A hybrid knowledge and ensemble classification approach for prediction of venous thromboembolism

Clinical narratives such as progress summaries, lab reports, surgical reports, and other narrative texts contain key biomarkers about a patient's health. Evidence-based preventive medicine needs accurate semantic and sentiment analysis to extract and classify medical features as the input to appropriate machine learning classifiers. However, the traditional approach of using single classifiers is limited by the need for dimensionality reduction techniques, statistical feature correlation, a faster learning rate, and the lack of consideration of the semantic relations among features. Hence, extracting semantic and sentiment-based features from clinical text and combining multiple classifiers to create an ensemble intelligent system overcomes many limitations and provides a more robust prediction outcome. The selection of an appropriate approach and its interparameter dependency becomes key for the success of the ensemble method. This paper proposes a hybrid knowledge and ensemble learning framework for prediction of venous thromboembolism (VTE) diagnosis consisting of the following components: a VTE ontology, semantic extraction and sentiment assessment of risk factor framework, and an ensemble classifier. Therefore, a component-based analysis approach was adopted for evaluation using a data set of 250 clinical narratives where knowledge and ensemble achieved the following results with and without semantic extraction and sentiment assessment of risk factor, respectively: a precision of 81.8% and 62.9%, a recall of 81.8% and 57.6%, an F measure of 81.8% and 53.8%, and a receiving operating characteristic of 80.1% and 58.5% in identifying cases of VTE.     

Sensitive Mother-to-Adolescent Disclosures After Divorce: Is the Experience of Sons Different From That of Daughters?

This study addressed two main questions: (a) Are adolescent sons and daughters exposed to sensitive maternal disclosures after divorce with similar frequency and in similar detail? and (b) Does gender act as a moderator in the association between maternal disclosures and adolescent adjustment difficulties? Forced-choice and open-ended data were collected from 194 adolescents within 2 years after their parents' divorce. Quantitative analyses revealed that although the majority of adolescents experience some level of maternal disclosure, neither frequency nor detail of maternal disclosure differed as a function of adolescent gender. Frequent and detailed maternal disclosures were associated with adolescent adjustment difficulties, primarily psychological distress. Gender did not moderate that significant association. Qualitative analysis shed light on the link between maternal disclosures and adolescent distress, suggested the importance of how disclosures are made, and revealed several gender differences in reactions to maternal disclosures. Implications of the findings are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Social Support and Social Strain Among Husbands and Wives: A Multilevel Analysis.

In response to recent calls in the literature for within-person examinations of social support processes over time, this study explores the relationships of spousal support, spousal strain, and well-being among husbands and wives, both within the same day and across days. Eighty-three couples were interviewed and completed a structured diary twice daily for 1 week. The results of multilevel hierarchical modeling suggest that both spousal support and spousal strain made significant, independent contributions to concurrent negative affect, although only spousal support was a significant predictor of next-day negative affect. Spousal strain interacted with spousal support to predict next-day negative affect. Direct and moderating effects of perceived marital adjustment on negative affect were discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Providing information to clients about psychological tests: A survey of attorneys' and law students' attitudes.

Surveyed 70 practicing attorneys and 150 law students to determine the extent to which they felt it was their responsibility to inform clients they referred for psychological testing about the testing process and about the validity scales on tests. Results showed that almost 50% of the attorneys and over 33% of the students believe that clients referred for testing always or usually should be informed of validity scales on tests. These results suggest that many test takers, particularly in forensic settings, may have information about validity scales that facilitates their giving biased responses without detection. Psychologists doing forensic evaluations should be alert to this possibility and should consider using more than one approach to detect response distortions. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Fractal error for detecting man-made features in aerial images

A technique is proposed for aiding photointerpreters in detecting man-made features in aerial reconnaissance images. The technique, which uses a metric called fractal error, is based on the observed propensity of natural image features to fit a fractional Brownian motion model. Man-made features usually do not fit this model well, and consequently the fractal error metric may be used as a discriminant function for detecting man-made scene features     

Juvenile competence to stand trial evaluations: A survey of current practices and test usage among psychologists.

What is the current standard of practice for evaluations of juvenile competence to stand trial (JCST)? The present study surveyed psychologists regarding the practices used when conducting JCST evaluations. Respondents rated the importance of 17 elements that might be included in a JCST evaluation report. Of these elements, 7 were considered essential by 70% or more of respondents, with 9 additional elements rated as either essential or recommended. A majority of respondents felt that the use of psychological and forensic instruments was important. A list of tests used is provided, and the implications for the development of standards and policy are discussed to provide practitioners with additional knowledge that will help to further the state of the discipline. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Investigation of Arrhenius acceleration factor for integrated circuit early life failure region with several failure mechanisms

Use of the Arrhenius equation for analysis of burn-in and life test data has been called into question in recent years. Validity of the Arrhenius activation energy is asserted to be restricted to only one failure mechanism. Therefore, if multiple failure mechanisms apply to an integrated circuit type, the temperature acceleration factor must be complex. In this study a model is constructed using the Weibull distribution for the failure rate applicable when there are multiple failure mechanisms. In this model a different Arrhenius activation energy corresponds to each failure mechanism. It is shown that under conditions expected to be valid for most integrated circuits, an empirical effective Arrhenius activation energy can be computed that is valid for life test data taken under typical conditions to better than 10%. This provides some justification for the continued usage of a simple Arrhenius equation as an empirical model to analyze life test data.