Points of interest and visual dictionaries for automatic retinal lesion detection.

In this paper, we present an algorithm to detect the presence of diabetic retinopathy (DR)-related lesions from fundus images based on a common analytical approach that is capable of identifying both red and bright lesions without requiring specific pre- or postprocessing. Our solution constructs a visual word dictionary representing points of interest (PoIs) located within regions marked by specialists that contain lesions associated with DR and classifies the fundus images based on the presence or absence of these PoIs as normal or DR-related pathology. The novelty of our approach is in locating DR lesions in the optic fundus images using visual words that combines feature information contained within the images in a framework easily extendible to different types of retinal lesions or pathologies and builds a specific projection space for each class of interest (e.g., white lesions such as exudates or normal regions) instead of a common dictionary for all classes. The visual words dictionary was applied to classifying bright and red lesions with classical cross validation and cross dataset validation to indicate the robustness of this approach. We obtained an area under the curve (AUC) of 95.3% for white lesion detection and an AUC of 93.3% for red lesion detection using fivefold cross validation and our own data consisting of 687 images of normal retinae, 245 images with bright lesions, 191 with red lesions, and 109 with signs of both bright and red lesions. For cross dataset analysis, the visual dictionary also achieves compelling results using our images as the training set and the RetiDB and Messidor images as test sets. In this case, the image classification resulted in an AUC of 88.1% when classifying the RetiDB dataset and in an AUC of 89.3% when classifying the Messidor dataset, both cases for bright lesion detection. The results indicate the potential for training with different acquisition images under different setup conditions with a high accuracy of referral based on the presence of either red or bright lesions or both. The robustness of the visual dictionary against image quality (blurring), resolution, and retinal background, makes it a strong candidate for DR screening of large, diverse communities with varying cameras and settings and levels of expertise for image capture.

Blood lead levels and growth status among African-American and Hispanic children in Dallas, Texas--1980 and 2002: Dallas Lead Project II.

OBJECTIVE: The purpose of this investigation is to analyze childhood blood lead levels and growth status (ages 2-12) in Dallas, Texas lead smelter communities in the 1980s and 2002, where smelters operated from 1936 to 1990. METHODS AND MATERIALS: A sample of convenience study design was used in two cohorts (n=360): 1980-1989 (n=191) and 2002 (n=169). Multivariate analysis of variance and covariance and tandem multiple regressions were used to evaluate the association between stature and blood lead level in two time periods. RESULTS: In 2002 average child blood lead level (1.6 microg/dL+/-0.2 SE) was significantly (p<0.001) lower compared to the 1980 cohort mean level (23.6 microg/dL+/-1.3 SE). Average height and weight in 2002 were 4.5 cm and 4.0 kg greater, respectively, than in 1980. Lowered blood lead level was associated with 3.9 cm, 3.5 kg and 1.1 units greater height, weight and body mass index (BMI), respectively. Cohort effect was associated with greater height (0.6 cm), weight (0.5 kg) and BMI (0.1). CONCLUSION: This investigation reports on child growth in a community before and after the transition from high to low blood lead levels over several decades. Using child growth as a proxy, health status of Dallas's lead smelter communities increased markedly over the past two decades, primarily because of lower blood lead levels, while the poverty rate was only marginally lower.

Security requirements for a lifelong electronic health record system: an opinion.

This article discusses the authors' views on the security requirements of a central, unique electronic health record. The requirements are based on the well-known principles of confidentiality and integrity and the less discussed principles of control and legal value. The article does not discuss any technical or legal solutions to the requirements proposed herein.

Decision support system for the diagnosis of schizophrenia disorders.

Clinical decision support systems are useful tools for assisting physicians to diagnose complex illnesses. Schizophrenia is a complex, heterogeneous and incapacitating mental disorder that should be detected as early as possible to avoid a most serious outcome. These artificial intelligence systems might be useful in the early detection of schizophrenia disorder. The objective of the present study was to describe the development of such a clinical decision support system for the diagnosis of schizophrenia spectrum disorders (SADDESQ). The development of this system is described in four stages: knowledge acquisition, knowledge organization, the development of a computer-assisted model, and the evaluation of the system's performance. The knowledge was extracted from an expert through open interviews. These interviews aimed to explore the expert's diagnostic decision-making process for the diagnosis of schizophrenia. A graph methodology was employed to identify the elements involved in the reasoning process. Knowledge was first organized and modeled by means of algorithms and then transferred to a computational model created by the covering approach. The performance assessment involved the comparison of the diagnoses of 38 clinical vignettes between an expert and the SADDESQ. The results showed a relatively low rate of misclassification (18-34%) and a good performance by SADDESQ in the diagnosis of schizophrenia, with an accuracy of 66-82%. The accuracy was higher when schizophreniform disorder was considered as the presence of schizophrenia disorder. Although these results are preliminary, the SADDESQ has exhibited a satisfactory performance, which needs to be further evaluated within a clinical setting.

Decision support system for the diagnosis of schizophrenia disorders

Clinical decision support systems are useful tools for assisting physicians to diagnose complex illnesses. Schizophrenia is a complex, heterogeneous and incapacitating mental disorder that should be detected as early as possible to avoid a most serious outcome. These artificial intelligence systems might be useful in the early detection of schizophrenia disorder. The objective of the present study was to describe the development of such a clinical decision support system for the diagnosis of schizophrenia spectrum disorders (SADDESQ). The development of this system is described in four stages: knowledge acquisition, knowledge organization, the development of a computer-assisted model, and the evaluation of the system's performance. The knowledge was extracted from an expert through open interviews. These interviews aimed to explore the expert's diagnostic decision-making process for the diagnosis of schizophrenia. A graph methodology was employed to identify the elements involved in the reasoning process. Knowledge was first organized and modeled by means of algorithms and then transferred to a computational model created by the covering approach. The performance assessment involved the comparison of the diagnoses of 38 clinical vignettes between an expert and the SADDESQ. The results showed a relatively low rate of misclassification (18-34%) and a good performance by SADDESQ in the diagnosis of schizophrenia, with an accuracy of 66-82%. The accuracy was higher when schizophreniform disorder was considered as the presence of schizophrenia disorder. Although these results are preliminary, the SADDESQ has exhibited a satisfactory performance, which needs to be further evaluated within a clinical setting.

Cooperative knowledge-making with female and male rural doctors.

INTRODUCTION: It is becoming increasingly difficult to engage rural doctors in survey-based research. Rural doctors in Australia are time-poor and overworked, yet it is vital that researchers find ways to engage them because they are the holders of information that is critical to effective workforce policy and planning. AIMS: To establish a cooperative research outcome with rural General Practitioners at a time when they were subject to many competing requests for contributions to various data gathering exercises. To develop and apply a knowledge-instrument for researching the practice of female doctors. METHOD: The research project began with the intention of locating a partially hidden voice, that of female rural GPs, and bringing it to the forefront. This grew out of 6 years' work with doctors which identified that women had their own relationship with rural practice and that this was not widely recognised in the professional and policy context. Each step of the research process was negotiated with the doctors to ensure that their solutions were the basis of the work, and their language was the vehicle of investigation. Dephi rounds were used to develop content for a national survey of rural GPs. Thirty-five female rural and remote GPs contributed to 3 Delphi rounds to construct the central section of the questionnaire. The work of the expert panel contributed the unique questions at the heart of a questionnaire that was sent to 2000 rural GPs in Rural Remote and Metropolitan Areas (RRMA) 4-7. The sample was stratified by RRMA and randomised for women, with a matching sample of men to provide a control group, test whether issues identified by women are relevant to men too, and allow a gender analysis. RESULTS: Sixty-three percent of the women returned usable surveys and 54% of the men. This was a comparatively high response rate, especially for a complex, 16 page questionnaire with 79 questions, administered at a time when rural doctors had become resistant to mail surveys. Fifty-six doctors commented on the questionnaire itself, most of them appreciating the topics raised. CONCLUSION: It was possible to develop a cooperative relationship with rural doctors that resulted in high rates of participation in the research, particularly from women. What women do can be researched and included in knowledge about rural practice, and men will respond to female-designed data collection instruments. Careful attention to questions of voice, presentation, communication and purpose can assist in bringing the experience of women as well as men into the research frame.

Sustainable rural practice for female general practitioners.

An expert panel of female rural and remote doctors have nominated updating professional skills as the most important strategy for sustainable rural general practice for women. The panel was comprised of members of the Australian College of Rural and Remote Medicine (ACRRM). The panel was asked to identify and prioritise strategies they had used to make rural practice work for them. They identified and ranked the following eight groups of strategies: (i) structure medical practice to work for you; (ii) implement personal strategies; (iii) obtain and update professional skills; (iv) establish professional and personal boundaries; (v) gain exposure to rural practice; (vi) engage with the community; (vii) implement professional strategies; and (viii) engage with women. Detailed strategies within these groups have been identified and will form the basis of grounded knowledge about how to structure rural and remote practice to work for women. This will complement the work of ACRRM, the Rural Doctors Association and workforce agencies in developing models of sustainable rural medical practice.

Rural mental health: neither romanticism nor despair.

This paper explores the relationship between rural places and mental health. It begins with a definition of mental health and an outline of the data that have led to the current concern with promoting positive mental health. We then consider aspects of rural life and place that contribute to positive mental health or increase the likelihood of mental health problems. Issues identified include environment, place, gender identity, violence and dispossession and the influence of the effects of structural changes in rural communities. The paper concludes with a discussion of some of the determinants of resilience in rural places, including social connectedness, valuing diversity and economic participation.

The human proteinase-activated receptor-3 (PAR-3) gene. Identification within a Par gene cluster and characterization in vascular endothelial cells and platelets.

Proteolytically activated receptors (PARs) represent an emerging subset of seven transmembrane G protein-coupled receptors that mediate cell activation events by receptor cleavage at distinct scissile bonds located within receptor amino termini. Differential genomic blotting using a yeast artificial chromosome known to contain the PAR-1 and PAR-2 genes identified the PAR-3 gene within a PAR gene cluster spanning approximately 100 kilobases at 5q13. The PAR-3 gene is relatively small (approximately 12 kilobases); and, like the PAR-1 and PAR-2 genes, it displays a two-exon structure, with the majority of the coding sequence and the proteolytic cleavage site contained within the larger second exon. Sequence analysis of the 5'-flanking region demonstrates that the promoter is TATA-less, similar to that seen with PAR-1, with the identification of nucleic acid motifs potentially involved in transcriptional gene regulation, including AP-1, GATA, and octameric sequences. PAR-3 transcripts were apparent in human vascular endothelial cells, although at considerably lower levels than those of PAR-1 and not significantly modulated by the endothelial cell stimulus tumor necrosis factor-alpha. Likewise, although PAR-3 mRNA was evident in human platelets, receptor cell surface expression was modest (approximately 10%) compared with that of PAR-1. Thus, although PAR-3 is postulated to represent a second thrombin receptor, its modest endothelial cell and platelet expression suggest that PAR-3 activation by alpha-thrombin is less relevant for physiological responses in these mature cells. Rather, given its disparately greater expression in megakaryocytes (and megakaryocyte-like human erythroleukemia cells), a regulatory role in cellular development (by protease activation) could be postulated.

A temporal extension to the parsimonious covering theory.

In this paper, parsimonious covering theory is extended in such a way that temporal knowledge can be accommodated. In addition to causally associating possible manifestations with disorders, temporal relationships about duration and the time elapsed before a manifestation comes into existence can be represented by a graph. Precise definitions of the solution of a temporal diagnostic problem as well as algorithms to compute the solutions are provided. The medical suitability of the extended parsimonious cover theory is studied in the domain of food-borne disease.

Ahead with Cairo. Monitoring country activities.

PIP: In the aftermath of the 1994 UN Conference on Population and Development (ICPD) in Cairo, countries are proceeding with their implementation of the plan of action adopted at the conference. A brief description is given of some actions taken by specific countries toward plan implementation. In the Philippines meetings were held immediately after the conference in October on the implications for the Management, Family Planning, and Nongovernmental Organizations programs. The issues of concern were identified as the need for regular consultative meetings among relevant agencies, consultations with women's groups, and a responsive adolescents program. In Australia the program thrust was to focus on the implications for immigration. Monitoring of the plans of action will be undertaken by nongovernmental organizations (NGOs). In Malaysia committees are preparing a program of action suitable for implementation in Malaysia. A regional women's NGO organized a forum on the implications of ICPD for women's reproductive health, women's rights, and empowerment in Malaysia. In Vietnam, press conferences are used to communicate conference results. An NGO translated relevant ICPD materials into Vietnamese. In Indonesia, several ministries convened meetings among donors, NGOs, women's groups, and experts. In India, the government held a national conference. One view was that population issues should be discussed in the context of gender equality and empowerment of women. Another issue was the importance of placing reproductive health in the larger context of health and primary health services. Health personnel at all levels were considered in need of sensitization on gender issues. Problems such as anemia have not been successfully addressed in existing programs. The government agreed to remove in phases target driven programs and the sterilization emphasis. In Bangladesh, a national committee was formed, and NGOs are actively distributing information. In Japan, the Family Planning Federation in a collaborative effort is actively promoting concrete actions.^ieng

Examination of irreversible platelet-fibrinogen interactions.

The progressive stabilization of fibrinogen binding to ADP-treated platelets has been well described, but the nature of this interaction remains obscure. In the present study, irreversibly bound fibrinogen was defined as that fraction of bound iodinated fibrinogen that failed to dissociate from stimulated human gel-filtered platelets within 10 min of adding 10 mM ethylenediaminetetraacetic acid. It represented 16 +/- 11% (mean +/- SD, n = 10) of fibrinogen bound to ADP-treated platelets after 1 min and 52 +/- 11% of fibrinogen bound to these platelets after 60 min. Similar results were obtained if platelets were stimulated with purified human thrombin (0.1 U/ml) or epinephrine (10 microM). Irreversible fibrinogen binding was significantly reduced at 4 degrees C (27 +/- 9%, mean +/- SD, n = 6) if platelets were preincubated (30 min, 25 degrees C) with 30 micrograms/ml cytochalasin B or D (18 +/- 8%) or stimulated with chymotrypsin (0.5 mg/2-3 X 10(8) platelets) (31 +/- 8%). Formation of irreversible platelet-fibrinogen interactions correlated with the incorporation of actin and actin-binding protein into the Triton X-100-insoluble platelet cytoskeleton and the ability of platelets to retract fibrin clots. Irreversibly bound fibrinogen was available on platelets for digestion by 0.2 U/ml plasmin. The enzyme removed 96 +/- 6% (mean +/- SD, n = 6) of all bound fibrinogen from platelets after 30 min at 25 degrees C. This was not accompanied by significant release of [14C]serotonin or lactate dehydrogenase. Furthermore, platelets incubated with plasmin could bind fibrinogen normally after the enzyme had been neutralized with aprotinin.(ABSTRACT TRUNCATED AT 250 WORDS)

Why women don't use contraception.

PIP: Subjective and objective factors relating to why women do not use and continue to use contraception are examined. The information presented is based on 2 samples of women: 1736 women who presented at the Fertility Control Clinic (Australia) between July 1973 and February 1974; and 233 women who came to the Clinic in July and August 1974. The information about each woman includes social factors such as age, marital status, religion, education, occupation and place of residence, contraceptive history, reason for seeking abortion, information about sexual experience, and an assessment of why the woman was not using effective contraception. Culturally conditioned feelings of guilt about sexual activity and the belief that adults condemn pre-marital sex makes it very difficult for a young woman to get up the courage to request contraception. A total of 12% of 1 Clinic sample were either too afraid to see a doctor for contraception or did see a doctor and were refused contraception. A very significant factor preventing good contraceptive use at the beginning of sexual experience is the unplanned nature of the experience. 75% of the teenagers in the 1st sample failed to initiate adequate contraception because they were poorly informed, unsure of their sexual role, or deterred by their doctor. Ignorance of the need for contraception and the methods available is clearly an objective inhibition to their use, but the reason for the ignorance may be bound up with subjective factors such as guilt about sex and subsequent ambivalence toward learning about it. Reasons for failure to continue to use contraception include the following: for some, the risk of producing an unwanted pregnancy adds flavor to the sexual act; some women rationalize their sexual activity, and this usually leads to discontinuation of contraceptive use; failure to change the contraceptive when needs change; the need to prove fertility; fear of adverse side-effects; failure to anticipate coitus; prohibition of the prescription of contraceptives in new residential area; and incorrect information. Available evidence supports the proposition that making the facilities available will greatly reduce the incidence of poor or neglected contraception.^ieng