OBJECTIVES: Diabetes is increasing in worldwide prevalence, toward epidemic levels. Diabetic neuropathy, one of the most common complications of diabetes mellitus, is a serious condition that can lead to amputation. This study used a multicategory support vector machine (MSVM) to predict diabetic peripheral neuropathy severity classified into four categories using patients' demographic characteristics and clinical features. METHODS: In this study, the data were collected at the Diabetes Center of Hamadan in Iran. Patients were enrolled by the convenience sampling method. Six hundred patients were recruited. After obtaining informed consent, a questionnaire collecting general information and a neuropathy disability score (NDS) questionnaire were administered. The NDS was used to classify the severity of the disease. We used MSVM with both one-against-all and one-against-one methods and three kernel functions, radial basis function (RBF), linear, and polynomial, to predict the class of disease with an unbalanced dataset. The synthetic minority class oversampling technique algorithm was used to improve model performance. To compare the performance of the models, the mean of accuracy was used. RESULTS: For predicting diabetic neuropathy, a classifier built from a balanced dataset and the RBF kernel function with a one-against-one strategy predicted the class to which a patient belonged with about 76% accuracy. CONCLUSIONS: The results of this study indicate that, in terms of overall classification accuracy, the MSVM model based on a balanced dataset can be useful for predicting the severity of diabetic neuropathy, and it should be further investigated for the prediction of other diseases.
Amputation ; Classification ; Cross-Sectional Studies* ; Dataset ; Diabetes Complications ; Diabetic Neuropathies ; Humans ; Informed Consent ; Iran ; Logistic Models ; Methods ; Peripheral Nervous System Diseases* ; Prevalence ; Support Vector Machine*

Longitudinal data are prevalent in clinical research; due to their correlated nature, special analysis must be used for this type of data. Creatinine is an important marker in predicting end-stage renal disease, and it is recorded longitudinally. This study compared the prediction performance of linear regression (LR), linear mixed-effects model (LMM), least-squares support vector regression (LS-SVR), and mixed-effects least-squares support vector regression (MLS-SVR) methods to predict serum creatinine as a longitudinal outcome.

PURPOSE: Anatomical variations of the external nasal wall are highly important, since they play a role in obstruction or drainage of the ostiomeatal complex and ventilation and can consequently elevate the risk of pathological sinus conditions. This study aimed to assess anatomical variations of the nasal cavity and ethmoidal sinuses and their correlations on cone-beam computed tomography (CBCT) scans. MATERIALS AND METHODS: This cross-sectional study evaluated CBCT scans of 250 patients, including 107 males and 143 females, to determine the prevalence of anatomical variations of the nasal cavity and ethmoidal sinuses. All images were taken using a New Tom 3G scanner. Data were analyzed using the chi-square test, Kruskal-Wallis test, and the Mann-Whitney test. RESULTS: The most common anatomical variations were found to be nasal septal deviation (90.4%), agger nasi air cell (53.6%), superior orbital cell (47.6%), pneumatized nasal septum (40%), and Onodi air cell (37.2%). Correlations were found between nasal septal deviation and the presence of a pneumatized nasal septum, nasal spur, and Haller cell. No significant associations were noted between the age or sex of patients and the presence of anatomical variations (P>0.05). CONCLUSION: Radiologists and surgeons must pay close attention to the anatomical variations of the sinonasal region in the preoperative assessment to prevent perioperative complications.
Cone-Beam Computed Tomography ; Cross-Sectional Studies ; Drainage ; Ethmoid Sinus ; Female ; Humans ; Male ; Nasal Cavity ; Nasal Septum ; Orbit ; Prevalence ; Surgeons ; Ventilation

Objectives: Heart failure (HF) is a common disease with a high hospital readmission rate. This study considered class imbalance and missing data, which are two common issues in medical data. The current study’s main goal was to compare the performance of six machine learning (ML) methods for predicting hospital readmission in HF patients. Methods: In this retrospective cohort study, information of 1,856 HF patients was analyzed. These patients were hospitalized in Farshchian Heart Center in Hamadan Province in Western Iran, from October 2015 to July 2019. The support vector machine (SVM), least-square SVM (LS-SVM), bagging, random forest (RF), AdaBoost, and naïve Bayes (NB) methods were used to predict hospital readmission. These methods’ performance was evaluated using sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. Two imputation methods were also used to deal with missing data. Results: Of the 1,856 HF patients, 29.9% had at least one hospital readmission. Among the ML methods, LS-SVM performed the worst, with accuracy in the range of 0.57–0.60, while RF performed the best, with the highest accuracy (range, 0.90–0.91). Other ML methods showed relatively good performance, with accuracy exceeding 0.84 in the test datasets. Furthermore, the performance of the SVM and LS-SVM methods in terms of accuracy was higher with the multiple imputation method than with the median imputation method. Conclusions This study showed that RF performed better, in terms of accuracy, than other methods for predicting hospital readmission in HF patients.

PURPOSE: This study was performed to evaluate the position of impacted mandibular third molars in different skeletal facial types among a group of Iranian patients. MATERIALS AND METHODS: A total of 400 mandibular third molars in 200 subjects with different types of facial growth were radiographically investigated for their positions according to their types of facial growth on the basis of the beta angle. The subjects were divided into three groups (class I, II, and III) according to ANB angle, representing the anteroposterior relationship of the maxilla to the mandible. Meanwhile, the subjects were also divided into three groups (long, normal, and short face) according to the angle between the stella-nasion and mandibular plane (SNGoGn angle). ANOVA was used for statistical analysis. RESULTS: The mean beta angle showed no significant difference among class I, II, and III malocclusions (df=2, F=0.669, p=0.513). The same results were also found in short, normal, and long faces (df=1.842, F=2, p=0.160). The mesioangular position was the most frequent one in almost all of the facial growth patterns. Distoangular and horizontal positions of impaction were not found in the subjects with class III and normal faces. In the long facial growth pattern, the frequency of vertical and distoangular positions were not different. CONCLUSION: In almost all of the skeletal facial types, the mesioangular impaction of the mandibular third molar was the most prevalent position, followed by the horizontal position. In addition, beta angle showed no significant difference in different types of facial growth.
Humans ; Malocclusion ; Mandible ; Maxilla ; Molar, Third* ; Tooth, Impacted