Discriminating between bipolar and major depressive disorder using a machine learning approach and resting-state EEG data.

OBJECTIVE: Distinguishing major depressive disorder (MDD) from bipolar disorder (BD) is a crucial clinical challenge as effective treatment is quite different for each condition. In this study electroencephalography (EEG) was explored as an objective biomarker for distinguishing MDD from BD using an efficient machine learning algorithm (MLA) trained by a relatively large and balanced dataset. METHODS: A 3 step MLA was applied: (1) a multi-step preprocessing method was used to improve the quality of the EEG signal, (2) symbolic transfer entropy (STE), an effective connectivity measure, was applied to the resultant EEG and (3) the MLA used the extracted STE features to distinguish MDD (N = 71) from BD (N = 71) subjects. RESULTS: 14 connectivity features were selected by the proposed algorithm. Most of the selected features were related to the frontal, parietal, and temporal lobe electrodes. The major involved regions were the Broca region in the frontal lobe and the somatosensory association cortex in the parietal lobe. These regions are near electrodes FC5 and CPz and are involved in processing language and sensory information, respectively. The resulting classifier delivered an evaluation accuracy of 88.5% and a test accuracy of 89.3%, using 80% of the data for training and evaluation and the remaining 20% for testing, respectively. CONCLUSIONS: The high evaluation and test accuracies of our algorithm, derived from a large balanced training sample suggests that this method may hold significant promise as a clinical tool. SIGNIFICANCE: The proposed MLA may provide an inexpensive and readily available tool that clinicians may use to enhance diagnostic accuracy and shorten time to effective treatment.

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.

Methadone toxicity: comparing tablet and syrup formulations during a decade in an academic poison center of Iran.

CONTEXT: Due to an increase in the number of methadone maintenance clinics in the past decade in Iran, acute methadone overdose has become one of the common poisonings in our society. OBJECTIVE: To compare the characteristics of methadone poisoning between syrup and tablet formulation as well as to discuss the relative advantages and disadvantages of poisoning from the perspective of toxicity. MATERIAL AND METHODS: In a retrospective cross-sectional study from 2000 to 2010, sampled data of all hospitalized methadone-overdosed patients were collected through chart review of hospital records. Concurrently, the total number of methadone sales was gathered. RESULTS: A total of 1426 patients with methadone poisoning had been hospitalized, including 1072 cases who consumed syrup or tablet solely. Mean ± SD milligram ingested dose of syrup and tablet were 153 ± 339 and 88 ± 274, respectively (p < 0.001). The mean time elapsed since ingestion was 9 ± 9 and 7 ± 7 h, respectively. Most of the accidental poisoning cases occurred as a result of syrup formulation, particularly by children under 12 years old after being mistaken for cough mixture or water. Conversely, exposure to methadone tablets was more common in patients with suicidal intent. There was no statistically significant difference between the rates of intubation and death between the two groups. DISCUSSION: Higher doses of methadone in the syrup form appear to exert a similar severity of poisoning and outcomes compared to lesser doses of that in the tablet form. Similarities in outcomes, despite differences in exposure history, may reflect relatively prompt transfer to hospital and adequate provision of clinical care, including supportive care and naloxone. CONCLUSION: In order to reduce the rate of poisoning, we recommend the use of child-resistant containers for dispensing syrup, reduction in methadone concentration, adding a coloring agent, special flavor, and education of patients on the safe storage of methadone in their home in order to reduce the occurrence of accidental poisonings.

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.