جستجوی مقالات مرتبط با کلیدواژه « clinical decision support system » در نشریات گروه « پزشکی »

With the change in the epidemiology of diseases, chronic kidney disease has shown a significant increase worldwide. Kidney transplantation is the optimal treatment option to improve patient quality of life. The main challenge in benefiting from a brain-dead patient's kidney is the selection of a right recipient in limited time. The purpose of this study was to review the requirements for designing and implementing clinical decision support systems for allocating brain-dead kidneys and the challenges facing them.

This scoping review was conducted by searching Scopus, PubMed, and Google scholar to find full-text English articles published until the end of 2021. The articles were analyzed based on the objectives of the study, the factors used in decision-making for allocation, the algorithms used in the decision-making process, and their outcome evaluations.

Two categories of medical (including the quality of the donated kidney) and equity/fairness factors were used in most allocation algorithms. However, the number of factors, the method, and the order of their application were different in different studies. Studies have reported different challenges but a positive impact using decision support systems.

One of the main challenges in the proper management of kidney transplants from brain-dead donors is to have local, agreed-upon protocols and algorithms regarding the methods, order, and weight of each of the medical and equity factors in the proposed protocol. Algorithms based on scoring have mostly been favored. Therefore, the probability of using a decision support system on this base seems to be higher.

Identifying risk factors is recommended as the first step for depression management in children and adolescents. This study aims to determine the data elements required for developing a clinical decision support system for screening major depression in young people.

This research was a descriptive-analytical study. The research population included a variety of mental health specialists that were both psychologists and students in psychiatry and guidance & counseling majors as well as electronic databases including Scopus, Pubmed, Embase, PsychInfo, WOS and Clinical key. The data collection tool was a questionnaire designed in three main sections which was answered by a convenient sample of 8 people who were specialists in the field. To analyze the extracted data Content Validity Ratio (CVR) and Mean measures were calculated for each item in questionnaire. Content Validity Index (CVI) and Cronbach’s Alpha (using SPSS software) were calculated which were equal to 0.74 and 0.824 respectively which confirmed validity and reliability of the research tool. 

 According to Lawshe’s table, data elements with CVR between 0 and 0.75 and Mean less than 1.5, like “Ethnicity and race” (CVR=-0.25, Mean=1.125), were rejected. Items such as “Gender” (CVR=0.5) with a CVR equal to or less than 0.75, as well as items with a CVR between 0 and 0.75 and a Mean equal to or more than 1.5, like “Marital status” (CVR=0.5, Mean=1.625) were retained and considered to be included as the minimum data set for screening major depression in ages 10 to 25 years. Data elements were categorized in three categories: Demographic, Clinical and Psychosocial

Clinical decision support systems can facilitate providing healthcare at different levels such as screening major depression. These systems can be used for screening major depression risk factors to improve accessibility to mental health practitioners, assure the implementation of guidelines and provide a common language between different levels of healthcare. Determining the minimum data set for screening major depression in ages 10 to 25 years, is the first step toward developing a clinical decision support system for screening individuals for major depression.

Breast cancer is one of the most common and aggressive malignancies in women. Timely diagnosis of breast cancer plays an important role in preventing the progression of this disease, timely treatment measures, and aftermath reducing the mortality rate of these patients. Machine learning has the potential ability to diagnose diseases quickly and cost-effectively. This study aims to design a CDSS based on the rules extracted from the decision tree algorithm with the best performance to diagnose breast cancer in a timely and effective manner.

The data of 597 suspected people with breast cancer (255 patients and 342 healthy people) were retrospectively extracted from the electronic database of Ayatollah Taleghani Hospital in Abadan city with 24 characteristics, mainly pertained to lifestyle and medical histories. After selecting the most important variables by using the Chi-square Pearson and one-way analysis of variance (P<0.05), the performance of selected data mining algorithms including RF, J-48, DS, RT and XG -Boost was evaluated for breast cancer diagnosis in Weka 3.4 software. Finally, the breast cancer diagnostic system was designed based on the best model and through C# programming language and Dot Net Framework V3.5.4.

Fourteen variables including personal history of breast cancer, breast sampling, and chest X-ray, high blood pressure, increased LDL blood cholesterol, presence of mass in upper inner quadrant of the breast, hormone therapy with estrogen, hormone therapy with Estrogen-progesterone, family history of breast cancer, age, history of other cancers, waist-to-hip ratio and fruit and vegetable consumption showed a significant relationship with the output class at the P<0.05. Based on the results of the performance evaluation of selected algorithms, the RF model with sensitivity, specificity, accuracy, and F- measure equal to 0.97, 0.99, 0.98, 0.974, respectively, AUC=0.936 had higher performance than other selected algorithms and was suggested as the best model for breast cancer diagnosis.

It seems that using modifiable variables such as lifestyle and reproductive-hormonal characteristics as input to the RF algorithm to design the CDSS, can detect breast cancer cases with optimal accuracy. In addition, the proposed system can be effectively adapted in real clinical environments for quick and effective disease diagnosis.

Asthma is uncontrolled in more than half of asthma patients due to inadequate and incorrect management. The main reasons for inadequate management are non-adherence, inadequate knowledge of a general practitioner about patientchr('39')s clinical condition, and not following asthma management guidelines The purpose of this study was to develop a conceptual model for the asthma management system in primary care

In this study, according to the guideline of the Global Initiative for Asthma, workflows for the management of asthma were extracted. Then, the conceptual model of the system was developed with unified modeling language and evaluated by an expert panel, including five asthma and allergy specialists, three informatics specialists and two health information management experts who were selected through non-probability sampling method. Data collection tools were the discussion framework with open-ended questions that reached a collective agreement after discussion on the conceptual model. The collective agreements were applied simultaneously to the diagrams of the conceptual model.

The conceptual model was developed and evaluated in 10 diagrams, including business use-case, use-case, activities, sequences and class diagrams. The diagrams were reported after evaluation. The business use-case shows the main use-case, and the use-case diagrams show the more detailed use-case which is used for the system. The activity diagram shows how the patient was admitted, visited, and managed. The sequence diagram and the class diagram also present the order of asthma management operation, the objects required by the asthma management, and how they are related, respectively.

Given the validity of the conceptual model by asthma and allergy specialists together with informatics and health information management, it can be expected that the current conceptual model will significantly help to design and implement efficient systems that meet the needs of users.

Drug-drug interactions (DDIs) are a common source of preventable medical errors in inpatient and outpatient settings of both developed and developing countries. When two or more drugs are simultaneously prescribed, interactions between their effects may result in preventable adverse events such as damages to vital organs, frequent hospitalizations, prolonged length of hospital stay, and increased care cost for both patients and healthcare systems. Clinical decision support systems (CDSSs) have a great potential to support care providers to identify and manage DDIs timely, and thereby, to improve the quality of decisions on medication prescriptions. In this opinion paper, we provide a concise review of efforts necessary for a successful design and development of a DDI-CDSS with particular focus on the Iranian healthcare context. We also touch upon the measures to consider in order to overcome some of the important challenges and barriers jeopardizing the design and application of DDI-CDSSs in Iran.

Contact lenses are transparent, thin plastic disks that cover the surface of the cornea. Appropriate lens prescription should be performed properly by an expert to provide better visual acuity and reduce side effects. The lens administration is a multi-stage, complex and time-consuming process involving many considerations. The purpose of this study was to develop a decision support system in the field of contact lens prescription. In this fundamental study, data were collected from 127 keratoconus patients referred to the contact lens clinic at Farabi Eye Hospital, Tehran, Iran during the period of March 2013 to July 2014. Five parameters in the contact lens prescribing process were investigated. Parameters were collected as follows. “Lens vertical position”, “vertical movement of the lens during blinking” and “width of the rim” in the fluorescein pattern were obtained by recording videos of the patients while wearing the lens. “Fluorescein dye concentration” under the lens was evaluated by the physician and “patient comfort” was obtained by asking the patient to fill a simple scoring system. Approved and disapproved lenses were judged and recorded based on the decision of an expert contact lens practitioner. The decision support system was designed using artificial neural networks with the mentioned variables as inputs. Approved and disapproved lenses are considered as system outputs. Artificial neural network was developed using MATLAB® software, version 8.3 (Mathworks Inc., Natick, MA, USA). Eighty percent of the data was used to train the support vector machine and the rest of the data (20%) to test the system's performance. Accuracy, sensitivity and specificity, calculated using the confusion matrix, were 91.3%, 89.8% and 92.6% respectively. The results indicate that the designed decision support system could assist contact lens prescription with high precision. According to the results, we conclude that hard contact lens fitness could be evaluated properly using an artificial neural network as a decision support system. The proposed system detected approved and disapproved contact lenses with high accuracy.

Clinical decision support systems are increasingly administered as a modern method to improve the quality of clinical therapeutic services delivered to patients.
To answer the following questions: 1. What are the widespread applications of clinical decision support systems in the field of nursing? 2. What are the most important barriers to clinical decision support systems in nursing? 3. What are the best strategies to reduce, remove, or overcome the barriers to clinical decision support systems in nursing?
In this systematic review study, English-language databases, including Science Direct, PubMed, Cochrane, and CINAHL, as well as a Persian-language database (the Scientific Information Database) were searched in three steps. Articles published during 2008 to the beginning of 2015 were searched for “clinical decision support system” (both in English and Persian) as the keyword. The keyword was selected from the Medical Subject Headings (MeSH) terms. The articles were selected based on three inclusion criteria, i.e. publication data after 2008, being in either Persian or English, publication in domestic or international scientific and research journals and accessibility of full texts or abstracts.
From the 1034 searched articles in the first phase, 337 articles were selected for the second phase. However, only 11 articles which were deeply related to the field of nursing were finally investigated. Using the given answers to the study questions, socio-technical factors were declared as the major theme. It was concluded that the expansion of clinical decision support systems in nursing required focus on three factors including communication between clinical information systems, clinical decision support systems, clients, and system errors, nurse's perspectives, and organizational changes.
Clinical decision support systems in nursing are still in their early stages of development. Since the progress of these systems in nursing has been significantly slower than that in other fields of medicine, innovative strategies are necessary to increase their application.

This was a descriptive study. The study was conducted in three teaching hospitals in Kerman, Iran in 2013. All physicians were invited to participated in the study. Data was collected using a questionnaire consisting of three parts: the description of CPOE, respondents’ demographics and questions about the study objectives. Data was described by median and quartiles and was analyzed using nonparametric methods.

In all 633 physicians were studied. Fifty-seven percent of physicians agreed with CPOE ease of use, 45% with CPOE usefulness and 32% with its positive effect on clinicians’ workflow. There were significant relationships between system ease of use and usefulness with physician’s age and gender.

The results showed that physicians would accept CPOE system to a good extent, if it were implemented. Younger doctors have a greater readiness to accept the system.

Warfarin is the most common oral anticoagulant. This drug is used for the prevention and treatment of thromboembolic patients. It is difficult for physician to predict the results of warfarin prescriptions because there is narrow boundary between therapeutic range and complications of warfarin. Therefore drug dose adjustment is normally performed by an expert physician. Decision support systems that use extracted knowledge from experts in the field of drug dose adjustment would be useful in reducing medical errors, especially in the clinics with limited access to experts. The aim of this study was to propose a method for boosting the maintenance dose of warfarin for a maximum period of three days to eliminate disruptions in International Normalized Ratio (INR). In a retrospective study, from December 2013 to February 2014 in Shahid Rajaee Heart Center, Tehran, Iran, 84 patients with International Normalized Ratio below (INR) the therapeutic range was selected who was undergone a boosting dose during three days. Patients with unstable maintenance dose were excluded from the study. In this study, data from 75 patients receiving warfarin therapy were used for developing and evaluation of the proposed model. The INR target range for 37 patients out of remaining 75 cases was between 2.5 and 3.5, while for 38 patients the intended INR range was between 2 and 3. A separate fuzzy model was designed for each of the above-mentioned therapeutic ranges. The recommended dose for 37 patients having INR therapeutic range of 2.5 to 3.5 has mean absolute error and root mean squared error of 1.89 and 2.78 respectively for three days. These error rates are 1.97 and 2.88 respectively for 38 patients who are in therapeutic range 2 to 3. The results are promising and encourage one to consider this system for more study with the aim of possible use as a decision support system in the future.

This research aims to design and implement a software with the ability to identify patients who are facing the risk of pulmonary embolism and deep venous thrombosis instantly as well as the ability to send timely reminders for any prophylactic action. The main target is introduce a clinical decision- support system which could finally lead to preventing mortality and handicap cases caused by embolism and thromboses in patients who are confined to bed in hospitals.

The software was designed using the Visual Basic. Net and SQL Server database. Afterwards the software was installed in the largest educational hospital of Kerman and a survey was conducted amongst the physicians using multiple questionnaires and interviews. Finally، the data were analyzed using the SPSS software.

The average score was 21. 16 for the physicians and 20. 76 for the nurses. T-Test results show that there is no significant difference between the total average score of the physicians and that of the nurses.

The results have shown that both groups (physicians and nurses) have a positive viewpoint about the software therefore using the clinical decision support system can be effective in reducing the occurrence of pulmonary embolism and deep venous thrombosis through sending timely electronic alerts to the medical staff.

Decision making and diagnosis of certain diseases can be a challenge for physicians. Neural networks have been used as clinical decision support systems. These networks are powerful algorithms which are capable of learning complex patterns and maintaining their accuracy even in cases when some data is missing. Congestive heart failure (CHF) and chronic obstructive pulmonary disease (COPD) have many similar symptoms which can make their distinction difficult especially at the time of admission or where the access to echocardiography is limited. The multilayer perceptron (MLP) and radial basis function (RBF) neural networks were used to differentiate between congestive heart failure and chronic obstructive pulmonary disorderpatients (n=266) using 43 clinical variables which were normalized following consultations with cardiologists. Bayesian regularization was used to improve the generalization of the MLP network. To design the RBF network, K-Means clustering was used to select the centers of radial basis functions, k-nearest neighborhood to define the spread and forward selection to select the optimum number of radial basis functions. A ten-fold cross validation was used to assess the generalization procedure. The MLP led to a sensitivity of 88.3 %, specificity of 83.7 % and an area under receiver operating characteristic curve (AUC) of 91.9±1.7 while RBF network resulted in 79.6 % sensitivity, 93 % specificity and AUC of 92.7±1.7.Discussion and Neural networks have been developed as a diagnostic algorithm in many clinical decision support systems and this study like many others confirms their ability to perform well in diagnosing certain diseases such as differentiating between COPD and CHF.