Tehran University Medical Journal

Background: Alzheimer's disease (AD) is the most common disorder of dementia, which has not been cured after its occurrence. AD progresses indiscernible, first destroy the structure of the brain and subsequently becomes clinically evident. Therefore, the timely and correct diagnosis of these structural changes in the brain is very important and it can prevent the disease or stop its progress. Nowadays, remark to this fact that magnetic resonance imaging (MRI) provides very useful and detailed information, and due to non-invasiveness, this method has been great interest to the researchers. The aim of this study was diagnosis of AD with MRI by support vector machine model (SVM).
Methods: This is an analytical and modeling research which done in School of Public Health, Kermanshah University of Medical Science, Iran, from February 2017 to November 2017. The data used in this study was a database named Miriad containing brain MRI of 69 individuals (46 Alzheimer's disease and 23 healthy subjects) that was collected at the central hospital in London. Individuals were categorized into two groups of healthy and Alzheimer's disease with two criteria: NINCDS-ADRAD and MMSE (as the golden standard). In this paper SVM model with three linear, binomial and Gaussian kernels was used to distinguish Alzheimer`s disease from healthy individuals.
Results: Finally, SVM model with Gaussian kernel, separated AD and healthy subjects with 88.34% accuracy. The most important Areas for Alzheimer were three Area: Right para hippocampal gyrus, Left para hippocampal gyrus and Right hippocampus. The clinical result of this study is to identify the most important ROI for the diagnosis of Alzheimer's by a clinical specialist. Experts should focus on atrophy in the three Areas.
Conclusion: This study showed that the SVM model with Gaussian RBF kernel can separated AD from healthy subjects by high accuracy. Based on results of this study, can make a software to use in MRI centers for screening AD test by people over the age of 50 years.

Background: 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.
Methods: 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.
Results: 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.
Conclusion: 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.

Background: Multiple sclerosis (MS) is a degenerative inflammatory disease which is most commonly diagnosed by magnetic resonance imaging (MRI). But, since the MRI device uses of a magnetic field, if there are metal objects in the patient's body, it can disrupt the health of the patient, the functioning of the MRI, and distortion in the images. Due to limitations of using MRI device, screening seems necessary for those patients who have metal objects in their bodies. Therefore, this study is carried out to compare two models: support vector machine and random forest.
Methods: This analytical-modelling research was implemented on MS data collection, the specifications of which are recorded in health registry system in School of Public Health, Kermanshah University of Medical Sciences, Iran, from May 2017 to August 2018. For the purpose of this study, a total of 317 subjects were selected as a sample; 188 subjects were diagnosed with MS and 128 subjects showed no symptoms of MS. In order to fit the support vector machine (SVM) model, radial basis kernel function was used. The parameters of this machine were optimized with genetic algorithm. After this step, the support vector machine and random forest (RF) were compared with respect to three factors: accuracy, sensitivity, and specificity.
Results: Based upon the obtained results of study, accuracy, sensitivity, and specificity of SVM were 0.79, 0.80, and 0.78, respectively. In comparison, accuracy, sensitivity, and specificity of RF were found to be 0.76, 0.81, and 0.70, respectively.
Conclusion: In general, both models which were compared in current study showed desirable performance; however, in term of accuracy, as an important criteria for performance comparison in this area of research, it can be argued that support vector machine can do better than random forest in diagnosing multiple sclerosis.

Background: In the current study, a hybrid feature selection approach involving filter and wrapper methods is applied to some bioscience databases with various records, attributes and classes; hence, this strategy enjoys the advantages of both methods such as fast execution, generality, and accuracy. The purpose is diagnosing of the disease status and estimating of the patient survival.
Methods: Feature selection algorithms have been modeled in Matlab R2021a during April and May 2022 in the framework of statistical pattern recognition. First, the features are ranked based on normalized mutual information, as a metric of relevance and redundancy of features, and accordingly, an optimum feature subset with the highest accuracy of classification is selected. Two feature selection algorithms, i.e., inclusion of features enhancing the classification accuracy and exclusion of irrelevant features are applied to the interest datasets, subsequent to the mini-batch k-means clustering of records.

Results: At the end of the execution of both feature selection methods, evaluation metrics including accuracy, precision, recall, and F1 score are measured and compared. Both proposed feature selection approaches for the molecular biology, hepatitis C virus (HCV), and E. coli bacteria datasets result in the precision and recall scores more than 98 percent, meaning that there are few false positives and false negatives in the linear support vector machine (LSVM) classification. Regarding the HCV dataset, selection of nine relevant features among the thirteen present ones using the feature exclusion method yields the classification accuracy and F1 score of 98.92 percent and 99.02 percent, respectively. The feature inclusion approach also results in an accuracy of 98.78 percent with a slight discrepancy. Conclusion: The results reveal superior strength of the feature selection methods used here for life science datasets with higher-order features such as protein/gene expression database. The potentials to generalize to other classifiers and automatically specify the optimal number of features during the feature selection procedure make these approaches flexible in many data mining applications for the life sciences.