Neuroimaging-based diagnostics could potentially assist clinicians to make more accurate diagnoses resulting in faster, more effective treatment. We participated in the 2011 ADHD-200 Global Competition which involved analyzing a large dataset of 973 participants including Attention deficit hyperactivity disorder (ADHD) patients and healthy controls. Each participant's data included a resting state functional magnetic resonance imaging (fMRI) scan as well as personal characteristic and diagnostic data. The goal was to learn a machine learning classifier that used a participant's resting state fMRI scan to diagnose (classify) that individual into one of three categories: healthy control, ADHD combined (ADHD-C) type, or ADHD inattentive (ADHD-I) type. We used participants' personal characteristic data (site of data collection, age, gender, handedness, performance IQ, verbal IQ, and full scale IQ), without any fMRI data, as input to a logistic classifier to generate diagnostic predictions. Surprisingly, this approach achieved the highest diagnostic accuracy (62.52%) as well as the highest score (124 of 195) of any of the 21 teams participating in the competition. These results demonstrate the importance of accounting for differences in age, gender, and other personal characteristics in imaging diagnostics research. We discuss further implications of these results for fMRI-based diagnosis as well as fMRI-based clinical research. We also document our tests with a variety of imaging-based diagnostic methods, none of which performed as well as the logistic classifier using only personal characteristic data.

BACKGROUND: The objective of the current study was to determine the prevalence and the degree of lowered self-esteem across the spectrum of psychiatric disorders. METHOD: The present study was carried out on a consecutive sample of 1,190 individuals attending an open-access psychiatric outpatient clinic. There were 957 psychiatric patients, 182 cases with conditions not attributable to a mental disorder, and 51 control subjects. Patients were diagnosed according to DSM III-R diagnostic criteria following detailed assessments. At screening, individuals completed two questionnaires to measure self-esteem, the Rosenberg self-esteem scale and the Janis and Field Social Adequacy scale. Statistical analyses were performed on the scores of the two self-esteem scales. RESULTS: The results of the present study demonstrate that all psychiatric patients suffer some degree of lowered self-esteem. Furthermore, the degree to which self-esteem was lowered differed among various diagnostic groups. Self-esteem was lowest in patients with major depressive disorder, eating disorders, and substance abuse. Also, there is evidence of cumulative effects of psychiatric disorders on self-esteem. Patients who had comorbid diagnoses, particularly when one of the diagnoses was depressive disorders, tended to show lower self-esteem. CONCLUSIONS: Based on both the previous literature, and the results from the current study, we propose that there is a vicious cycle between low self-esteem and onset of psychiatric disorders. Thus, low self-esteem increases the susceptibility for development of psychiatric disorders, and the presence of a psychiatric disorder, in turn, lowers self-esteem. Our findings suggest that this effect is more pronounced with certain psychiatric disorders, such as major depression and eating disorders.

Previous studies have found that treatment with lithium over a 4-week period may increase the concentration of N-acetyl-aspartate (NAA) in both bipolar patients and controls. In view of other findings indicating that NAA concentrations may be a good marker for neuronal viability and/or functioning, it has been further suggested that some of the long term benefits of lithium may therefore be due to actions to improve these neuronal properties. The aim of the present study was to utilize H magnetic resonance spectroscopy ( H MRS) to further examine the effects of both lithium and sodium valproate upon NAA concentrations in treated euthymic bipolar patients. In the first part of the study, healthy controls (n =18) were compared with euthymic bipolar patients (type I and type II) who were taking either lithium (n =14) or sodium valproate (n =11), and NAA : creatine ratios were determined. In the second part, we examined a separate group of euthymic bipolar disorder patients taking sodium valproate (n =9) and compared these to age- and sex-matched healthy controls (n =11), and we quantified the exact concentrations of NAA using an external solution. The results from the first part of the study showed that bipolar patients chronically treated with lithium had a significant increase in NAA concentrations but, in contrast, there were no significant increases in the sodium valproate-treated patients compared to controls. The second part of the study also found no effects of sodium valproate on NAA concentrations. These findings are the first to compare NAA concentrations in euthymic bipolar patients being treated with lithium or sodium valproate. The results support suggestions that longer-term administration of lithium to bipolar patients may increase NAA concentrations. However, the study suggests that chronic administration of sodium valproate to patients does not lead to similar changes in NAA concentrations. These findings suggest that sodium valproate and lithium may not share a common mechanism of action in bipolar disorder involving neurotrophic or neuroprotective effects.

A subset of patients with comorbid major depressive disorder and generalized anxiety disorder (GAD) was examined from a double-blind. placebo-controlled study comparing the efficacy and safety of venlafaxine extended release (XR) and fluoxetine. From a total of 368 patients, 92 patients meeting DSM-IV criteria for major depressive disorder who also had comorbid GAD were identified. The comparison group comprised 276 evaluable noncomorbid patients. Patients received venlafaxine XR (75-225 mg/day), fluoxetine (20-60 mg/day), or placebo for 12 weeks. Efficacy evaluations included Hamilton Rating Scale for Depression (HAM-D), Hamilton Rating Scale for Anxiety (HAM-A), and Clinical Global Impressions (CGI) scale. By the final assessment at week 12, comorbid patients in the venlafaxine XR group, but not in the fluoxetine group, showed a significantly greater decrease than those in the placebo group in the primary efficacy variables of mean HAM-D and HAM-A total scores (p < .05, pairwise comparison). In comorbid patients, significant pairwise differences were noted between venlafaxine XR and placebo at week 12 for the secondary variables of HAM-D anxiety-somatization and retardation factors, HAM-D depressed mood item. HAM-A psychic anxiety factor, the Hospital Anxiety and Depression scale (HAD) anxiety subscale score, and the Covi Anxiety Scale score. Fluoxetine was significantly different from placebo only on the HAD depression subscale score. Response, defined as > or = 50% decrease in symptoms score, was achieved in 66% and 59% of the comorbid patients for HAM-D and HAM-A, respectively, in the venlafaxine XR group at week 12. This response was higher than that seen with fluoxetine (52% and 45%) or placebo (36% and 24%). Onset of efficacy appeared to be slower in comorbid than in noncomorbid patients. This is the first evidence from a controlled study of the effectiveness of pharmacotherapy in patients with comorbid major depressive disorder and GAD. The delayed improvement in comorbid patients compared with noncomorbid patients suggests that a longer treatment period may be necessary in comorbid patients.