Data-driven decision making for the screening of cognitive impairment in primary care: a machine learning approach using data from the ELSA-Brasil study.

The systematic assessment of cognitive performance of older people without cognitive complaints is controversial and unfeasible. Identifying individuals at higher risk of cognitive impairment could optimize resource allocation. We aimed to develop and test machine learning models to predict cognitive impairment using variables obtainable in primary care settings. In this cross-sectional study, we included 8,291 participants of the baseline assessment of the ELSA-Brasil study, who were aged between 50 and 74 years and were free of dementia. Cognitive performance was assessed with a neuropsychological battery and cognitive impairment was defined as global cognitive z-score below 2 standard deviations. Variables used as input to the prediction models included demographics, social determinants, clinical conditions, family history, lifestyle, and laboratory tests. We developed machine learning models using logistic regression, neural networks, and gradient boosted trees. Participants' mean age was 58.3±6.2 years, 55% were female. Cognitive impairment was present in 328 individuals (4%). Machine learning algorithms presented fair to good discrimination (areas under the ROC curve between 0.801 and 0.873). Extreme Gradient Boosting presented the highest discrimination, high specificity (97%), and negative predictive value (97%). Seventy-six percent of the individuals with cognitive impairment were included among the highest ranked individuals by this algorithm. In conclusion, we developed and tested a machine learning model to predict cognitive impairment based on primary care data that presented good discrimination and high specificity. These characteristics could support the detection of patients who would not benefit from cognitive assessment, facilitating the allocation of human and economic resources.

Data-driven decision making for the screening of cognitive impairment in primary care: a machine learning approach using data from the ELSA-Brasil study

The systematic assessment of cognitive performance of older people without cognitive complaints is controversial and unfeasible. Identifying individuals at higher risk of cognitive impairment could optimize resource allocation. We aimed to develop and test machine learning models to predict cognitive impairment using variables obtainable in primary care settings. In this cross-sectional study, we included 8,291 participants of the baseline assessment of the ELSA-Brasil study, who were aged between 50 and 74 years and were free of dementia. Cognitive performance was assessed with a neuropsychological battery and cognitive impairment was defined as global cognitive z-score below 2 standard deviations. Variables used as input to the prediction models included demographics, social determinants, clinical conditions, family history, lifestyle, and laboratory tests. We developed machine learning models using logistic regression, neural networks, and gradient boosted trees. Participants' mean age was 58.3±6.2 years, 55% were female. Cognitive impairment was present in 328 individuals (4%). Machine learning algorithms presented fair to good discrimination (areas under the ROC curve between 0.801 and 0.873). Extreme Gradient Boosting presented the highest discrimination, high specificity (97%), and negative predictive value (97%). Seventy-six percent of the individuals with cognitive impairment were included among the highest ranked individuals by this algorithm. In conclusion, we developed and tested a machine learning model to predict cognitive impairment based on primary care data that presented good discrimination and high specificity. These characteristics could support the detection of patients who would not benefit from cognitive assessment, facilitating the allocation of human and economic resources.

Machine learning for predicting chronic diseases: a systematic review.

OBJECTIVES: We aimed to review the literature regarding the use of machine learning to predict chronic diseases. STUDY DESIGN: This was a systematic review. METHODS: The searches included five databases. We included studies that evaluated the prediction of chronic diseases using machine learning models and reported the area under the receiver operating characteristic curve values. The Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis scale was used to assess the quality of studies. RESULTS: In total, 42 studies were selected. The best reported area under the receiver operating characteristic curve value was 1, whereas the worst was 0.74. K-nearest neighbors, Naive Bayes, deep neural networks, and random forest were the machine learning models most frequently used for achieving the best performance. CONCLUSION: We found that machine learning can predict the occurrence of individual chronic diseases, progression, and their determinants and in many contexts. The findings are original and relevant to improve clinical decisions and the organization of health care facilities.

Income inequality and self-reported health in a representative sample of 27 017 residents of state capitals of Brazil.

Background: The association between income inequality and health has been analyzed predominantly in developed countries with modest levels of inequality. The study aimed to analyze the association between income inequality and self-reported health (SRH) in the adult population of the 27 Brazilian capitals. Methods: Individuals aged 18 years or older from the National Health survey residing in Brazilian capitals in 2013 were analyzed (n = 27 017). Bayesian multilevel models were applied after controlling for individual factors and area-level socioeconomic characteristics. Results: We found a significant association between income inequality and SRH, even after controlling for individual and contextual factors. The results indicate greater odds of poor SRH among those living in areas with medium (OR = 1.31, 95% CI: 1.17-1.47) and high income inequality level (OR = 1.39, 95% CI: 1.24-1.56). Income inequality remained significantly associated with SRH, even after controlling for other contextual socioeconomic characteristics, such as local illiteracy rate, violence and per capita income. Conclusions: The study highlights the importance of the individual and contextual characteristics associated with SRH. Our findings suggest that city-level income inequality can have a detrimental effect on individual health, over and above other contextual socioeconomic characteristics and individual factors.

Angiografia dos dígitos de bovinos jovens antes e após indução de acidose ruminal / Digital angiography in young cattle before and after ruminal acidosis induction

O presente estudo objetivou descrever a rede vascular dos dígitos dos membros pélvicos de bovinos antes e após aplicação intrarruminal de oligofrutose, empregando a venografia. Utilizaram-se seis bovinos alocados em dois grupos (GI e GII), que receberam 13 e 17g/kg de oligofrutose, respectivamente. A venografia dos dígitos foi feita em quatro momentos: 15 dias antes (M0) e 36 horas (M1), sete dias (M2) e 30 dias (M3) após aplicação de oligofrutose. Mensurou-se a largura das veias visualizadas e avaliou-se possível supressão do fluxo sanguíneo dos vasos. A largura foi avaliada pela análise de variância (ANOVA) e pelo teste t (5%). Em M0, nas radiografias, foram identificadas 25 estruturas, incluindo veias, artérias e rede vascular. As veias mensuradas foram: digital dorsal comum III e dorsal da falange distal e os ramos plantares para o coxim digital do dígito lateral e medial. Apenas a v. digital dorsal comum III apresentou maior largura após 36 horas e constrição com 30 dias (P≤0,05) da aplicação de oligofrutose. Comparando-se os momentos, encontrou-se vasodilatação no M1 e vasoconstrição nos demais. A mensuração da largura dos vasos não sofreu (P≥0,05) interferência quando se compararam os grupos. Concluiu-se que a venografia dos dígitos de bovinos permite estudar e identificar alterações da vascularização.(AU)

The objective of this study was to describe vascular net of bovine digit before and after intrarruminal administration of oligofructose, with the use of venography. Six animals sorted in two groups (GI and GII) that received 13 and 17g/kg of oligofructose respectively were used. Digits venography were done in four moments: 15 days before (M0) and 36 hours (M1), seven days (M2) and 30 days (M3) after administration of oligofructose. Width of visualized veins and evaluated possible blood flow vessels suppression was measured. The width was evaluated by ANOVA and T test (5%). In M0 25 structures were identified, including veins, arteries and vascular net in radiographic images. Veins measured were: common digital III and dorsal of distal phalanx and plantar branches to digital cushion of lateral and medial digits. Only V. digital dorsal common III presented higher width after 36 hours and constriction with 30 days (P≤0.05) of oligofructose administration. Comparing moments, vessel dilation on M1 and constriction on other moments. Measurement of vessel width didn´t suffer interference when groups were compared. Venography of bovine digits allowed for the study and identification of changes in vascularization.(AU)

Patterns and predictors of health service use among people with mental disorders in São Paulo metropolitan area, Brazil.

AIMS: Important transformations in psychiatric healthcare (HC) delivery have been implemented in Latin America during the beginning of 21st century. However, information on current service uses patterns is scant, obstructing the estimates and proper planning of service needs for general population. The current investigation aims to describe patterns and estimates predictors of 12-month HC use by individuals with mental disorders in São Paulo metropolitan area, Brazil. METHOD: Data are from São Paulo Mental Health Survey, a cross-sectional multistage representative study. Participants were face-to-face interviewed in their household, using a structured diagnostic interview, the World Mental Health Survey Initiative version of the Composite International Diagnostic Interview. A total of 5037 respondents, non-institutionalised, aged 18 years and older were interviewed. The response rate was 81.3%. We determined the percentages of individuals with 12-month DSM-IV anxiety, mood and substance disorders that received treatment in the 12 months prior to assessment in main service sectors (specialty mental health, general medicine, human services (HS), and complementary and alternative medicine). The number of visits and percentage of individuals who received treatment at minimally adequacy also was estimated. Multilevel regression controlled contextual variables that influenced the use of service and treatment adequacy. RESULTS: Only 10.1% of respondents used some HC service in the 12 months prior to assessment for their psychiatric problems, including 3.9% of them being treated either by a psychiatrist, 3.5% by a non-psychiatrist mental health specialist, 3.3% by a general medical (GM) provider, 1.5% by a HS provider and 1.4% by a complementary and alternative medical provider. In general, those participants who received service in the mental health specialty sector reported more visits than those in the GM sector (median 3.9 v. 1.5 visits). The cases seen in specialty sector outnumber those visiting GM treatment in terms of minimally adequate treatment (54.6 v. 23.2%). The likelihood of receiving treatment was significantly greater among individuals diagnosed with any anxiety and mood disorder, presenting more severe disorders, and with possession of HC insurance. CONCLUSIONS: The great majority of individuals with an active mental disorder in São Paulo were either untreated or insufficiently treated. Awareness and training programmes to GM professionals are advocated to improve recognition, care take and referral to specialty care when needed. Proper integration among HC sectors is recommended.

Can we document the practice of dispensing? A systematic review.

WHAT IS KNOWN: Documentation is a process indicator utilized to evaluate quality clinical pharmacist services. In this framework, documentation of dispensing, besides supporting patient care, allows evaluation of the impact of counselling. OBJECTIVE: To identify and assess studies of documentation by pharmacists in the dispensing process. METHOD: A systematic review was carried out according to the following steps: (i) identification of studies in the following databases: PubMed/Medline, Web of Science, Scopus and Lilacs, using the descriptors 'counselling', 'dispensing', 'community pharmacy services', 'pharmacies' and 'pharmacists' in different combinations; (ii) evaluation of studies, in which the title, abstract and full text of the studies, and the evaluation of the methodological quality of the selected studies were analysed. RESULTS: In total, 26 articles met the specific criteria. Few studies addressed documentation as part of the dispensing working process (3), and 16 articles reported documentation using non-electronic systems. The main variables documented were patient information, drug therapy problems and clinical interventions. Furthermore, 20 studies showed the effects of documentation in the dispensing process and 23 studies included statistical evidence. Eight articles met between 42% and 75% of the 28 items recommended by the STROBE initiative, and two articles met approximately 60% of the 36 items recommended by the CONSORT initiative. WHAT IS NEW AND CONCLUSION: Few studies address documentation as part of the dispensing working process. Thus, researchers should be concerned with standardizing documentation and implementing more robust designs and multicenter studies.

Latin American Study of Nutrition and Health (ELANS): rationale and study design.

BACKGROUND: Obesity is growing at an alarming rate in Latin America. Lifestyle behaviours such as physical activity and dietary intake have been largely associated with obesity in many countries; however studies that combine nutrition and physical activity assessment in representative samples of Latin American countries are lacking. The aim of this study is to present the design rationale of the Latin American Study of Nutrition and Health/Estudio Latinoamericano de Nutrición y Salud (ELANS) with a particular focus on its quality control procedures and recruitment processes. METHODS/DESIGN: The ELANS is a multicenter cross-sectional nutrition and health surveillance study of a nationally representative sample of urban populations from eight Latin American countries (Argentina, Brazil, Chile, Colombia, Costa Rica, Ecuador, Perú and Venezuela). A standard study protocol was designed to evaluate the nutritional intakes, physical activity levels, and anthropometric measurements of 9000 enrolled participants. The study was based on a complex, multistage sample design and the sample was stratified by gender, age (15 to 65 years old) and socioeconomic level. A small-scale pilot study was performed in each country to test the procedures and tools. DISCUSSION: This study will provide valuable information and a unique dataset regarding Latin America that will enable cross-country comparisons of nutritional statuses that focus on energy and macro- and micronutrient intakes, food patterns, and energy expenditure. TRIAL REGISTRATION: Clinical Trials NCT02226627.

Analysis of the quality of prescriptions at a cardiovascular ward in Brazil: a pilot study.

AIM OF STUDY: To analyze the quality of prescriptions in a hospital in Brazil. METHODS: A cross-sectional pilot study of the quality of prescriptions of adult patients admitted at the cardiovascular ward. Data were collected with the help of a structured form developed by the researchers based on related literature, with items about medications and completeness of prescriptions. The form was divided into four categories of prescription quality indicators: prescription type, legibility and readability of handwriting, and completeness. MAIN OUTCOME MEASURES 100 patients participated in the study, with ages between 20 and 94 years (mean of 67.12 ± 16.6 years), We analyzed 5,030 on 496 prescriptions for 100 patients. Of 11% the handwriting was considered to be less legible and 17% considered illegible. In terms of readability, a high incidence of medications were prescribed by their brand names (89%), and 13,707 abbreviations (mean of 27.6 per prescription) were used mainly to refer to the route of administration (31%), concentration (27%), and indications for use (20%). In relation to completeness, 471 (95%) prescriptions were considered incomplete, mainly medication data. CONCLUSION: The quality indicators used in this study revealed a high rate of prescription problems and errors.

O beijo como mobilizador para educação em saúde: ênfase na saúde bucal de adolescentes; relatos de uma experiência / The kiss as a mobilizer for health education: emphasis in bucal health of adolescents; an experience report

Resumo: Este trabalho relata a experiência de um grupo de profissionais das equipes de saúde da família que, por meio da Metodologia da Problematização, usaram "o beijo" como tema mobilizador para educação em saúde bucal, com adolescentes da oitava série do primeiro grau das escolas públicas da Regional Bairro Novo em Curitiba no período de 1999 a 2001. Os adolescentes participaram ativamente da construção do problema, levantando dúvidas, discutindo possíveis soluções, expressando desejos, interesses, relacionando a saúde bucal com suas experiências afetivas e sexuais. A estratégia utilizada mostrou-se efetiva, criando um clima de confiança entre a equipe e os adolescentes, tornando-se uma experiência satisfatória e motivadora no campo da educação em saúde bucal.

Evolution of nutritional status of infants infected with the human immunodeficiency virus.

CONTEXT: There are today only a limited number of studies defining growth parameters and nutritional status for HIV children. OBJECTIVE: To study the nutritional status of infants infected with the human immunodeficiency virus. TYPE OF STUDY: Longitudinal study. SETTING: Department of Pediatrics, Faculty of Medical Sciences, UNICAMP, Campinas, Brazil. PARTICIPANTS: One hundred and twenty-four children born to HIV infected mothers were evaluated from birth until the age of two years. They were subdivided into two groups: 71 infected children and 53 non-infected children. MAIN MEASUREMENTS: Growth was evaluated in both groups by comparing Z-scores for weight/age (w/a), length/age (H/a) and weight/length (w/H) (using the NCHS curves as reference). RESULTS: The Z-score analyses showed that there was a significant difference between the two groups for all the variables studied, except for the H/a value at 3 months of age and the W/H value at 21 months of age, which showed P > 0.05. CONCLUSIONS: The growth of infected infants was observed to be severely affected in comparison with that of seroreversed infants in the same age groups. Although clinical manifestations may take time to appear, the onset of growth changes begin soon after birth.

Hepatitis E virus immunoglobulin G antibodies in different populations in Campinas, Brazil.

The seroprevalence of anti-hepatitis E virus (HEV) antibodies was investigated by enzyme immunoassay in 205 volunteer blood donors, 214 women who attended a center for anonymous testing for human immunodeficiency virus (HIV) infection, and 170 hospital employees in Campinas, a city in southeastern Brazil. The prevalence of anti-HEV antibodies ranged from 2.6% (3 of 117) in health care professionals to 17.7% (38 of 214) in women who considered themselves at risk for HIV. The prevalence of anti-HEV antibodies in health care professionals was not significantly different from that in healthy blood donors (3.0%, 5 of 165) and blood donors with raised alanine aminotransferase levels (7.5%, 3 of 40). The prevalence of anti-HEV antibodies (13.2%, 7 of 53) in cleaning service workers at a University hospital was similar to that among women at risk for HIV infection. These results suggest that HEV is circulating in southeastern Brazil and that low socioeconomic status is an important risk factor for HEV infection in this region.

Circulating heat shock proteins in women with a history of recurrent vulvovaginitis.

OBJECTIVE: Predisposing factors influencing recurrences of bacterial vaginosis (BV) or vaginitis from Candida remain unidentified for most women. As a component of studies to determine host susceptibility factors to genital tract infections in women, we measured expression of the 60-kDa and 70-kDa heat shock proteins (hsp60 and hsp70, respectively) in the circulation of women with or without a history of recurrent BV or candidal vaginitis and with or without a current lower genital tract infection. Heat shock protein expression is associated with a down-regulation of pro-inflammatory immune responses that would inhibit microbial infection. METHOD: The investigators measured hsp60 and hsp70, antibodies to these proteins, the pro-inflammatory cytokine tumor necrosis factor-alpha (TNF-alpha), and the anti-inflammatory cytokine interleukin-10 (IL-10) in sera by ELISA. The study population consisted of 100 women who attended a gynecology clinic in Campinas, Brazil. Of those, 55 had a history of recurrent vulvovaginitis (RV), while 45 were controls with no such history. Only women who were asymptomatic for at least 1 month were studied. RESULTS: Although all were asymptomatic, clinical and microbiological examination revealed that five of the women with a history of RV and two controls had a current candidal vaginal infection; 16 RV patients and 12 controls had BV; and six RV patients had both BV and candidiasis. Twenty-eight RV patients and 31 controls had no clinical or microbiological detectable vaginal infection. Among the RV patients, hsp60 and hsp70 were more prevalent in those with current BV (40.9% and 50.0%, respectively) or a candidal infection (45.5% and 54.5%) than in women with no current infection (21.4% and 17.9%). In the women with no history of RV, BV was not associated with a high prevalence of hsp60 (8.3%) or hsp70 (8.3%). Interleukin-10 and TNF were not more prevalent in vaginitis patients or controls with a current candidal infection or BV than in uninfected subjects. CONCLUSION: The high prevalence of circulating hsp60 and hsp70 in women with a history of RV and current BV or vaginal candidiasis, but not in women with no history of RV, suggests that differences in heat shock protein induction may be related to susceptibility to recurrent vaginal infections.

Avaliacao de erros de medida na area de oftalmologia. / Evaluation of measurement errors in ophthalmology

Utilizando-se de medidas de intervalos anatomicos do olho e fenda palpebral, os autores analisam a magnitude dos erros experimentais cometidos na obtencao das mesmas e propoe um metodo de avaliacao da pericia do leitor escolhido para tais mensuracoes