Application and comparison of classification algorithms for recognition of Alzheimer's disease in electrical brain activity (EEG)

The early detection of subjects with probable Alzheimer's disease (AD) is crucial for effective appliance of treatment strategies. Here we explored the ability of a multitude of linear and non-linear classification algorithms to discriminate between the electroencephalograms (EEGs) of patients with varying degree of AD and their age-matched control subjects. Absolute and relative spectral power, distribution of spectral power, and measures of spatial synchronization were calculated from recordings of resting eyes-closed continuous EEGs of 45 healthy controls, 116 patients with mild AD and 81 patients with moderate AD, recruited in two different centers (Stockholm, New York). The applied classification algorithms were: principal component linear discriminant analysis (PC LDA), partial least squares LDA (PLS LDA), principal component logistic regression (PC LR), partial least squares logistic regression (PLS LR), bagging, random forest, support vector machines (SVM) and feed-forward neural network. Based on 10-fold cross-validation runs it could be demonstrated that even tough modern computer-intensive classification algorithms such as random forests, SVM and neural networks show a slight superiority, more classical classification algorithms performed nearly equally well. Using random forests classification a considerable sensitivity of up to 85% and a specificity of 78%, respectively for the test of even only mild AD patients has been reached, whereas for the comparison of moderate AD vs. controls, using SVM and neural networks, values of 89% and 88% for sensitivity and specificity were achieved. Such a remarkable performance proves the value of these classification algorithms for clinical diagnostics.

Evaluation of sugar maple dieback in the Upper Great Lakes region and development of a forest health youth education program

Acer saccharum Marsh., is one of the most valuable trees in the northern hardwood forests. Severe dieback was recently reported by area foresters in the western Upper Great Lakes Region. Sugar Maple has had a history of dieback over the last 100 years throughout its range and different variables have been identified as being the predisposing and inciting factors in different regions at different times. Some of the most common factors attributed to previous maple dieback episodes were insect defoliation outbreaks, inadequate precipitation, poor soils, atmospheric deposition, fungal pathogens, poor management, or a combination of these. The current sugar maple dieback was evaluated to determine the etiology, severity, and change in dieback on both industry and public lands. A network of 120 sugar maple health evaluation plots was established in the Upper Peninsula, Michigan, northern Wisconsin, and eastern Minnesota and evaluated annually from 2009-2012. Mean sugar maple crown dieback between 2009-2012 was 12.4% (ranging from 0.8-75.5%) across the region. Overall, during the sampling period, mean dieback decreased by 5% but individual plots and trees continued to decline. Relationships were examined between sugar maple dieback and growth, habitat conditions, ownership, climate, soil, foliage nutrients, and the maple pathogen sapstreak. The only statistically significant factor was found to be a high level of forest floor impacts due to exotic earthworm activity. Sugar maple on soils with lower pH had less earthworm impacts, less dieback, and higher growth rates than those on soils more favorable to earthworms. Nutritional status of foliage and soil was correlated with dieback and growth suggesting perturbation of nutrient cycling may be predisposing or contributing to dieback. The previous winter's snowfall totals, length of stay on the ground, and number of days with freezing temperatures had a significant positive relationship to sugar maple growth rates. Sapstreak disease, Ceratocystis virescens, may be contributing to dieback in some stands but was not related to the amount of dieback in the region. The ultimate goal of this research is to help forest managers in the Great Lakes Region prevent, anticipate, reduce, and/or salvage stands with dieback and loss in the future. An improved understanding of the complex etiology associated with sugar maple dieback in the Upper Great Lakes Region is necessary to make appropriate silvicultural decisions. Forest Health education helps increase awareness and proactive forest management in the face of changing forest ecosystems. Lessons are included to assist educators in incorporating forest health into standard biological disciplines at the secondary school curricula.

Identification of pathogen and host-response markers correlated with periodontal disease

BACKGROUND: Periodontitis is the major cause of tooth loss in adults and is linked to systemic illnesses, such as cardiovascular disease and stroke. The development of rapid point-of-care (POC) chairside diagnostics has the potential for the early detection of periodontal infection and progression to identify incipient disease and reduce health care costs. However, validation of effective diagnostics requires the identification and verification of biomarkers correlated with disease progression. This clinical study sought to determine the ability of putative host- and microbially derived biomarkers to identify periodontal disease status from whole saliva and plaque biofilm. METHODS: One hundred human subjects were equally recruited into a healthy/gingivitis group or a periodontitis population. Whole saliva was collected from all subjects and analyzed using antibody arrays to measure the levels of multiple proinflammatory cytokines and bone resorptive/turnover markers. RESULTS: Salivary biomarker data were correlated to comprehensive clinical, radiographic, and microbial plaque biofilm levels measured by quantitative polymerase chain reaction (qPCR) for the generation of models for periodontal disease identification. Significantly elevated levels of matrix metalloproteinase (MMP)-8 and -9 were found in subjects with advanced periodontitis with Random Forest importance scores of 7.1 and 5.1, respectively. The generation of receiver operating characteristic curves demonstrated that permutations of salivary biomarkers and pathogen biofilm values augmented the prediction of disease category. Multiple combinations of salivary biomarkers (especially MMP-8 and -9 and osteoprotegerin) combined with red-complex anaerobic periodontal pathogens (such as Porphyromonas gingivalis or Treponema denticola) provided highly accurate predictions of periodontal disease category. Elevated salivary MMP-8 and T. denticola biofilm levels displayed robust combinatorial characteristics in predicting periodontal disease severity (area under the curve = 0.88; odds ratio = 24.6; 95% confidence interval: 5.2 to 116.5). CONCLUSIONS: Using qPCR and sensitive immunoassays, we identified host- and bacterially derived biomarkers correlated with periodontal disease. This approach offers significant potential for the discovery of biomarker signatures useful in the development of rapid POC chairside diagnostics for oral and systemic diseases. Studies are ongoing to apply this approach to the longitudinal predictions of disease activity.

Detection of a major gene for resistance to fusiform rust disease in loblolly pine by genomic mapping.

Genomic mapping has been used to identify a region of the host genome that determines resistance to fusiform rust disease in loblolly pine where no discrete, simply inherited resistance factors had been previously found by conventional genetic analysis over four decades. A resistance locus, behaving as a single dominant gene, was mapped by association with genetic markers, even though the disease phenotype deviated from the expected Mendelian ratio. The complexity of forest pathosystems and the limitations of genetic analysis, based solely on phenotype, had led to an assumption that effective long-term disease resistance in trees should be polygenic. However, our data show that effective long-term resistance can be obtained from a single qualitative resistance gene, despite the presence of virulence in the pathogen population. Therefore, disease resistance in this endemic coevolved forest pathosystem is not exclusively polygenic. Genomic mapping now provides a powerful tool for characterizing the genetic basis of host pathogen interactions in forest trees and other undomesticated, organisms, where conventional genetic analysis often is limited or not feasible.

Experimental studies on control of oak wilt disease /

Cover title.

Armillaria root disease /

Includes index.

A bibliography of the Dutch elm disease,

"A revised and expanded edition of a similar list mimeographed in February 1935."

Forest pest conditions in the Pacific Northwest.

Some issues have a distinctive title.

Forest pest conditions during ... in the Pacific Northwest /

Description based on: 1980.

Forest health conditions in Alaska.

Latest issue consulted: 2004.

Proceedings of the Symposium on Research and Management of Annosus Rood Disease (Heterobasidion annosum) in Western North America, April 18-21, 1989, Monterey, California /

Includes bibliographical references.

Unplanned land clearing of Colombian rainforests: Spreading like disease?

Deforestation often occurs as temporal waves and in localized fronts termed 'deforestation hotspots' driven by economic pulses and population pressure. Of particular concern for conservation planning are 'biodiversity hotspots' where high concentrations of endemic species undergo rapid loss and fragmentation of habitat. We investigate the deforestation process in Caqueta, a biodiversity hotspot and major colonization front of the Colombian Amazon using multi-temporal satellite imagery of the periods 1989-1996-1999-2002. The probabilities of deforestation and regeneration were modeled against soil fertility, accessibility and neighborhood terms, using logistic regression analysis. Deforestation and regeneration patterns and rates were highly variable across the colonization front. The regional average annual deforestation rate was 2.6%, but varied locally between -1.8% (regeneration) and 5.3%, with maximum rates in landscapes with 40-60% forest cover and highest edge densities, showing an analogous pattern to the spread of disease. Soil fertility and forest and secondary vegetation neighbors showed positive and significant relationships with the probability of deforestation. For forest regeneration, soil fertility had a significant negative effect while the other parameters were marginally significant. The logistic regression models across all periods showed a high level of discrimination power for both deforestation and forest regeneration, with ROC values > 0.80. We document the effect of policies and institutional changes on the land clearing process, such as the failed peace process between government and guerillas in 1999-2002, which redirected the spread of deforestation and increased forest regeneration. The implications for conservation in biologically rich areas, such as Caqueta are discussed. (c) 2005 Elsevier B.V All rights reserved.

High accuracy discrimination of Parkinson's disease participants from healthy controls using smartphones

The aim of this study is to accurately distinguish Parkinson's disease (PD) participants from healthy controls using self-administered tests of gait and postural sway. Using consumer-grade smartphones with in-built accelerometers, we objectively measure and quantify key movement severity symptoms of Parkinson's disease. Specifically, we record tri-axial accelerations, and extract a range of different features based on the time and frequency-domain properties of the acceleration time series. The features quantify key characteristics of the acceleration time series, and enhance the underlying differences in the gait and postural sway accelerations between PD participants and controls. Using a random forest classifier, we demonstrate an average sensitivity of 98.5% and average specificity of 97.5% in discriminating PD participants from controls. © 2014 IEEE.

Seven Ulmus minor clones tolerant to Ophiostoma novo-ulmi registered as forest reproductive material in Spain

The Spanish elm programme began in 1986 in response to the devastating impact of Dutch elm disease on natural elm stands and urban trees. Its main objectives were to conserve remaining genetic resources and select and breed tolerant native elm genotypes. After 27 years of work conducting susceptibility trials on thousands of elm genotypes, the first seven tolerant Ulmus minor trees are now being registered by the Spanish Environmental Administration. This paper presents the results of the susceptibility tests on these clones and their distinctive genetic, morphological and phenological features. In all susceptibility trials the commercial ?Sapporo Autumn Gold? clone, which is highly tolerant to O. novo-ulmi, was used as a control. The registered clones were named ?Ademuz?, ?Dehesa de la Villa?, ?Majadahonda?, ?Toledo?, ?Dehesa de Amaniel?, ?Retiro? and ?Fuente Umbría?. The most tolerant clone was ?Dehesa de Amaniel?, as its wilting values were below 5% during the two consecutive inoculation trials performed in Madrid. ?Fuente Umbría?, tested over four consecutive years in Guadalajara and Palencia, was the Spanish clone with the most reliable tolerance level to O. novo-ulmi. The ?Ademuz? and ?Majadahonda? clones had the highest ornamental scores and are promising trees for use in urban environments and tree breeding for ornamental quality. These two genotypes showed a later bud burst phenology than the other U. minor clones, demonstrating suitability to areas with late frost events. The Spanish programme aims to substantially increase the range of tolerant native elms through new selections and crossings to gain a better understanding of the genetic basis of resistance.

Beech bark disease distribution and resistance in Michigan and fungal endophyte ecology of resistant and susceptible beech (Fagus grandifolia Ehrh.)

Beech bark disease (BBD), a non-native association of the fungal pathogen Neonectria faginata and the beech scale insect Cryptococcus fagisuga, has dramatically affected American beech within North American forests. To monitor the spread and effects of BBD in Michigan, a network of forest health monitoring plots was established in 2001 following the disease discovery in Ludington State Park (Mason County). Forest health canopy condition and basic forestry measurements including basal area were reassessed on beech trees in these plots in 2011 and 2012. The influence of bark-inhabiting fungal endophytes on BBD resistance was investigated by collecting cambium tissue from apparently resistant and susceptible beech. Vigor rating showed significant influences of BBD in sample beech resulting in reduced health and substantiated by significant increases of dead beech basal area over time. C. fagisuga distribution was found to be spatially clustered and widespread in the 22 counties in Michigan's Lower Peninsula which contained monitoring plots. Neonectria has been found in Emmet, Cheboygan and Wexford in the Lower Peninsula which may coincide with additional BBD introduction locations. Surveys for BBD resistance resulted in five apparently resistant beech which were added to a BBD resistance database. The most frequently isolated endophytes from cambium tissue were identified by DNA sequencing primarily as Deuteromycetes and Ascomycetes including Chaetomium globosum, Neohendersonia kickxii and Fusarium flocciferum. N. faginata in antagonism trials showed significant growth reduction when paired with three beech fungal endophytes. The results of the antagonism trial and decay tests indicate that N. faginata may be a relatively poor competitor in vivo with limited ability to degrade cellulose.