Supporting content-based image retrieval and computer-aided diagnosis systems with association rule-based techniques

In this work, we take advantage of association rule mining to support two types of medical systems: the Content-based Image Retrieval (CBIR) systems and the Computer-Aided Diagnosis (CAD) systems. For content-based retrieval, association rules are employed to reduce the dimensionality of the feature vectors that represent the images and to improve the precision of the similarity queries. We refer to the association rule-based method to improve CBIR systems proposed here as Feature selection through Association Rules (FAR). To improve CAD systems, we propose the Image Diagnosis Enhancement through Association rules (IDEA) method. Association rules are employed to suggest a second opinion to the radiologist or a preliminary diagnosis of a new image. A second opinion automatically obtained can either accelerate the process of diagnosing or to strengthen a hypothesis, increasing the probability of a prescribed treatment be successful. Two new algorithms are proposed to support the IDEA method: to pre-process low-level features and to propose a preliminary diagnosis based on association rules. We performed several experiments to validate the proposed methods. The results indicate that association rules can be successfully applied to improve CBIR and CAD systems, empowering the arsenal of techniques to support medical image analysis in medical systems. (C) 2009 Elsevier B.V. All rights reserved.

Heart failure disease management program experience in 4,545 heart failure admissions to a community hospital

Background Disease management programs (DMPs) are developed to address the high morbi-mortality and costs of congestive heart failure (CHF). Most studies have focused on intensive programs in academic centers. Washington County Hospital (WCH) in Hagerstown, MD, the primary reference to a semirural county, established a CHF DMP in 2001 with standardized documentation of screening and participation. Linkage to electronic records and state vital statistics enabled examination of the CHF population including individuals participating and those ineligible for the program. Methods All WCH inpatients with CHF International Classification of Diseases, Ninth Revision code in any position of the hospital list discharged alive. Results Of 4,545 consecutive CHF admissions, only 10% enrolled and of those only 52.2% made a call. Enrollment in the program was related to: age (OR 0.64 per decade older, 95% CI 0.58-0.70), CHF as the main reason for admission (OR 3.58, 95% CI 2.4-4.8), previous admission for CHF (OR 1.14, 95% CI 1.09-1.2), and shorter hospital stay (OR 0.94 per day longer, 95% CI 0.87-0.99). Among DMP participants mortality rates were lowest in the first month (80/1000 person-years) and increased subsequently. The opposite mortality trend occurred in nonenrolled groups with mortality in the first month of 814 per 1000 person-years in refusers and even higher in ineligible (1569/1000 person-years). This difference remained significant after adjustment. Re-admission rates were lower among participants who called consistently (adjusted incidence rate ratio 0.62, 95% CI 0.52-0.77). Conclusion Only a small and highly select group participated in a low-intensity DMP for CHF in a community-based hospital. Design of DMPs should incorporate these strong selective factors to maximize program impact. (Am Heart J 2009; 15 8:459-66.)

An association rule-based method to support medical image diagnosis with efficiency

In this paper, we propose a method based on association rule-mining to enhance the diagnosis of medical images (mammograms). It combines low-level features automatically extracted from images and high-level knowledge from specialists to search for patterns. Our method analyzes medical images and automatically generates suggestions of diagnoses employing mining of association rules. The suggestions of diagnosis are used to accelerate the image analysis performed by specialists as well as to provide them an alternative to work on. The proposed method uses two new algorithms, PreSAGe and HiCARe. The PreSAGe algorithm combines, in a single step, feature selection and discretization, and reduces the mining complexity. Experiments performed on PreSAGe show that this algorithm is highly suitable to perform feature selection and discretization in medical images. HiCARe is a new associative classifier. The HiCARe algorithm has an important property that makes it unique: it assigns multiple keywords per image to suggest a diagnosis with high values of accuracy. Our method was applied to real datasets, and the results show high sensitivity (up to 95%) and accuracy (up to 92%), allowing us to claim that the use of association rules is a powerful means to assist in the diagnosing task.

MHM assay: molecular sexing based on the sex-specific methylation pattern of the MHM region in chickens

Bird sex determination using molecular methods has proved to be a valuable tool in different studies. Although it is possible to sex most birds by coupling the CHD assay with others available methods, no sex-determining gene like SRY in mammalians has been identified in birds. The male hypermethylated (MHM) region on the Z chromosome has been found to be hypermethylated in males and hypomethylated in females in birds of the order Galliformes. We analyzed the DNA from feathers of 50 adult chickens to verify the methylation pattern of the MHM region by PCR and the restriction enzyme HpaII (a method named MHM assay). The results, visualized in agarose gel, were compared with PCR amplification of the CHD-Z and CHD-W genes (polyacrylamide gel) and with the birds` phenotype. All males (25) showed hypermethylation of the MHM region, and all females (25) showed hypomethylation. The sexing by MHM assay was in according with phenotype and CHD sexing. To our knowledge, this is the first study that uses the MHM region for sexing birds. Although the real role of the MHM region in the sex determination is still unclear, this could be a universal marker for sexing birds and may be involved in sex determination by its influence on transcriptional processes. The MHM assay could be a good alternative for CHD assay in developmental studies.

Knowledge and practices of medical students to prevent tuberculosis transmission in Rio de Janeiro, Brazil

Objectives. To describe knowledge, practices, and associated factors of medical students to prevent transmission of tuberculosis (TB) in five medical schools. Methods. Cross-sectional survey of undergraduate medical students in preclinical and in early and late clinical years. Information was obtained on sociodemographic profile, previous lectures on TB, knowledge about TB transmission, exposure to patients with active pulmonary TB, and use of respiratory protective masks. Results. Among 1 094 respondents, 575 (52.6%) correctly answered that coughing, speaking, and sneezing can transmit TB. Early [adjusted odds ratio = 4.0 (3.0, 5.5)] and late [adjusted odds ratio = 4.2 (3.1, 5.8)] clinical years were associated with correct answers, but having had previous lectures on TB was not. Among those who had previous lectures on TB, the rate of correct answers increased from 42.1% to 61.6%. Among 332 medical students who reported exposure to TB patients, 194 (58.4%) had not used protective masks. More years of clinical experience was associated with the use of masks [adjusted odds ratio = 2.9 (1.4, 6.1)], while knowledge was inversely associated with the use of masks [adjusted odds ratio = 0.4 (0.2, 0.6)]. Conclusions. Many medical students are not aware of the main routes of TB infection, and lectures on TB are not sufficient to change knowledge and practices. Regardless of knowledge about TB transmission, students engage in risky behaviors: more than two-thirds do not use a protective mask when examining an active TB case. We suggest innovative, effective active learning experiences to change this scenario.

Stroke awareness in Brazil - Alarming results in a community-based study

Background and Purpose-Stroke is the leading cause of death in Brazil. This community-based study assessed lay knowledge about stroke recognition and treatment and risk factors for cerebrovascular diseases and activation of emergency medical services in Brazil. Methods-The study was conducted between July 2004 and December 2005. Subjects were selected from the urban population in transit about public places of 4 major Brazilian cities: S (a) over tildeo Paulo, Salvador, Fortaleza, and Ribeir (a) over tildeo Preto. Trained medical students, residents, and neurologists interviewed subjects using a structured, open-ended questionnaire in Portuguese based on a case presentation of a typical patient with acute stroke at home. Results-Eight hundred fourteen subjects were interviewed during the study period (53.9% women; mean age, 39.2 years; age range, 18 to 80 years). There were 28 different Portuguese terms to name stroke. Twenty-two percent did not recognize any warning signs of stroke. Only 34.6% of subjects answered the correct nationwide emergency telephone number in Brazil (# 192). Only 51.4% of subjects would call emergency medical services for a relative with symptoms of stroke. In a multivariate analysis, individuals with higher education called emergency medical services (P=0.038, OR=1.5, 95%, CI: 1.02 to 2.2) and knew at least one risk factor for stroke (P<0.05, OR=2.0, 95% CI: 1.2 to 3.2) more often than those with lower education. Conclusions-Our study discloses alarming lack of knowledge about activation of emergency medical services and availability of acute stroke treatment in Brazil. These findings have implications for public health initiatives in the treatment of stroke and other cardiovascular emergencies.