Efficacy of three screening instruments in the identification of autistic-spectrum disorders

Background Screening instruments for autistic-spectrum disorders have not been compared in the same sample. Aims To compare the Social Communication Questionnaire (SCQ), the Social Responsiveness Scale (SRS) and the Children's Communication Checklist (CCC). Method Screen and diagnostic assessments on 119 children between 9 and 13 years of age with special educational needs with and without autistic-spectrum disorders were weighted to estimate screen characteristics for a realistic target population. Results The SCQ performed best (area under receiver operating characteristic curve (AUC)=0.90; sensitivity. 6; specificity 0.78). The SRS had a lower AUC (0.77) with high sensitivity (0.78) and moderate specificity (0.67). The CCC had a high sensitivity but lower specificity (AUC=0.79; sensitivity 0.93; specificity 0.46). The AUC of the SRS and CCC was lower for children with IQ < 70. Behaviour problems reduced specificity for all three instruments. Conclusions The SCQ, SRS and CCC showed strong to moderate ability to identify autistic-spectrum disorder in this at-risk sample of school-age children with special educational needs.

Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms

Objective: This paper presents a detailed study of fractal-based methods for texture characterization of mammographic mass lesions and architectural distortion. The purpose of this study is to explore the use of fractal and lacunarity analysis for the characterization and classification of both tumor lesions and normal breast parenchyma in mammography. Materials and methods: We conducted comparative evaluations of five popular fractal dimension estimation methods for the characterization of the texture of mass lesions and architectural distortion. We applied the concept of lacunarity to the description of the spatial distribution of the pixel intensities in mammographic images. These methods were tested with a set of 57 breast masses and 60 normal breast parenchyma (dataset1), and with another set of 19 architectural distortions and 41 normal breast parenchyma (dataset2). Support vector machines (SVM) were used as a pattern classification method for tumor classification. Results: Experimental results showed that the fractal dimension of region of interest (ROIs) depicting mass lesions and architectural distortion was statistically significantly lower than that of normal breast parenchyma for all five methods. Receiver operating characteristic (ROC) analysis showed that fractional Brownian motion (FBM) method generated the highest area under ROC curve (A z = 0.839 for dataset1, 0.828 for dataset2, respectively) among five methods for both datasets. Lacunarity analysis showed that the ROIs depicting mass lesions and architectural distortion had higher lacunarities than those of ROIs depicting normal breast parenchyma. The combination of FBM fractal dimension and lacunarity yielded the highest A z value (0.903 and 0.875, respectively) than those based on single feature alone for both given datasets. The application of the SVM improved the performance of the fractal-based features in differentiating tumor lesions from normal breast parenchyma by generating higher A z value. Conclusion: FBM texture model is the most appropriate model for characterizing mammographic images due to self-affinity assumption of the method being a better approximation. Lacunarity is an effective counterpart measure of the fractal dimension in texture feature extraction in mammographic images. The classification results obtained in this work suggest that the SVM is an effective method with great potential for classification in mammographic image analysis.

A kernel-based two-class classifier for imbalanced data sets

Many kernel classifier construction algorithms adopt classification accuracy as performance metrics in model evaluation. Moreover, equal weighting is often applied to each data sample in parameter estimation. These modeling practices often become problematic if the data sets are imbalanced. We present a kernel classifier construction algorithm using orthogonal forward selection (OFS) in order to optimize the model generalization for imbalanced two-class data sets. This kernel classifier identification algorithm is based on a new regularized orthogonal weighted least squares (ROWLS) estimator and the model selection criterion of maximal leave-one-out area under curve (LOO-AUC) of the receiver operating characteristics (ROCs). It is shown that, owing to the orthogonalization procedure, the LOO-AUC can be calculated via an analytic formula based on the new regularized orthogonal weighted least squares parameter estimator, without actually splitting the estimation data set. The proposed algorithm can achieve minimal computational expense via a set of forward recursive updating formula in searching model terms with maximal incremental LOO-AUC value. Numerical examples are used to demonstrate the efficacy of the algorithm.

Screening for convergence insufficiency using the CISS is not indicated in young adults

Aim This paper presents Convergence Insufficiency Symptom Survey (CISS) and orthoptic findings in a sample of typical young adults who considered themselves to have normal eyesight apart from weak spectacles. Methods The CISS questionnaire was administered,followed by a full orthoptic evaluation, to 167 university undergraduate and postgraduate students during the recruitment phase of another study. The primary criterion for recruitment to this study was that participants‘feltthey had normal eyesight'. A CISS score of ≥21 was used to define‘significant’symptoms, and convergence insufficiency (CI) was defined as convergence≥8cm from the nose with a fusion range <15Δ base-out with small or no exophoria. Results The group mean CISS score was 15.4. In all, 17(10%) of the participants were diagnosed with CI, but 11(65%) of these did not have significant symptoms. 41(25%) participants returned a‘high’CISS score of ≥21 but only 6 (15%) of these had genuine CI. Sensitivity of the CISS to detect CI in this asymptomatic sample was 38%; specificity 77%; positive predictive value 15%; and negative predictive value 92%. The area under a receiver operating characteristic curve was 0.596 (95% CI 0.46 to 0.73). Conclusions‘Visual symptoms’are common in young adults, but often not related to any clinical defect, while true CI may be asymptomatic. This study suggests that screening for CI is not indicated

Construction of neurofuzzy models for imbalanced data classification

We propose a new class of neurofuzzy construction algorithms with the aim of maximizing generalization capability specifically for imbalanced data classification problems based on leave-one-out (LOO) cross validation. The algorithms are in two stages, first an initial rule base is constructed based on estimating the Gaussian mixture model with analysis of variance decomposition from input data; the second stage carries out the joint weighted least squares parameter estimation and rule selection using orthogonal forward subspace selection (OFSS)procedure. We show how different LOO based rule selection criteria can be incorporated with OFSS, and advocate either maximizing the leave-one-out area under curve of the receiver operating characteristics, or maximizing the leave-one-out Fmeasure if the data sets exhibit imbalanced class distribution. Extensive comparative simulations illustrate the effectiveness of the proposed algorithms.

Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge

Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi-center data set. Using clinical practice as the starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimer's disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with a total of 29 algorithms. The algorithms were trained on a small training set (n = 30) and optionally on data from other sources (e.g., the Alzheimer's Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.

Resolution and discrimination - two sides of the same coin

The notions of resolution and discrimination of probability forecasts are revisited. It is argued that the common concept underlying both resolution and discrimination is the dependence (in the sense of probability theory) of forecasts and observations. More specifically, a forecast has no resolution if and only if it has no discrimination if and only if forecast and observation are stochastically independent. A statistical tests for independence is thus also a test for no resolution and, at the same time, for no discrimination. The resolution term in the decomposition of the logarithmic scoring rule, and the area under the Receiver Operating Characteristic will be investigated in this light.

Exploring the association of diary product intake with the fatty acids C15:0 and C17:0 measured from dried blood spots in a multi-population cohort: findings from the Food4Me study

Scope: The use of biomarkers in the objective assessment of dietary intake is a high priority in nutrition research. The aim of this study was to examine pentadecanoic acid (C15:0) and heptadecanoic acid (C17:0) as biomarkers of dairy foods intake. Methods and results: The data used in the present study were obtained as part of the Food4me Study. Estimates of C15:0 and C17:0 from dried blood spots and intakes of dairy from an FFQ were obtained from participants (n=1,180) across 7 countries. Regression analyses were used to explore associations of biomarkers with dairy intake levels and receiver operating characteristic (ROC) analyses were used to evaluate the fatty acids. Significant positive associations were found between C15:0 and total intakes of high-fat dairy products. C15:0 showed good ability to distinguish between low and high consumers of high-fat dairy products. Conclusion: C15:0 can be used as a biomarker of high-fat dairy intake and of specific high-fat dairy products. Both C15:0 and C17:0 performed poorly for total dairy intake highlighting the need for caution when using these in epidemiological studies.

Variable selection algorithm for the construction of MIMO operating point dependent neurofuzzy networks

An input variable selection procedure is introduced for the identification and construction of multi-input multi-output (MIMO) neurofuzzy operating point dependent models. The algorithm is an extension of a forward modified Gram-Schmidt orthogonal least squares procedure for a linear model structure which is modified to accommodate nonlinear system modeling by incorporating piecewise locally linear model fitting. The proposed input nodes selection procedure effectively tackles the problem of the curse of dimensionality associated with lattice-based modeling algorithms such as radial basis function neurofuzzy networks, enabling the resulting neurofuzzy operating point dependent model to be widely applied in control and estimation. Some numerical examples are given to demonstrate the effectiveness of the proposed construction algorithm.

Time diversity decorrelator (TDD); a near-far resistant detector for asynchronous CDMA system

Greater attention has been focused on the use of CDMA for future cellular mobile communications. CA near-far resistant detector for asynchronous code-division multiple-access (CDMA) systems operating in additive white Gaussian noise (AWGN) channels is presented. The multiuser interference caused by K users transmitting simultaneously, each with a specific signature sequence, is completely removed at the receiver. The complexity of this detector grows only linearly with the number of users, as compared to the optimum multiuser detector which requires exponential complexity in the number of users. A modified algorithm based on time diversity is described. It performs detection on a bit-by-bit basis and overcomes the complexity of using a sequence detector. The performance of this detector is shown to be superior to that of the conventional receiver.

Correcting for local oscillator phase offset in a DVB-T compliant receiver under multipath conditions

In 1997, the UK implemented the worlds first commercial digital terrestrial television system. Under the ETS 300 744 standard, the chosen modulation method, COFDM, is assumed to be multipath resilient. Previous work has shown that this is not necessarily the case. It has been shown that the local oscillator required for demodulation from intermediate-frequency to baseband must be very accurate. This paper shows that under multipath conditions, standard methods for obtaining local oscillator phase lock may not be adequate. This paper demonstrates a set of algorithms designed for use with a simple local oscillator circuit which will allow correction for local oscillator phase offset to maintain a low bit error rate with multipath present.