for RMSE, MAE, and R^2 are 0.095, 0.081, and 0.788, respectively.

A comprehensive comparison between some other predictive methods and the implemented model shows the outperformance of the proposed approach. Additionally, the evaluation results indicate the efficiency of the proposed approach.

Noise is a critical concern for practical machine learning, especially medical applications. There exist two kinds of noise, including attributes and class noises. Class noise is potentially more dangerous, so various filtering techniques, particularly prediction-based, have been proposed to control it. Great attention to class noise has made the researchers ignorant that attribute noise, in turn, is harmful. Hence, it is improper to utilize prediction-based filtering to correct class noise without regarding attribute noise.

To tackle this problem, we developed a method to fix class noise in the presence of attribute noise. This method excludes noisy components of attributes, based on the information bottleneck principle, by compressing attributes locally and gradually in successive iterations. It uses heterogeneous ensemble filtering to correct class noise. In the initial iteration, filtering is conservative and progressively, in succeeding iterations, tends to majority vote.

We compared the proposed method's predictive performance with the RF majority-vote filter on three real binary classification problems from the UCI repository, including Breast, Transfusion, and Ionosphere. Random forest, adaptive boosting, support vector machines, and naïve Bayes were used for assessing methods from different viewpoints. Results show that the proposed method performed better than the RF majority-vote filter and seems to open a promising research scope for noise filtering.

Our study revealed that correcting class noise by controlling attribute noise enhances the predictive performance of classifiers.

Hospitals, as the most critical and costly part of the health system of any country, are required to provide quality and cost-effective diagnostic and treatment services, and optimal resource efficiency and cost management are considered essential elements for achieving these goals. In the meantime, proper expertise in medical supplies purchasing has been considered one of the ways to maintain and improve the quality of services and control costs in hospitals. In this regard, this research aims to identify effective indicators in the expertise of medical supplies purchasing.

This research was of the applied type and was carried out in a descriptive-survey way. To implement, the indicators collected from previous related studies, with the opinion of experts and using the Delphi method, were completed, and the expertise model of medical supplies purchasing was designed and proposed.

Sixteen criteria for medical supplies purchasing in five main categories, "cost", "quality and safety", "compliance with requirements", "delivery conditions" and "supplier records" were identified, categorized, and designed in the form of a conceptual model of purchasing expertise. According to the results, the criteria of "quality", "importer/producer registration in the system of the General Department of Medical Equipment" and "price" were recognized as the most critical indicators in the purchase of medical supplies.

Accurate identification of effective quantitative and qualitative indicators in the purchase of medical supplies and their use in health and treatment centers will lead to the supply of suitable medical supplies and, as a result, provide quality and cost-effective services along with the efficient management of resources and expenses, it will lead to the improvement of the country's health system services and increase in the satisfaction of service recipients.

Hospital management issues have been one of the most important concerns of governments. These challenges involve medical staff and health policymakers more than ever during crises such as the Covid-19 epidemic. Lack of hospital beds and special-care facilities, medical staff shortage, and immediate reduction of drug inventory is among the most important problems in critical situations. Designing technological management solutions and using existing potentials to evaluate the condition of hospitals at the macro level can greatly reduce the incidence of such problems.

In this study, an attempt is made to prevent the aforementioned problems using a technological solution in Hospital Information Systems (HISs), where a directorial analysis in evaluating the facilities and limitations of medical and healthcare centers on the one hand, and the architecture of the Electronic Health Record (EHR), on the other hand, is performed. Launching an online system transferring the live status of beds between the HIS and EHR systems is the first step, and adopting macro-management approaches to use the available treatment capacities for optimal patient coverage is the second step.

This system is launched nationally based on the current platform of Iran's EHR at a low cost. Collecting patient data during the stages of admission, treatment, and discharge, while facilitating the monitoring of the hospital beds, helps to enrich the content of the EHR, as well as the launch of online management-monitoring dashboards.

Patient status monitoring, bed vacancy, and the discharge rate of hospitals could be monitored offline and lately, and we improved it by providing a novel model.