aa azizi

Gestational diabetes is associated with many short-term and long-term complications in mothers and newborns; hence, the detection of its risk factors can contribute to the timely diagnosis and prevention of relevant complications. The present study aimed to design and compare Gestational diabetes mellitus (GDM) prediction models using artificial intelligence algorithms.

In this study, Decision Tree and Artificial Neural Network algorithms were used to predict GDM. The research population encompassed 1270 pregnant women referred for primary care at urban healthcare centers in Ahvaz, of whom 816 persons were healthy, and 454 individuals were diagnosed with GDM. To evaluate the effectiveness of the GDM prediction models, their sensitivity, specificity, precision, and accuracy were calculated and compared. Finally, the AdaBoost classification algorithm was used to boost the two proposed models.

Following the Principal Component Analysis (PCA), nine cases were selected for primary modeling. In the Artificial Neural Network model, the area under the ROC curve and sensitivity were 83.2 and 85.1%, respectively, and the area under the ROC curve and sensitivity for the Decision Tree model were 0.826 and 84%, respectively. After removing variables with lower weights and reinforcing the proposed model, the level under the rock curve and sensitivity increased by 0.861 and 92.1%, respectively. In this regard, fasting blood sugar at the first pregnancy visit, history of gestational diabetes in previous pregnancies, body mass index, mothers’ age, and family history of diabetes had the highest accuracy in predicting GDM.

The findings of this study indicate that artificial intelligence algorithms are accurate and effective for the early prediction of gestational diabetes.

Using data mining to develop prediction models from large amounts of data in medicine has become increasingly popular during the recent years. In this study، we intend to use a decision tree data mining algorithm in order to identify factors influencing mortality in burn patients.

The present retrospective descriptive study is based on burning patients’ records. Overall، the medical records of 4804 patients were scrutinized. The collected data were analyzed using statistical software (SPSS version 16)، data mining software (Clementine version 12)، and CHAID algorithm.

The resulting model for predicting survival and mortality of burning patients included the percentage of Total Burn Surface Area (TBSA %)، degree of burn، length of stay، gender، and age of patients. Other variables including blood cultures، wound cultures، urine cultures، and the months of patient hospitalization had no effect on improving the efficiency of the model.

The proposed model is valid and reliable due to its accuracy (approximately 95%). In fact، the results of this study، some of which are consistent with the results of other studies، can propose a comprehensive، accurate، and reliable local model for predicting mortality and survival of burning patients based on the mentioned variables. Thus، this local model can be used as an important criterion for evaluating the effective treatment of burn patients.

Owing to t he critical importance of emergency department activities in saving lives، information systems of this department should be free of fault to prevent the incidence of errors. Usability evaluation methods are used to assess this quality measure. Heuristic evaluation is one of the methods which identifies usability problems with minimum amount of time، cost and resources. The objective of this research was to evaluate the usability of emergency department admission subsystem of health information systems in Mashhad University of Medical Sciences. Using Nielsen’s 10 usability principles، three trained evaluators، independent of each other، evaluated the corresponding subsystem and determined the severity of identified problems. All the problems، identified by independent evaluators، were collected in a single list and the mean severity of each problem was calculated. A total of 163 usability problems were identified. The lowest mismatch with usability principles was related to “error prevention” (3 %) and the highest was related to “consistency and standards” (27 %). The average severity of problems varied from 2. 3 (minor problem) concerning “system''s visibility” to 2. 9 (major problem) concerning “help users recognize، diagnose، and recover from errors”. Heuristic Evaluation can be used to identify a high number of usability problems related to health information applications in health care systems. If remain unsolved، these problems may waste users’ and patients’ time، increase errors، reduce data quality، and in general، threaten patient’s safety.

Evaluation of medical records departments in hospitals of Iran shows that these departments have not achieved desirable standards and high quality services. The major aim of this survey is to evaluate the performance of the Medical Records Departments of hospitals of Ahvaz for awareness of their status. This is an applied research, conducted in descriptive cross-sectional. Research population includes medical records departments of hospitals Imam Khomeini, Golestan, Razi, Aboozar, Shafa, Taleghani, Salamat and Sina. In this study the required data has been collected by the use of a questionnaire and four types of check-lists in each of Admission, Filing, Coding and statistics units. To analyze of data, each four checklists of units was assigned 100 score and then the performance average of each unit was calculated and compared. The best performance was for statistics units (71.97%) and lowest it was for coding units (56.79%) Functional status standards were partially observed. Auditing results show that the functional status in medical records departments of university hospitals in Ahvaz lack standard instructions that should be followed on all the functional processes and require appropriate attention by trustees of these hospitals.