Empirical investigation of decision tree ensembles for monitoring cardiac complications of diabetes

Cardiac complications of diabetes require continuous monitoring since they may lead to increased morbidity or sudden death of patients. In order to monitor clinical complications of diabetes using wearable sensors, a small set of features have to be identified and effective algorithms for their processing need to be investigated. This article focuses on detecting and monitoring cardiac autonomic neuropathy (CAN) in diabetes patients. The authors investigate and compare the effectiveness of classifiers based on the following decision trees: ADTree, J48, NBTree, RandomTree, REPTree, and SimpleCart. The authors perform a thorough study comparing these decision trees as well as several decision tree ensembles created by applying the following ensemble methods: AdaBoost, Bagging, Dagging, Decorate, Grading, MultiBoost, Stacking, and two multi-level combinations of AdaBoost and MultiBoost with Bagging for the processing of data from diabetes patients for pervasive health monitoring of CAN. This paper concentrates on the particular task of applying decision tree ensembles for the detection and monitoring of cardiac autonomic neuropathy using these features. Experimental outcomes presented here show that the authors' application of the decision tree ensembles for the detection and monitoring of CAN in diabetes patients achieved better performance parameters compared with the results obtained previously in the literature.

An empirical investigation of hypersexuality

The aim of this study was to investigate the nature of hypersexuality and the personality factors associated with the desire for and experience of high frequency sexual behavior. Participants in the study were 69 male and 93 female university students. Respondents reported on their desire for and experience of masturbation, oral sex, sexual intercourse, pornography, indecent phone calls or letters, prostitution, exhibitionism, voyeurism, as well as providing self-report measures which evaluated their levels of state and trait anxiety, depression, obsessive and compulsive symptoms and fear of intimacy. The results demonstrated that subjects who engaged in high-frequency voyeurism were more depressed than low-frequency voyeurs. Respondents in the high-frequency sexual deviant desire and behavior groups appeared to have more obsessive-compulsive symptoms in comparison to the low-frequency deviant sexual behavior and desire groups. Increased psychopathology was not associated with high-frequency non-deviant sexual behaviors and desires. This finding raised the question of whether labels such as sexual compulsion and addiction are merely pathologizing illegal sexual behavior.

Measurement invariance across chronic conditions: a systematic review and an empirical investigation of the Health Education Impact Questionnaire (heiQ™).

To examine whether lack of measurement invariance (MI) influences mean comparisons among different disease groups, this paper provides (1) a systematic review of MI in generic constructs across chronic conditions and (2) an empirical analysis of MI in the Health Education Impact Questionnaire (heiQ™).

An empirical investigation of personality traits of software testers

Software testing is the process of an execution based investigation of some aspects of the software's quality. The efficiency of the process depends on the methods and technologies used, but crucially also on the human testers. Software testers typically attempt to anticipate and expose ways software may be defective, a fundamentally different task set to those of other software development practitioners. This raises the question of whether the personality of software testers may be different to other people involved in software development. To test this hypothesis, we collected personality profiles using the big five factor model of around 200 software development practitioners. Analysis of this data indicates that software testers are significantly higher on the conscientiousness factor than other software development practitioners, while other factors remain broadly consistent.

The impact of public capital and public investment on economic growth: an empirical investigation

in this anicle we measure the impact of public sector capital and investment on economic growth. Initially, traditional growth accounting regressions are run for a cross-country data set. A simple endogenous growth model is then constructed in order to take into account the determinants of labor, private capital and public capital. In both cases, public capital is a separate argument of the production function. An additional data-set constructed with quarterly American data was used in the estimations of the growth mode!. The results indicate lhat public capital and public investment play a significant role in determining growth rates and have a significant impact on capital and labor returns. Furthermore, the impact of public investment on productivity growth was found to be positive and always significant for bolh samples. Hence. in a fully optimizing modelo we confmn previous results in the literature that lhe failure of public investment to keep pace with output growlh during the Seventies and Eighties may have played a major role in the slowdown of lhe productivity growth in the period. Anolher main outcome concems the output elasticity wilh respect to public capital. The coefficiem estimates are always positive and significant but magnitudes depend on each of lhe two data set used.

Speak now or forever hold your peace: an empirical investigation of whistleblowing in Brazilian organizations

À medida que ajudam as organizações a prevenir condutas irregulares e a manter um ambiente de trabalho mais éticos, as denúncias (whistleblowing) são frequentemente apontadas pela literatura como um benefício à sociedade como um todo. Entretanto, pouco se sabe a respeito de muitos aspectos associados à decisão de denunciar uma irregularidade. No Brasil, em especial, onde o assunto permanece sendo negligenciado por pesquisadores, elementos culturais específicos podem obstruir o caminho da denuncia, além de impor restrições à generalização dos resultados de pesquisas anteriores, quase sempre voltadas para a realidade anglo-saxônica. Com base nesses pressupostos, este estudo busca identificar os antecedentes do whistleblowing interno nas organizações brasileiras. De modo geral, os resultados da pesquisa empírica realizada com uma ampla amostra de profissionais oriundos de empresas púbicas e privadas dão suporte ao modelo proposto e reforçam a noção de que o ato de denunciar é o resultado complexo da interação entre fatores da organização, do indivíduo da situação observada. Em particular, os resultados sugerem que os indivíduos são mais propensos a realizar a denúncia quando a irregularidade observada é percebida como grave e quando a própria denuncia é vista como um curso de ação ético. Por outro lado, os indivíduos podem optar pelo silêncio se o alvo da denúncia for alguém com alto status na organização, se eles não sentirem apoio da organização ou se temerem retaliações. A influência negativa do medo de retaliação sobre a intenção de denunciar, contudo, pode ser atenuada se o indivíduo está convencido de que o correto a fazer é denunciar. Por fim, os resultados também sugerem que profissionais em posição gerencial são mais propensos a denunciar irregularidades do que os demais membros de uma organização. As implicações desses resultados, bem como as limitações e contribuições do estudo para a teoria e para a prática são discutidas em detalhe, juntamente com sugestões para pesquisas futuras.

Medical Malpractice in Public Healthcare Systems: An Empirical Investigation of Scheduled Damages

In the last decades, medical malpractice has been framed as one of the most critical issues for healthcare providers and health policy, holding a central role on both the policy agenda and public debate. The Law and Economics literature has devoted much attention to medical malpractice and to the investigation of the impact of malpractice reforms. Nonetheless, some reforms have been much less empirically studied as in the case of schedules, and their effects remain highly debated. The present work seeks to contribute to the study of medical malpractice and of schedules of noneconomic damages in a civil law country with a public national health system, using Italy as case study. Besides considering schedules and exploiting a quasi-experimental setting, the novelty of our contribution consists in the inclusion of the performance of the judiciary (measured as courts’ civil backlog) in the empirical analysis. The empirical analysis is twofold. First, it investigates how limiting compensations for pain and suffering through schedules impacts on the malpractice insurance market in terms of presence of private insurers and of premiums applied. Second, it examines whether, and to what extent, healthcare providers react to the implementation of this policy in terms of both levels and composition of the medical treatments offered. Our findings show that the introduction of schedules increases the presence of insurers only in inefficient courts, while it does not produce significant effects on paid premiums. Judicial inefficiency is attractive to insurers for average values of schedules penetration of the market, with an increasing positive impact of inefficiency as the territorial coverage of schedules increases. Moreover, the implementation of schedules tends to reduce the use of defensive practices on the part of clinicians, but the magnitude of this impact is ultimately determined by the actual degree of backlog of the court implementing schedules.