A Machine Learning Algorithm to Discriminating Between Bipolar and Major Depressive Disorders Based on Resting EEG Data

Distinguishing major depressive disorder (MDD) from bipolar disorder (BD) is a crucial clinical challenge due to the lack of known biomarkers. Conventional methods of diagnosis rest exclusively on symptomatic presentation, and personal and family history. As a result, BD-depressed episode (BD-DE) is often misdiagnosed as MDD, and inappropriate therapy is given. Electroencephalography (EEG) has been widely studied as a potential source of biomarkers to differentiate these disorders. Previous attempts using machine learning (ML) methods have delivered insufficient sensitivity and specificity for clinical use, likely as a consequence of the small training set size, and inadequate ML methodology. We hope to overcome these limitations by employing a training dataset of resting-state EEG from 71 MDD and 71 BD patients. We introduce a robust 3 steps ML technique: 1) a multi-step preprocessing method is used to improve the quality of the EEG signal 2) symbolic transfer entropy (STE), which is an effective connectivity measure, is applied to the resultant EEG signals 3) the ML algorithm uses the extracted STE features to distinguish MDD from BD patients. Clinical Relevance--- The accuracy of our algorithm, derived from a large sample of patients, suggests that this method may hold significant promise as a clinical tool. The proposed method delivered total accuracy, sensitivity, and specificity of 84.9%, 83.4%, and 87.1%, respectively.

Association of retinol-binding protein 4 with metabolic syndrome in first-degree relatives of type 2 diabetic patients

Background:

Retinol-binding protein 4 (RBP4) is known to regulate lipid and glucose metabolism and insulin resistance. The influences of RBP4 on metabolic syndrome (MS) are still unclear. The purpose of this study is to evaluate the association between serum levels of RBP4 and MS components in first-degree relations of type 2 diabetic patients.

Materials and Methods:

This cross-sectional study was performed within the framework of the diabetes prevention project in Isfahan. This study has been conducted during 2012–2013. Seventy-eight subjects participate, with an average age of 43.20 ± 5.29 years. Weight, height, waist and hip circumferences, blood pressure (BP) of participants, fasting plasma glucose, hemoglobin A1c, total cholesterol, high-density lipoprotein cholesterol, triglyceride (TG), and serum RBP4 were measured from fasting blood sample taken from each participant after an overnight fast (12–14 h).

Results:

Systolic and diastolic BP were significantly higher in people in top median of RBP4 (11.8 ± 1.5 vs. 11.0 ± 1.2, P = 0.01 and 7.8 ± 1.0 vs. 7.3 ± 0.9, P = 0.03). Moreover, TG in people with high levels of RBP4 was higher compared with those with low levels of RBP4 (177.7 ± 97.6 vs. 138.7 ± 56.9, P = 0.02). People with low levels of RBP4 had significant greater hip circumferences (107.9 ± 7.5 vs. 104.3 ± 8.0, P = 0.04). There was no correlation between RBP4 and MS in crude model (odds ratio [OR]: 1.00, 0.95–1.05, P = 0.97). This null correlation remained after adjustment for body mass index, age, and physical activity (OR: 0.93, 0.91–1.07, P = 0.31).

Conclusion:

Although RBP4 levels were positively association with some risk factors of MS including hip circumference, TG, and systolic and diastolic BP, it does not seem to be a valuable marker for identification of the MS in the first relative degree of diabetic patients.

Effects of direct and indirect bleach on dentin fracture toughness

There are concerns that tooth-whitening procedures irreversibly damage tooth structure. We investigated the hypothesis that dental bleaches significantly affect dentin structural integrity. The objective was to evaluate the effects of peroxide bleaches on dentin fracture toughness. Compact test specimens, composed of human dentin, were used (n = 10/group). Bleach (16% or 10% carbamide peroxide or 3% hydrogen peroxide) or control material, containing 0.1% sodium fluoride, was applied directly or indirectly to dentin through enamel (6 hrs/day) for 2 or 8 weeks. Fracture toughness results were analyzed by ANOVA and Fisher's LSD test (p < 0.05). There were significant decreases in mean fracture toughness after two- and eight-week direct (19-34% and 61-68%, respectively) and indirect (up to 17% and 37%, respectively) bleach application. The in vitro reduction in dentin fracture toughness caused by the application of peroxide bleaches was greater for the direct application method, longer application time, and higher bleach concentration.