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.

Acute stress reactions in the first 3 weeks postpartum: A study of 219 parturients

OBJECTIVES: There is increasing research on posttraumatic stress (PS) 4-6 weeks and 3 months postpartum, but, there are no data on acute stress reactions (ASR) in the first 3 weeks postpartum, i.e. the potential precursors of PS. However, ASR may have long-term effects, e.g., on a subsequent pregnancy without having manifested as PS in the meantime. We propose: (i) to describe the patterns of ASR after childbirth, (ii) to explore differences between women with normal and traumatogenic ASR, and (iii) to provide data on the early detection of traumatogenic ASR 2 and 3 weeks postpartum. STUDY DESIGN: Intra-event variables (relationship with caregivers, overall birth experience, and dissociative experiences, as well as obstetric variables) were assessed 48-96h. postpartum, as were ASR (by means of the Impact-of-Event Scale IES) in weeks 1, 2, and 3 postpartum. According to research on PS the upper 33%-range of ASR in weeks 2 and 3 was defined as 'traumatogenic'. RESULTS: Normal ASR in week 1 are at a level which in non-obstetric trauma-situations is considered as the upper range of low stress or lower range of medium distress. ASR decline constantly from week 1 to week 3. However, high ASR in week 1 do not drop faster than do low ones, thus indicating a prolonged stress reaction in women with high ASR in week 1. Low ASR (IES-scores <10) and high ASR (IES-scores >20) in week 1 are highly predictive for normal ASR, and traumatogenic ASR in weeks 2 and 3, respectively. Medium ASR (IES-scores 10-20) in week 1 are of uncertain predictive value for stress reactions in weeks 2 and 3 and have to be re-assessed at that time. CONCLUSIONS: Clinical screening for ASR appears to be helpful in detecting women with a compromised ability to process childbirth-related stress. The association between ASR and long-term development should be further explored.

[Precancerous and high risk lesions of the oral mucosa--Diagnosis, therapy and follow-up in two cases]

Stomatologic lesions at risk to develop an oral squamous cell carcinoma (OSCC) such as oral leukoplakia, erythroplakia/erythroleukoplakia, or oral lichen planus, need an early detection, diagnosis and a long-term/lifelong follow-up to prevent malignant transformation. In the following report, two patients are presented with oral mucosal lesions, who were referred, diagnosed, treated, and underwent follow-up examinations at the Stomatology Service of the Department of Oral Surgery and Stomatology at the University of Bern. These two cases emphasize the importance of early detection and managment of precancerous lesions or initial stages of OSCC. Additionally, risk factors, such as tobacco and alcohol consumption and their influence on stomatologic lesions and their prognosis, will be discussed.

Determination of caries risk at resin composite margins

PURPOSE: To design an artificial mouth in order to evaluate if a new diagnostic tool (Clinpro Cario Diagnosis) can be used for early detection of secondary caries at resin composite margins in vitro. METHODS: 32 intact human third molars received standardized Class-V resin composite restorations (Tetric Ceram bonded with Syntac SC). After storage for 4 weeks at 37 degrees C, teeth were subjected to 5,000 or 10,000 thermocycles (+/- 5 degrees C and +/- 55 degrees C) and polysiloxane impressions were taken. Streptococcus mutans 10449 (SM) was used in a nutrition medium to initiate a secondary caries process. Daily, the teeth were incubated for 2 x 2.5 hours in SM containing nutrition medium followed by 2 x 9.5 hours incubation in artificial saliva. Teeth were investigated after total incubation periods of 4, 6, and 8 weeks. After the different incubation protocols, the restoration margins were evaluated for infection and secondary caries processes in using Clinpro Cario Diagnosis which measures site-specifically the lactic acid production of SM in response to a sucrose challenge. The color signal was read 5 minutes after removal of the diagnostic impression. After thermocycling and biological load cycling, precision polysiloxane impressions were taken and replicas were investigated under a light microscope for gap widths at enamel and dentin margins. Demineralization was evaluated by fluorescence microscopy in using a special FITC filter. The demineralization depths at the cavity margin were calculated with Xpert for Windows using a pixel distance of 5 microm. RESULTS: After the different thermocycling protocols, no differences in gap widths and demineralization depths were found (P > 0.05). After SM incubation, gap widths and demineralization depths were significantly dependent on SM incubation time and previous number of thermocycles (P < 0.05). Lactic acid formations of SM were detectable by Clinpro Cario Diagnosis at dentin cavosurface margins formed after 6 weeks of incubation with SM (P < 0.05).

Radiological diagnosis of hepatocellular carcinoma

Treatment of hepatocellular carcinomas (HCC) is often complicated by the fact that early HCCs are mostly asymptomatic and the carcinoma is often discovered at an advanced stage. The aim of diagnostic imaging is to detect HCC at an early stage, when curative options are available. In recent years, there have been many efforts to improve early detection of small HCC. The purpose of this article is to describe the pertinent findings of HCCs in non-invasive, diagnostic imaging, including ultrasound, computed tomography, as well as modern magnetic resonance imaging techniques. Special emphasis is given to the frequently addressed difficulties of differentiation of precancerous lesions and small HCCs. A non-invasive diagnostic approach is considered with a review of the literature.

Invasion patterns of emerald ash borer and European earthworms in forested ecosystems

Invasive and exotic species present a serious threat to the health and sustainability of natural ecosystems. These species often benefit from anthropogenic activities that aid their introduction and dispersal. This dissertation focuses on invasion dynamics of the emerald ash borer, native to Asia, and European earthworms. These species have shown detrimental impacts in invaded forest ecosystems across the Great Lakes region, and continue to spread via human-assisted long distance dispersal and by natural modes of dispersal into interior forests from areas of introduction. Successful forest management requires that the impact and effect of invasive species be considered and incorporated into management plans. Understanding patterns and constraints of introduction, establishment, and spread will aid in this effort. To assist in efforts to locate introduction points of emerald ash borer, a multicriteria risk model was developed to predict the highest risk areas. Important parameters in the model were road proximity, land cover type, and campground proximity. The model correctly predicted 85% of known emerald ash borer invasion sites to be at high risk. The model’s predictions across northern Michigan can be used to focus and guide future monitoring efforts. Similar modeling efforts were applied to the prediction of European earthworm invasion in northern Michigan forests. Field sampling provided a means to improve upon modeling efforts for earthworms to create current and future predictions of earthworm invasion. Those sites with high soil pH and high basal area of earthworm preferred overstory species (such as basswood and maples) had the highest likelihood of European earthworm invasion. Expanding beyond Michigan into the Upper Great Lakes region, earthworm populations were sampled across six National Wildlife Refuges to identify potential correlates and deduce specific drivers and constraints of earthworm invasion. Earthworm communities across all refuges were influenced by patterns of anthropogenic activity both within refuges and in surrounding ecoregions of study. Forest composition, soil pH, soil organic matter, anthropogenic cover, and agriculture proximity also proved to be important drivers of earthworm abundance and community composition. While there are few management options to remove either emerald ash borer or European earthworms from forests after they have become well established, prevention and early detection are important and can be beneficial. An improved understanding the factors controlling the distribution and invasion patterns of exotic species across the landscape will aid efforts to determine their consequences and generate appropriate forest management solutions to sustain ecosystem health in the presence of these invaders.

Risk assessment for invasive exotic plants using multi-criteria risk models

Invasive exotic plants have altered natural ecosystems across much of North America. In the Midwest, the presence of invasive plants is increasing rapidly, causing changes in ecosystem patterns and processes. Early detection has become a key component in invasive plant management and in the detection of ecosystem change. Risk assessment through predictive modeling has been a useful resource for monitoring and assisting with treatment decisions for invasive plants. Predictive models were developed to assist with early detection of ten target invasive plants in the Great Lakes Network of the National Park Service and for garlic mustard throughout the Upper Peninsula of Michigan. These multi-criteria risk models utilize geographic information system (GIS) data to predict the areas at highest risk for three phases of invasion: introduction, establishment, and spread. An accuracy assessment of the models for the ten target plants in the Great Lakes Network showed an average overall accuracy of 86.3%. The model developed for garlic mustard in the Upper Peninsula resulted in an accuracy of 99.0%. Used as one of many resources, the risk maps created from the model outputs will assist with the detection of ecosystem change, the monitoring of plant invasions, and the management of invasive plants through prioritized control efforts.

[Diagnosis, treatment and follow up of prostata cancer]

Prostate cancer is the most frequent diagnosed malignancy in men with an increasing incidence. In well informed men between the age of 50 and 70 years screening should be offered when requested. Not every newly diagnosed prostate cancer requires immediate treatment. Curative treatment should be offered to men with a minimal life expectancy of 10 years. In men older than 50-75 years, therefore further screening is not necessary due to a lack of a therapeutic consequence. Curative treatment options enclose as the gold standard surgical removal, i.e. open radical prostatectomy with pelvic lymph node dissection, and radio-oncologic treatments, be it percutaneous radiation therapy, brachytherapies or a combination thereof. Palliative treatment options are mainly hormonal treatment (medical or surgical androgen deprivation), local radiation, treatment with bisphosphonates, chemotherapy and surgical desobstruction of the prostate. Regular follow up allows for early detection of recurrences and an active treatment concept.

Impact of low vision on well-being in 10 European countries

BACKGROUND: Because of the growing life expectancy in developed countries and the exponential increase in vision loss with increasing age, a growing number of elderly persons will eventually suffer from visual impairment and blindness. This paper describes the association between self-reported vision and well-being in individuals aged 50 years and older and their families. METHODS: Using binary logistic regressions on data from the 2004 Survey of Health, Ageing and Retirement in Europe (SHARE), we analysed the association between self-reported corrected vision in general, corrected distance vision and corrected reading vision on 11 variables capturing emotional well-being, future hopes and perspectives, and concentration on daily activities. RESULTS: For 22,486 individuals from 10 European countries, aged 64.23 +/- 10.52 years, lower vision was associated with a highly significant negative impact on all measured aspects of well-being. CONCLUSIONS: These data from a large population base in Europe provide evidence that persons with low vision have a higher probability of concentration problems during reading and entertainment; losing interest and enjoyment in their activities; feeling fatigued, irritable, sad, and tearful; having less hope for the future; and wishing for death. Effective measures of early detection, prevention, rehabilitation, education and research, as well as a holistic view of a patient, could help counter these problems, thereby improving mental and physical health and reducing the economic impact of low vision.

[Tumor surveillance after resection of colorectal cancer]

Because recurrent adenocarcinoma of the colon and rectum (CRC) can still be treated with acceptable 5-year survival rates, tumor surveillance plays an important role. Early detection of recurrent disease from CRC allows for effective treatment with intention for cure. This is why, in 2007, an interdisciplinary group modified the popular "FAGAS" criteria, a proposition for surveillance after curative resection of colorectal cancer. Proposed are the 3-monthly follow-up of the tumor marker CEA (carcino embryonic antigen), which, in case of lower sigmoid or rectal cancer, would be completed by rectosigmoidoscopy and endosonography every 6 months. As a major change liver sonography is now proposed to be replaced by annual thoraco-abdominal CT scan. Colonoscopy within the first year after resection has its place in the surveillance due to a high rate of metachronous secondary tumors missed in the initial endoscopy. Once completed it needs not to be repeated for at least 3 years. Only in cases where early stage CRC was been completely resected no schematic surveillance must take place.

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.

Limited predictive value of FDG-PET for response assessment in the preoperative treatment of esophageal cancer: results of a prospective multi-center trial (SAKK 75/02)

BACKGROUND: Only responding patients benefit from preoperative therapy for locally advanced esophageal carcinoma. Early detection of non-responders may avoid futile treatment and delayed surgery. PATIENTS AND METHODS: In a multi-center phase ll trial, patients with resectable, locally advanced esophageal carcinoma were treated with 2 cycles of induction chemotherapy followed by chemoradiotherapy (CRT) and surgery. Positron emission tomography with 2[fluorine-18]fluoro-2-deoxy-d-glucose (FDG-PET) was performed at baseline and after induction chemotherapy. The metabolic response was correlated with tumor regression grade (TRG). A decrease in FDG tumor uptake of less than 40% was prospectively hypothesized as a predictor for histopathological non-response (TRG > 2) after CRT. RESULTS: 45 patients were included. The median decrease in FDG tumor uptake after chemotherapy correlated well with TRG after completion of CRT (p = 0.021). For an individual patient, less than 40% decrease in FDG tumor uptake after induction chemotherapy predicted histopathological non-response after completion of CRT, with a sensitivity of 68% and a specificity of 52% (positive predictive value 58%, negative predictive value 63%). CONCLUSIONS: Metabolic response correlated with histopathology after preoperative therapy. However, FDG-PET did not predict non-response after induction chemotherapy with sufficient clinical accuracy to justify withdrawal of subsequent CRT and selection of patients to proceed directly to surgery.

Regular follow-up after curative resection of nonsmall cell lung cancer: a real benefit for patients?

Even though complete resection is regarded as the only curative treatment for nonsmall cell lung cancer (NSCLC), >50% of resected patients die from a recurrence or a second primary tumour of the lung within 5 yrs. It remains unclear, whether follow-up in these patients is cost-effective and whether it can improve the outcome due to early detection of recurrent tumour. The benefit of regular follow-up in a consecutive series of 563 patients, who had undergone potentially curative resection for NSCLC at the University Hospital, was analysed. The follow-up consisted of clinical visits and chest radiography according to a standard protocol for up to 10 yrs. Survival rates were estimated using the Kaplan-Meier analysis method and the cost-effectiveness of the follow-up programme was assessed. A total of 23 patients (6.4% of the group with lobectomy) underwent further operation with curative intent for a second pulmonary malignancy. The regular follow-up over a 10-yr period provided the chance for a second curative treatment to 3.8% of all patients. The calculated costs per life-yr gained were 90,000 Swiss Francs. The cost-effectiveness of the follow-up protocol was far above those of comparable large-scale surveillance programmes. Based on these data, the intensity and duration of the follow-up was reduced.

Community mean traits as additional indicators to monitor effects of land-use intensity on grassland plant diversity

Semi-natural grasslands, biodiversity hotspots in Central-Europe, suffer from the cessation of traditional land-use. Amount and intensity of these changes challenge current monitoring frameworks typically based on classic indicators such as selected target species or diversity indices. Indicators based on plant functional traits provide an interesting extension since they reflect ecological strategies at individual and ecological processes at community levels. They typically show convergent responses to gradients of land-use intensity over scales and regions, are more directly related to environmental drivers than diversity components themselves and enable detecting directional changes in whole community dynamics. However, probably due to their labor- and cost intensive assessment in the field, they have been rarely applied as indicators so far. Here we suggest overcoming these limitations by calculating indicators with plant traits derived from online accessible databases. Aiming to provide a minimal trait set to monitor effects of land-use intensification on plant diversity we investigated relationships between 12 community mean traits, 2 diversity indices and 6 predictors of land-use intensity within grassland communities of 3 different regions in Germany (part of the German ‘Biodiversity Exploratory’ research network). By standardization of traits and diversity measures, use of null models and linear mixed models we confirmed (i) strong links between functional community composition and plant diversity, (ii) that traits are closely related to land-use intensity, and (iii) that functional indicators are equally, or even more sensitive to land-use intensity than traditional diversity indices. The deduced trait set consisted of 5 traits, i.e., specific leaf area (SLA), leaf dry matter content (LDMC), seed release height, leaf distribution, and onset of flowering. These database derived traits enable the early detection of changes in community structure indicative for future diversity loss. As an addition to current monitoring measures they allow to better link environmental drivers to processes controlling community dynamics.

Gender differences in methods of suicide attempts and prevalence of previous suicide attempts

Objective: Suicide attempts are important predictors of completed suicide. Adolescents admitted to the emergency room of a large university hospital in Bern after a suicide attempt during the years 2004-2010 were prospectively assessed for methods of suicide attempt. Method: Adolescents (N = 257; 66.5% female; age 14-21 years), presenting after a suicide attempt, were assessed with the WHO/EURO Multicentre Study on Parasuicide assessment tool. Results: Males more often used jumping from a high place (14% vs. 4.6% in females, p < .05) and less often intoxication (36% vs. 71.3%, p < .01). At least one previous suicide attempt was reported in 100 patients (44.4%; more females than males: Cramer-V = 0.21; p = .002). Of these, 35 adolescents did not present to this hospital or not at all for a previous suicide attempt. Conclusions: The present study is the first to examine methods of suicide attempts according to the ICD-10 X codes in this age group. Gender differences were observed. Because a relevant number of patients did not present to the same hospital or not at all for a previous suicide attempt, studies on pathways to care of adolescents after their first suicide attempt are important for early detection and intervention strategies.