Individual Classification of Mild Cognitive Impairment Subtypes by Support Vector Machine Analysis of White Matter DTI.

BACKGROUND AND PURPOSE: MCI was recently subdivided into sd-aMCI, sd-fMCI, and md-aMCI. The current investigation aimed to discriminate between MCI subtypes by using DTI. MATERIALS AND METHODS: Sixty-six prospective participants were included: 18 with sd-aMCI, 13 with sd-fMCI, and 35 with md-aMCI. Statistics included group comparisons using TBSS and individual classification using SVMs. RESULTS: The group-level analysis revealed a decrease in FA in md-aMCI versus sd-aMCI in an extensive bilateral, right-dominant network, and a more pronounced reduction of FA in md-aMCI compared with sd-fMCI in right inferior fronto-occipital fasciculus and inferior longitudinal fasciculus. The comparison between sd-fMCI and sd-aMCI, as well as the analysis of the other diffusion parameters, yielded no significant group differences. The individual-level SVM analysis provided discrimination between the MCI subtypes with accuracies around 97%. The major limitation is the relatively small number of cases of MCI. CONCLUSIONS: Our data show that, at the group level, the md-aMCI subgroup has the most pronounced damage in white matter integrity. Individually, SVM analysis of white matter FA provided highly accurate classification of MCI subtypes.

Outbreak of Mycobacterium haemophilum infections after permanent makeup of the eyebrows.

We report a Mycobacterium haemophilum outbreak after permanent make-up of the eyebrows performed by the same freelance artist. Twelve patients presented an eyebrow lesion and cervical lymphadenitis. All were treated with antibiotics. Surgery was required in 10 cases. M. haemophilum DNA was identified in the make-up ink.

Permanent Genetic Resources added to Molecular Ecology Resources Database 1 August 2010-30 September 2010

This article documents the addition of 229 microsatellite marker loci to the Molecular Ecology Resources Database. Loci were developed for the following species: Acacia auriculiformis x Acacia mangium hybrid, Alabama argillacea, Anoplopoma fimbria, Aplochiton zebra, Brevicoryne brassicae, Bruguiera gymnorhiza, Bucorvus leadbeateri, Delphacodes detecta, Tumidagena minuta, Dictyostelium giganteum, Echinogammarus berilloni, Epimedium sagittatum, Fraxinus excelsior, Labeo chrysophekadion, Oncorhynchus clarki lewisi, Paratrechina longicornis, Phaeocystis antarctica, Pinus roxburghii and Potamilus capax. These loci were cross-tested on the following species: Acacia peregrinalis, Acacia crassicarpa, Bruguiera cylindrica, Delphacodes detecta, Tumidagena minuta, Dictyostelium macrocephalum, Dictyostelium discoideum, Dictyostelium purpureum, Dictyostelium mucoroides, Dictyostelium rosarium, Polysphondylium pallidum, Epimedium brevicornum, Epimedium koreanum, Epimedium pubescens, Epimedium wushanese and Fraxinus angustifolia.

Colonic movements in healthy subjects as monitored by a Magnet Tracking System.

The Magnet Tracking System (MTS) is a minimally-invasive technique of continuous evaluation of gastrointestinal motility. In this study, MTS was used to analyse colonic propulsive dynamics and compare the transit of a magnetic pill with that of standard radio-opaque markers. MTS monitors the progress in real time of a magnetic pill through the gut. Ten men and 10 women with regular daily bowel movements swallowed this pill and 10 radio-opaque markers at 8 pm. Five hours of recordings were conducted during 2 following mornings. Origin, direction, amplitude and velocity of movements were analysed relative to space-time plots of the pill trajectory. Abdominal radiographs were taken to compare the progress of both pill and markers. The magnetic pill lay idle for 90% of its sojourn in the colon; its total retrograde displacement accounted for only 20% of its overall movement. Analysis of these movements showed a bimodal distribution of velocities: around 1.5 and 50 cm min(-1), the latter being responsible for 2/3 of distance traversed. There were more movements overall and more mass movements in males. Net hourly forward progress was greater in the left than right colon, and greater in males. The position of the magnetic pill correlated well with the advancement of markers. MTS showed patterns and propulsion dynamics of colonic segments with as yet unmet precision. Detailed analysis of slow and fast patterns of colonic progress makes it possible to specify the motility of colonic segments, and any variability in gender. Such analysis opens up promising avenues in studies of motility disorders.

Non-invasive diagnostic biomarkers for estimating the onset time of permanent cerebral ischemia.

The treatments for ischemic stroke can only be administered in a narrow time-window. However, the ischemia onset time is unknown in ~30% of stroke patients (wake-up strokes). The objective of this study was to determine whether MR spectra of ischemic brains might allow the precise estimation of cerebral ischemia onset time. We modeled ischemic stroke in male ICR-CD1 mice using a permanent middle cerebral artery filament occlusion model with laser Doppler control of the regional cerebral blood flow. Mice were then subjected to repeated MRS measurements of ipsilateral striatum at 14.1 T. A striking initial increase in γ-aminobutyric acid (GABA) and no increase in glutamine were observed. A steady decline was observed for taurine (Tau), N-acetyl-aspartate (NAA) and similarly for the sum of NAA+Tau+glutamate that mimicked an exponential function. The estimation of the time of onset of permanent ischemia within 6 hours in a blinded experiment with mice showed an accuracy of 33±10 minutes. A plot of GABA, Tau, and neuronal marker concentrations against the ratio of acetate/NAA allowed precise separation of mice whose ischemia onset lay within arbitrarily chosen time-windows. We conclude that (1)H-MRS has the potential to detect the clinically relevant time of onset of ischemic stroke.

Synchronous and baroceptor-sensitive oscillations in skin microcirculation: evidence for central autonomic control.

To determine whether skin blood flow is local or takes part in general regulatory mechanisms, we recorded laser-Doppler flowmetry (LDF; left and right index fingers), blood pressure, muscle sympathetic nerve activity (MSNA), R-R interval, and respiration in 10 healthy volunteers and 3 subjects after sympathectomy. We evaluated 1) the synchronism of LDF fluctuations in two index fingers, 2) the relationship with autonomically mediated fluctuations in other signals, and 3) the LDF ability to respond to arterial baroreflex stimulation (by neck suction at frequencies from 0.02 to 0.20 Hz), using spectral analysis (autoregressive uni- and bivariate, time-variant algorithms). Synchronous LDF fluctuations were observed in the index fingers of healthy subjects but not in sympathectomized patients. LDF fluctuations were coherent with those obtained for blood pressure, MSNA, and R-R interval. LDF fluctuations were leading blood pressure in the low-frequency (LF; 0.1 Hz) band and lagging in the respiratory, high-frequency (HF; approximately 0.25 Hz) band, suggesting passive "downstream" transmission only for HF and "upstream" transmission for LF from the microvessels. LDF fluctuations were responsive to sinusoidal neck suction up to 0.1 Hz, indicating response to sympathetic modulation. Skin blood flow thus reflects modifications determined by autonomic activity, detectable by frequency analysis of spontaneous fluctuations.

The "reversed" treatment approach for synchronous liver metastases and colorectal cancer. Feasability and first results

Background: The « reversed treatment» approach inverts the treatment sequence of¦advanced synchronous colorectal liver metastases - i.e. the liver metastasis is¦treated first, followed by resection of the primary tumor. Chemotherapy is performed¦before and after liver surgery. We recently started to use a reversed treatment¦approach in selected patients. The aim of this study is to critically assess this new¦treatment modality.¦Methods: Nine patients (7 male, 2 female, mean age 62 years) benefited from this¦new treatment between November 2008 and May 2010. The data were collected¦retrospectively.¦Results: All patients responded to the neoadjuvant chemotherapy. The median¦number of liver metastases was 6 (range 1 - 22). The median size of the largest liver¦metastases was 4.3 cm (range 2.6 - 13 cm). Three patients had portal vein¦embolization prior to liver surgery. Two patients could not complete the treatment.¦One had to undergo emergency surgery for occluding colonic tumor. The second one¦showed liver recurrence before starting the adjuvant chemotherapy. The seven¦patients who completed the treatment are still alive after a median time of 27 months¦(range 17 - 37 months). Seven of them had recurrence (1 rectal, 6 liver). The median¦disease-free survival was 9 months (range 0 - 17 months).¦Conclusion: Based on our preliminary experiences, the reversed strategy shows¦encouraging results for the treatment of advanced synchronous colorectal liver¦metastases in well selected patients. The treatment was generally well tolerated and¦long term survival seems to be prolonged.

Auditory Neurons with Transitory Axons to Visual Areas Form Short Permanent Projections.

The kitten's auditory cortex (including the first and second auditory fields AI and AII) is known to send transient axons to either ipsi- or contralateral visual areas 17 and 18. By the end of the first postnatal month the transitory axons, but not their neurons of origin, are eliminated. Here we investigated where these neurons project after the elimination of the transitory axon. Eighteen kittens received early (postnatal day (pd) 2 - 5) injections of long lasting retrograde fluorescent traces in visual areas 17 and 18 and late (pd 35 - 64) injections of other retrograde fluorescent tracers in either hemisphere, mostly in areas known to receive projections from AI and AII in the adult cat. The middle ectosylvian gyrus was analysed for double-labelled neurons in the region corresponding approximately to AI and AII. Late injections in the contralateral (to the analysed AI, AII) hemisphere including all of the known auditory areas, as well as some visual and 'association' areas, did not relabel neurons which had had transient projections to either ipsi- or contralateral visual areas 17 - 18. Thus, AI and AII neurons after eliminating their transient juvenile projections to visual areas 17 and 18 do not project to the other hemisphere. In contrast, relabelling was obtained with late injections in several locations in the ipsilateral hemisphere; it was expressed as per cent of the population labelled by the early injections. Few neurons (0 - 2.5%) were relabelled by large injections in the caudal part of the posterior ectosylvian gyrus and the adjacent posterior suprasylvian sulcus (areas DP, P, VP). Multiple injections in the middle ectosylvian gyrus relabelled a considerably larger percentage of neurons (13%). Single small injections in the middle ectosylvian gyrus (areas AI, AII), the caudal part of the anterior ectosylvian gyrus and the rostral part of the posterior ectosylvian gyrus relabelled 3.1 - 7.0% of neurons. These neurons were generally near (<2.0 mm) the outer border of the late injection sites. Neurons with transient projections to ipsi- or contralateral visual areas 17 and 18 were relabelled in similar proportions by late injections at any given location. Thus, AI or AII neurons which send a transitory axon to ipsi- or contralateral visual areas 17 and 18 are most likely to form short permanent cortical connections. In that respect, they are similar to medial area 17 neurons that form transitory callosal axons and short permanent axons to ipsilateral visual areas 17 and 18.

Analysis, modelling and classification of geospatial data using machine learning

The research considers the problem of spatial data classification using machine learning algorithms: probabilistic neural networks (PNN) and support vector machines (SVM). As a benchmark model simple k-nearest neighbor algorithm is considered. PNN is a neural network reformulation of well known nonparametric principles of probability density modeling using kernel density estimator and Bayesian optimal or maximum a posteriori decision rules. PNN is well suited to problems where not only predictions but also quantification of accuracy and integration of prior information are necessary. An important property of PNN is that they can be easily used in decision support systems dealing with problems of automatic classification. Support vector machine is an implementation of the principles of statistical learning theory for the classification tasks. Recently they were successfully applied for different environmental topics: classification of soil types and hydro-geological units, optimization of monitoring networks, susceptibility mapping of natural hazards. In the present paper both simulated and real data case studies (low and high dimensional) are considered. The main attention is paid to the detection and learning of spatial patterns by the algorithms applied.

Example-based support vector machine for drug concentration analysis

Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. In this paper, we focus on the prediction of drug concentrations using Support Vector Machines (S VM) and the analysis of the influence of each feature to the prediction results. Our study shows that SVM-based approaches achieve similar prediction results compared with pharmacokinetic model. The two proposed example-based SVM methods demonstrate that the individual features help to increase the accuracy in the predictions of drug concentration with a reduced library of training data.

Prognostic in Vivo Biomarkers for Lesion Development after Cerebral Ischemia

A better prediction of the outcome after ischemia and estimation of onset time at early time points would greatly facilitate clinical decisions. Therefore, the aim of the present study was to use magnetic resonance spectroscopy to identify neurochemical markers for outcome prediction at early time points after ischemia.ICR-CD1 mice were subjected to 10-minute, 30-minute or permanent middle cerebral artery occlusion (MCAO). The regional cerebral blood flow (CBF) was monitored in all animals by laser-Doppler flowmetry. All MR studies were carried out in a horizontal 14.1T magnet. Fast spin echo images with T2-weighted parameters were Bacquired to localize the volume of interest and evaluate the lesion size. Immediately after adjustment of field inhomogeneities, localized 1H MRS was applied to obtain the neurochemical profile from the striatum (6-8 μl) or the cortex (2.2-2.5 μl). Six animals (sham group) underwent nearly identical procedures without MCAO.By comparing the evolution of several metabolites in ischemia of varying severity, we observed that glutamine increases early after transient ischemia independently of severity, but decreases in permanent ischemia. On the opposite, GABA increased in permanent ischemia and decreased in transient. We also observed a decrease in the sum of N-acetyl aspartate + glutamate + taurine in all irreversibly damaged tissues, independently of reperfusion and severity. Finally, we have observed that some metabolites decrease exponentially after ischemia. This exponential decrease could be used to determine the time of ischemia onset in permanent ischemia.In Conclusion, magnetic resonance spectroscopy can be used as a prognostic and diagnostic tool to monitor reperfusion, identify reversibly and irreversibly damaged tissue and evaluate the time of ischemia onset. If these Results can be translated to stroke patients, this technique would greatly improve the diagnosis and help with clinical decisions.