An fMRI Normative Database for Connectivity Networks Using One-Class Support Vector Machines

The application of functional magnetic resonance imaging (fMRI) in neuroscience studies has increased enormously in the last decade. Although primarily used to map brain regions activated by specific stimuli, many studies have shown that fMRI can also be useful in identifying interactions between brain regions (functional and effective connectivity). Despite the widespread use of fMRI as a research tool, clinical applications of brain connectivity as studied by fMRI are not well established. One possible explanation is the lack of normal pattern, and intersubject variability-two variables that are still largely uncharacterized in most patient populations of interest. In the current study, we combine the identification of functional connectivity networks extracted by using Spearman partial correlation with the use of a one-class support vector machine in order construct a normative database. An application of this approach is illustrated using an fMRI dataset of 43 healthy Subjects performing a visual working memory task. In addition, the relationships between the results obtained and behavioral data are explored. Hum Brain Mapp 30:1068-1076, 2009. (C) 2008 Wiley-Liss. Inc.

Hip fracture prognosis: could bioimpedance be an alternative to conventional nutritional assessment?

Background: Risk-factors for mortality in hip fractures encompass nutritional status, nominally body mass index, but not body composition. Given the difficulty of anthropometric assessment in bedridden patients a prospective study with bioimpedance analysis was designed. Methods: Elderly patients with hip fracture were consecutively recruited. Biochemical tests, primitive bioimpedance measurements (resistance, reactance and phase angle) and follow-up till one year were targeted. Results: Patients (N = 69, 81.2 +/- 8.1 years old, 72.5% females) stayed in the hospital for 15.5 +/- 17.1 days, and 18.8 %(13/69) required further hospitalization during the ensuing months. Mortality was 11.6% within 30 days, coinciding with hospital mortality, and an additional 11.6% till one year, thus reaching 23.2%. Anemia, hypoalbuminemia and low transferrin, along with elevated glucose and urea were frequent, suggesting undernutrition with metabolic derangements. Reactance, urea and creatinine were different in patients suffering both early and late demise. Resistance, white blood cell count and osteoporosis were risk factors for early mortality only, and anemia exclusively for late mortality. Conclusions: Primitive bioimpedance measurements, which had not been hitherto investigated, were prognostically related to early and late mortality. These markers of disease-related malnutrition and especially reactance should be further studied in patients unfit for anthropometric evaluation due to fracture and immobility.