149 research outputs found
Sort by
STUDY ON FACTORS AFFECTING MORTALITY IN PATIENTS WITH BRAIN TRAUMATIC INJURIES RESULTING FROM TRAFFIC ACCIDENT BY USING DATA MINING
Get PDFIntroduction: One of the most important health problems is road traffic accident. Brain traumatic injury caused by crashes is the first cause of mortality among young people. Capabilities of Data Mining methods to find factor affecting and the prediction therapeutic outcomes leads to the improvement and effectiveness of the services. The aim of this study was to find the Factors affecting mortality in patients with brain traumatic injuries resulting from traffic accident by using the C5.0 decision tree and Bayesian network data mining methods.
Methods: In this cross-sectional study, the population of this study was 106 records of patients with brain traumatic injury caused by traffic accident referred to Khatam-al-Anbia hospital in Zahedan city. Data were collected with a researcher-made checklist that was prepared in consultation with experts in this field and review of previous studies. The validity of this checklist was confirmed by three health information technology experts. Data were analyzed by using two software SPSS MODELER 18.0 and SPSS Statistics 24.
Results: The accuracy of C5.0 decision tree and Bayesian network were 84.9% and 74.5% obtained. The most important variables that affect the death of accidental patients include Type of lesions, the work of the person in an accident (driver, passenger, pedestrian), accident location (inside or outside the city), and age of the patient. According to the result of this study, the type of lesions with the cause of death (p-value=0.024) is statistically significant.
Conclusion: The results of C5.0 decision tree and Bayesian network showed the most important and effective variable is type of lesions. Hence, by predicting the factors affecting in death of brain traumatic patients, healthcare provider with timely action can reduce the death and irreparable of injuries to these patients.
 
INVESTIGATING THE REMOTE MONITORING USAGE FOR HOME HEALTH CARE
Get PDFIntroduction: Managing and monitoring some diseases and disorders are costly and complicated for patients, their families and healthcare systems. Furthermore, many of the pharmaceutical facilities, equipment and disease management programs are not available to all people in the community. Therefore the use of wireless technologies along with the telephone-based transmission systems, can collect the patients’ health status data and share with related providers. Remote monitoring defines a management approach using communication technology to track patients’ health.
Methods: In this study, we searched recent articles indexed in PubMed, Science Direct, Ovid, Web of Science and Google Scholar to investigate articles which aimed to explore the use of remote patient monitoring systems in different clinical status and to review the advantages and disadvantages of these systems.
Results: People with chronic diseases such as heart disease have complicated care needs. If these people would not be exposed to proper interventions, this situation may lead to multiple referral to the emergency departments and even rehospitalization. Home care by using clear communication protocols, can have a significant impact on improving the quality of care and safety of patients after discharging from the hospital. In such chronic diseases, remote monitoring fascilities and interventions along with education can reduce the use of healthcare resources and the need for early re-admission. Remote monitoring can also support people with disturbances of consciousness. In the field of drug prescription, this technology can also offer recommendations for regulation and alteration of last prescribed drugs in addition to suggestions on patient behavioural changes by care providers and predefined algorithms. This technological method can also be used to monitor side effects of some medications such as antihypertensive drugs.
Conclusion: Monitoring patients remotely, is most commonly used in heart diseases, pulmonary diseases, diabetes and blood pressure diseases. Studies have also been conducted in areas such as serving the elderly and drug counseling. Although there are contradictions about the impact and effectiveness of this approach on some diseases, for patients who are hospitalized frequently, a daily program for monitoring them remotely can have an impact on optimizing health care resource utilization and reduce the number of admissions and length of stay in the hospital and ultimately improve the quality of life of the individual
AWARENESS OF PATIENTS’ BILLS OF RIGHTS AMONG MEDICAL STAFF IN MASHHAD MEDICAL UNIVERSITY` TEACHING HOSPITALS
Get PDFIntroduction: Respecting patients’ rights practice and keeping patient satisfied is one of most important principles in ethical medicine. Increasing Awareness and respecting patients’ rights result in better health care considering human and ethical rights. The Ministry of Health and Medical Education in Iran published a patients’ bill of rights and mandated it be posted conspicuously for the patients. With regard to necessity of Patients’ bill of rights, patients’ role in decision making and respecting their right, this study aimed to investigate awareness of patients’ bills of rights among medical staff in Mashhad medical university` teaching hospitals
Methods: The current analytical cross- sectional study was conducted on 129 medical staff in the year 2014-15 in Mashhad medical university` teaching hospitals. The data were collected using a self-administer questionnaire with 28 questions whose reliability was 80 according to Cronbach\u27s alpha. One-way analysis of variance, Student\u27s t-distribution was used to compare means of Awareness via SPSS Ver. 21.
Results: The results indicated that awareness of medical staff was M=65/3, SD=67/0. Nursing staff were the most aware and radiology staff were the less aware from patients’ bills of rights.
Conclusion: Today, observing patients \u27rights is one of the most important issues that should be placed at the top of the attention of health care programs, observance of patients’ bills of rights make people feel satisfied with respect for them at health care centers . So it is neceesery to inform patient and professional on patients’ bills of rights by publishing more attention to patients’ bills of rights result on better health car
Systematic extraction of diagnostic data items for common high-risk pregnancies using Delphi technique
Get PDFIntroduction
The quality of clinical decisions being made every day by on-call physicians are totally based on the quality of medical information they receive during telephone consultations with residents. Some basic factors such as the right selection of medical items, type and format, and also the volume of such information may highly affect the quality of remote consultations. Therefore, developing a trusted standard model for such clinical communication seems vital. In this research, we used Delphi technique to develop a set of information items in form of clinical decision archetypes to standardize teleconsultation in high-risk pregnancies.
Methods
A multi-stage cross-sectional study was conducted to exploit the diagnostic items for the most common high-risk pregnancies in three obstetrics and gynecology department of educational hospitals, Mashhad, Iran.
Results
Our study revealed eclampsia/preeclampsia, hemorrhage, PROM, pre-term and post-term delivery as the most common high-risk pregnancies in the hospitals being studied. 189 clinically-important items were extracted from scientific references and then hand-filtered to 128 items by the participating gynecology and obstetrics experts. The final items were categorized into five classes including general information, chief complaint / current problem, medical history, clinical examination, and paraclinic tests.
Conclusion
In this study, a set of clinical decision archetype was developed to improve the decisions being made in high risk pregnancies
CREATING A SEMI-SUPERVISED DATA MINING MODEL FOR PREDICTING BREAST CANCER RELAPSE
Get PDFIntroduction: Breast cancer is one of the most common types of cancer and malignancy in Iranian women,that recently has been a growing increase. there is always a possibility of recurrence In persons afflicted by thisdisease.In regarding to the complexity of analysis, data mining is among the best solutions that is used to detect or predict cancers.
Methods: In this retrospective study, data of 809 patients with breast cancer from center of breast cancer research of Tehran’s Academic Center for Education, Culture and Research (ACECR) and 26 features from each patients were used. In regarding to high number of missing data in this collection, only information of 655 patients and 14 features of each patient were usable. Many features in records have null values, thus as one of data pre-processing and preparing phases, via Auto-Clustering algorithm, the data was divided into 10 clusters and according to dominant values in each cluster for each feature, these null features has been valuing. Data was divided to recurrence and non- recurrence classes. Semi-supervised method has been used in this study. the modeling was performed using labeled data and then a hybrid model for giving label to nonlabled data has been created. For this, data with recurrence lable divided proportional 30 percent for testing and 70 percent for training,and got to decision tree algorithms C5.0, Chaid, Quest, CRT, Autoclassifier as inputs. Then, the model was formed by mixing classifier algorithms with Confidence-Weighting-Voting method for predicting cancer recurrence, and used K-Fold (K=10) method for evaluating created model.
Results: The sensitivity of developed hybrid model was 82.93% and its specificity was 93.93%. The precision value of the model is 89.47% and its accuracy is 89.72%. this model mistakenly labelled only 10% of recurrence in patients of breast cancer as non-recurrence.
Conclusion: Creating predictive models with an appropriate sensitivity and specificity isimportant since, if the possibility of recurrence is high, could perform special preventive proceedings before its spreading. The false negative percentage is also important in medical prediction models, as it can have very dangerous consequences. In the prediction model presented in this study, the value of this parameter was 10%, and in this regard, this model can be considered acceptabl
Liver Lesions Detection and Classification in Ultrasound Images Using Gabor Characterization, Edge Detection and Artificial Neural Networks
Get PDFIntroduction: In the last decade one of the main reasons for people mortality and disability is liver diseases. Early detection of these diseases can help adopt appropriate treatment methods. Ultrasound imaging is a non-invasive method for visualizing tissue specification and liver lesions detection which its resolution is lower than CT and MRI images. Precise determination of liver tissue lesions and progression degree of disease is possible with advanced computer techniques such as artificial neural networks (ANN) from medical images. In this paper, a classification-based method is presented to identify and diagnose liver lesions using the Gabor wavelet features and edge detection. In this method, the vector of features from healthy and damaged tissues is trained to the network based on Gabor filters. Then the suspected cases of tissue lesions in various liver diseases are identified by features extraction of entry images. After that, the edge detection technique is implemented and the internal points of the edge are tested as an inputs of a neural network which determine the healthy and unhealthy liver tissues.
Methods: Image features are extracted and processed by Gabor wavelet. Also the ANN is used to liver disease classification based on the images features. The forward multilayer perceptron neural network is organized with three layers of input, hidden and output. The training of this network is done with back propagation method and all of the data include "healthy tissues" and "damaged tissues" of the liver are collected in a large cellular array. Furthermore, an edge detection technique is used to indicate the points where the intensity of the light changes sharply. The sharp changes in image characteristics are usually representative of important events and changes in environments characteristics.
Results: The results of the implementation indicate a significant reduction in processing time of liver ultrasound images and also increase the precision and accuracy of liver lesions detection (approximately 5%) among different classified groups of hepatic patients compared with the similar image processing methods. In the proposed method, the total time of operations include feature extraction, image processing, lesions detection and diagnosis of the disease has been decreased by reduction of the number of examined points. In addition, an edge detection technique had been used to diagnose the size of damaged tissues in various liver diseases, which helps improve the early detection of tissue lesions because of reduction of the checking domain of points.
Conclusion: In this paper, a new method was presented to identify liver tissue lesions. Gabor wavelet method is employed to extract the features of the liver ultrasound images. These wavelets provide the context to understand the images frequency and their analysis in the area of the space, and given their great advantage, which is slow changes in the frequency domain, it is an appropriate filter to extract the image features. Then, the extracted features of the ultrasound images of various liver patients are stored to train a neural network, and finally the image processing method is performed to identify the healthy and damaged tissues and also to diagnose the type of disease. The search scope of problem is minimized as the input of the neural network to find the liver damaged tissue by the edge detection technique which is lead to errors reduction in identifying the tissue damages, increasing the detection speed of these lesions, and diagnosing the disease as well as determining the damage degree of liver.
 
QUANTITATIVE EVALUATION OF MEDICAL RECORD DOCUMENTATION IN IMAM REZA HOSPITAL, MASHHAD, IRAN
Get PDFIntroduction:
Diabetes is the most common endocrine disease. Given the importance of medical record documentation for diabetic patients and its significant impact on accurate treatment process, as well as early diagnosis and treatment of acute and chronic complications, this study aimed to qualitatively evaluate medical record documentation of diabetic patients.
Methods:
This descriptive and cross-sectional study was conducted on all medical records of diabetic patients (1200 cases) in the comprehensive Diabetes Center of Imam Reza Hospital. A checklist was prepared according to the main sectors and their sub-data elements to conduct a qualitative evaluation on documentation of medical records of diabetic patients. Descriptive statistics were used to report the results.
Results:
In this study, 1200 (710 women and 490 men) cases were evaluated. Mean documentation of main sectors of diabetic patients’ records were as follows: 49% demographic characteristics, 14% patient referral, 4% diagnosis, 50% lab tests, 25% diabetes medications,13% nephropathy screening test, 10% diabetic neuropathy, 41% specialty and subspecialty consultations and internal medicine physicians visits did not complete for all the patients.
Conclusion:
According to the results of this study, qualitative evaluation of medical record documentation of diabetic patients Showed poor documentation in this regard. It is suggested that results of this study be accessible to physicians of healthcare centers to take a positive step toward improved documentation of medical records. In addition, it seems necessary to modify diabetic medical records
Redox status in benign prostatic hyperplasia and non-metastatic prostate cancer in the Algerian population
Get PDFBackground: Depletion of cellular antioxidants can result from free radical formation due to normal endogenous reactions and the ingestion of exogenous substances and environmental factors. The levels of reactive oxygen species (ROS) have been shown to be significantly altered in malignant cells and in primary cancer tissues. We undertook the present study to investigate the possible alteration of oxidant/antioxidant status in Algerian patients with benign prostatic hyperplasia (BPH) and prostate cancer (PCa).
Methods: In total, 89 subjects made up of 26 patients with non-metastatic prostate cancer, 31 with benign prostatic hyperplasia (BPH), and 32 controls participated in this study. The concentrations of plasmatic malondialdehyde (MDA), erythrocytes catalase activity (CAT), and the plasma glutathione levels (GSH) were estimated using standard procedures.
Results: The results showed that MDA concentrations were significantly increased while erythrocyte catalase activity was significantly decreased in the prostate cancer group versus controls (P < 0.01) and BPH group (P < 0.05). GSH levels were lowered in prostate cancer patients versus control group with no significant changes.
Conclusions: Our results suggest that an alteration in the lipid peroxidation index with concomitant changes in the antioxidant defense system in prostate cancer patients compared with controls. We hypothesize that an altered pro-oxidant–antioxidant balance may lead to an increase in oxidative damage and consequently may play an important role in prostate carcinogenesis
Multicriteria decision making with ELECTRE III, SOLAP and GIS for spatiotemporal tuberculosis analytics
Get PDFBackground: Epidemic spread is a major public health problem. Rapid detection of the agent, identification of factors promoting spread of epidemic and effective treatment are important parameters in controlling the disease.
The purpose of this research is to develop a novel epidemiological surveillance system based on Multi Criteria Analysis Method (MCAM) and Geographical Information System (GIS) technology integrated into a decision support system called SYstème Décisionnel Spatiotemporel pour l’EPidémiologie (SYDSEP). The later was designed, implemented and validated in previous research for tuberculosis risk assessment.
Methods: We highlight the use of ELimination and Choice Expressing REality III (ELECTRE III) ranking method of MCAM in GIS that incorporate environment, socio-economic, medical factors to monitor and identify potential high-risk areas of tuberculosis and disease mapping. Factors related to the risk of tuberculosis are obtained from SYDSEP and constitute the input values of ELECTRE III ranking method for the 26 communes of the city of Oran (Algeria).
Results: The outcomes from the combination of GIS and ELECTRE III produced useful information on different levels of risks. Thematic maps on incidence numbers of disease are created to classify the TB incidences from the highest level to the lowest level. Thus, we can easily obtain the major factors that influence the spread of disease and lead to increasing numbers of confirmed cases.
Conclusion: GIS based ELECTRE III method within SYDSEP has demonstrated analytical capabilities in targeting high-risk spots and TB surveillance monitoring system of the city of Oran and it can help public health policy makers prioritizing their response goals and evaluating control strategies
Multimodality molecular imaging: Paving the way for personalized medicine
Get PDFEarly diagnosis and therapy increasingly operate at the cellular, molecular or even at the genetic level. As diagnostic techniques transition from the systems to the molecular level, the role of multimodality molecular imaging becomes increasingly important. Positron emission tomography (PET), x-ray CT and MRI are powerful techniques for in vivo imaging. The inability of PET to provide anatomical information is a major limitation of standalone PET systems. Combining PET and CT proved to be clinically relevant and successfully reduced this limitation by providing the anatomical information required for localization of metabolic abnormalities. However, this technology still lacks the excellent soft-tissue contrast provided by MRI. Standalone MRI systems reveal structure and function, but cannot provide insight into the physiology and/or the pathology at the molecular level. The combination of PET and MRI, enabling truly simultaneous acquisition, bridges the gap between molecular and systems diagnosis. MRI and PET offer richly complementary functionality and sensitivity; fusion into a combined system offering simultaneous acquisition will capitalize the strengths of each, providing a hybrid technology that is greatly superior to the sum of its parts.
This talk also reflects the tremendous increase in interest in quantitative molecular imaging using PET as both clinical and research imaging modality in the past decade. It offers a brief overview of the entire range of quantitative PET imaging from basic principles to various steps required for obtaining quantitatively accurate data from dedicated standalone PET and combined PET/CT and PET/MR systems including algorithms used to correct for physical degrading factors and to quantify tracer uptake and volume for radiation therapy treatment planning. Future opportunities and the challenges facing the adoption of multimodality imaging technologies and their role in biomedical research will also be addressed