An Intelligent Rule-based System for Status Epilepticus Prognostication.

BACKGROUND: Status epilepticus is one of the most common emergency neurological conditions with high morbidity and mortality. OBJECTIVE: The aim of this study is to propose an intelligent approach to determine prognosis and the most common causes and outcomes based on clinical symptoms. MATERIAL AND METHODS: In this descriptive-analytic study, a perceptron artificial neural network was used to predict the outcome of patients with status epilepticus on discharge. But this method, which is understandable, is known as black boxes. Therefore, some rules were extracted from it in this study. The case study of this paper is data of Nemazee hospital patients. RESULTS: The proposed model was prognosticated with 70% accuracy, while Bayesian network and Random Forest approaches have 51% and 46% accuracy. According to the results, recovery and mortality groups had often used phenytoin and anesthetic drugs as seizure controlling drug, respectively. Moreover, drug withdrawal and cerebral infarction were known as the most common etiology for recovery and mortality groups, respectively and there was a relationship between age and outcome, like in previous studies. CONCLUSION: To identify some factors affecting the outcome such as withdrawal, their effects either can be avoided or can use sensitive treatment for patients with poor prognosis.

The Benefits of Decision Tree to Predict Survival in Patients with Glioblastoma Multiforme with the Use of Clinical and Imaging Features.

BACKGROUND: Machine learning is a type of artificial intelligence which aims to improve machine with the ability of extracting knowledge from the environment. Glioblastoma multiforme (GBM) is one of the most common and aggressive primary malignant brain tumors in adults. Due to a low rate of survival in patients with these tumors, machine learning can help physicians for better decision-making. The aim of this paper is to develop a machine learning model for predicting the survival rate of patients with GBM based on clinical features and magnetic resonance imaging (MRI). MATERIALS AND METHODS: The present investigation is an observational study conducted to predict the survival rate in patients with GBM in 12 months. Fifty-five patients who were registered in five Iranian Hospitals (Tehran) during 2012-2014 were selected in this study. RESULTS: This study used Cox and C5.0 decision tree models based on clinical features and combined them with MRI. Accuracy, sensitivity, and specification parameters used to evaluate the models. The result of Cox and C5.0 for clinical feature was <32.73%, 22.5%, 45.83%>, <72.73%, 67.74%, 79.19%>, respectively; also, the result of Cox and C5.0 for both features was <60%, 48.58%, 75%>, <90.91%, 96.77%, 88.33%>, respectively. CONCLUSION: Using C5.0 decision tree model in both survival models including clinical features, both the imaging features and the clinical features as the covariates, shows additional predictive values and better results. The tumor width and Karnofsky performance status scores were determined as the most important parameters in the survival prediction of these types of patients.

Predicting Implantation Outcome of In Vitro Fertilization and Intracytoplasmic Sperm Injection Using Data Mining Techniques.

BACKGROUND: In vitro fertilization (IVF) and intracytoplasmic sperm injection (ICSI) are two important subsets of the assisted reproductive techniques, used for the treatment of infertility. Predicting implantation outcome of IVF/ICSI or the chance of pregnancy is essential for infertile couples, since these treatments are complex and expensive with a low probability of conception. MATERIALS AND METHODS: In this cross-sectional study, the data of 486 patients were collected using census method. The IVF/ICSI dataset contains 29 variables along with an identifier for each patient that is either negative or positive. Mean accuracy and mean area under the receiver operating characteristic (ROC) curve are calculated for the classifiers. Sensitivity, specificity, positive and negative predictive values, and likelihood ratios of classifiers are employed as indicators of performance. The state-of-art classifiers which are candidates for this study include support vector machines, recursive partitioning (RPART), random forest (RF), adaptive boosting, and one-nearest neighbor. RESULTS: RF and RPART outperform the other comparable methods. The results revealed the areas under the ROC curve (AUC) as 84.23 and 82.05%, respectively. The importance of IVF/ICSI features was extracted from the output of RPART. Our findings demonstrate that the probability of pregnancy is low for women aged above 38. CONCLUSION: Classifiers RF and RPART are better at predicting IVF/ICSI cases compared to other decision makers that were tested in our study. Elicited decision rules of RPART determine useful predictive features of IVF/ICSI. Out of 20 factors, the age of woman, number of developed embryos, and serum estradiol level on the day of human chorionic gonadotropin administration are the three best features for such prediction.

Structural investigation of websites of selected educational hospitals of Shiraz University of Medical Sciences from Patient Relationship Management (PRM) perspective.

BACKGROUND: Hospital websites are considered as an appropriate system for exchanging information and establishing communication between patients, hospitals, and medical staff. Website character, website contact interactivity, shopping convenience, as well as care and service are the factors that the present study investigated as far as the patient relationship management is concerned. METHODS: This descriptive-analytical study was conducted on 206 patients visiting Shahid Faghihi and Ali Asghar Hospitals in Shiraz, which were capable of offering electronic services. The data collection tool was a researcher-made questionnaire based on the Mekkamol model and other similar studies, as well as investigations into the websites of the world's top hospitals. The questionnaire's validity was approved by a committee of experts and its reliability was approved based on a 54-patient sample with a Cronbach's alpha of 0.94. The data were analyzed using the Structural Equation Modeling (SEM) with partial least squares (PLS) approach and by utilizing SPSS and Smart-PLS V2 software programs. RESULTS: The results showed that there are significant relationships between "website character" and "website contact interactivity" (p=0.00), between "shopping convenience" and "website contact interactivity" (p=0.00), and between "website contact interactivity" and "care and service" (p=0.00). CONCLUSION: Website design with such characteristics as website simplicity, shopping convenience, authenticity of information, and provision of such services as admission, scheduling appointments, and electronic payment of bills will result in interaction and communication between patients and hospital websites. This will, for its turn, pave the way for attracting more patients.