VANDERLEI CARNEIRO DA SILVA
Projetos de Pesquisa
Unidades Organizacionais
LIM/20 - Laboratório de Terapêutica Experimental, Hospital das Clínicas, Faculdade de Medicina
7 resultados
Resultados de Busca
Agora exibindo 1 - 7 de 7
- Crash Risk Predictors in Older Drivers: A Cross-Sectional Study Based on a Driving Simulator and Machine Learning Algorithms(2023) SILVA, V. C.; DIAS, A. S.; GREVE, J. M. D.; DAVIS, C. L.; SOARES, A. L. D. S.; BRECH, G. C.; AYAMA, S.; JACOB-FILHO, W.; BUSSE, A. L.; BIASE, M. E. M. de; CANONICA, A. C.; ALONSO, A. C.The ability to drive depends on the motor, visual, and cognitive functions, which are necessary to integrate information and respond appropriately to different situations that occur in traffic. The study aimed to evaluate older drivers in a driving simulator and identify motor, cognitive and visual variables that interfere with safe driving through a cluster analysis, and identify the main predictors of traffic crashes. We analyzed the data of older drivers (n = 100, mean age of 72.5 ± 5.7 years) recruited in a hospital in São Paulo, Brazil. The assessments were divided into three domains: motor, visual, and cognitive. The K-Means algorithm was used to identify clusters of individuals with similar characteristics that may be associated with the risk of a traffic crash. The Random Forest algorithm was used to predict road crash in older drivers and identify the predictors (main risk factors) related to the outcome (number of crashes). The analysis identified two clusters, one with 59 participants and another with 41 drivers. There were no differences in the mean of crashes (1.7 vs. 1.8) and infractions (2.6 vs. 2.0) by cluster. However, the drivers allocated in Cluster 1, when compared to Cluster 2, had higher age, driving time, and braking time (p < 0.05). The random forest performed well (r = 0.98, R2 = 0.81) in predicting road crash. Advanced age and the functional reach test were the factors representing the highest risk of road crash. There were no differences in the number of crashes and infractions per cluster. However, the Random Forest model performed well in predicting the number of crashes.
- Recommender System Based on Collaborative Filtering for Personalized Dietary Advice: A Cross-Sectional Analysis of the ELSA-Brasil Study(2022) SILVA, Vanderlei Carneiro; GORGULHO, Bartira; MARCHIONI, Dirce Maria; ALVIM, Sheila Maria; GIATTI, Luana; ARAUJO, Tania Aparecida de; ALONSO, Angelica Castilho; SANTOS, Itamar de Souza; LOTUFO, Paulo Andrade; BENSENOR, Isabela MartinsThis study aimed to predict dietary recommendations and compare the performance of algorithms based on collaborative filtering for making predictions of personalized dietary recommendations. We analyzed the baseline cross-sectional data (2008-2010) of 12,667 participants of the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). The participants were public employees of teaching and research institutions, aged 35-74 years, and 59% female. A semiquantitative Food Frequency Questionnaire (FFQ) was used for dietary assessment. The predictions of dietary recommendations were based on two machine learning (ML) algorithms-user-based collaborative filtering (UBCF) and item-based collaborative filtering (IBCF). The ML algorithms had similar precision (88-91%). The error metrics were lower for UBCF than for IBCF: with a root mean square error (RMSE) of 1.49 vs. 1.67 and a mean square error (MSE) of 2.21 vs. 2.78. Although all food groups were used as input in the system, the items eligible as recommendations included whole cereals, tubers and roots, beans and other legumes, oilseeds, fruits, vegetables, white meats and fish, and low-fat dairy products and milk. The algorithms' performances were similar in making predictions for dietary recommendations. The models presented can provide support for health professionals in interventions that promote healthier habits and improve adherence to this personalized dietary advice.
- Diet Quality of Workers and Retirees: A Cross-sectional Analysis of the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil)(2021) SILVA, Vanderlei C. da; GORGULHO, Bartira M.; MARCHIONI, Dirce M.; LOTUFO, Paulo A.; BENSENOR, Isabela M.; CHIAVEGATTO FILHO, Alexandre D. P.The objective of this study was to cross-sectionally analyze the diet quality of active workers and retirees to identify possible differences by gender and subgroups of working and nonworking retirees using baseline data from the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), a cohort study of employees of six higher education centers in Brazil. In the first phase of the study, which occurred between 2008 and 2010, the diets of 7,667 participants between 50 and 69 years of age (3,393 [44%] men and 4,274 [56%] women) were analyzed using a Food Frequency Questionnaire. Diets were evaluated using the Brazilian Healthy Eating Index-Revised. We used logistic regression models stratified by sex and adjusted for demographic, social, and health conditions to calculate the odds ratio (OR) and 95% confidence interval (95% CI) for the association of diet quality with working and nonworking retirees. Using active workers as the reference group, the results showed better diet quality among male retirees who were no longer working (OR: 1.58; 95% CI: 1.03-2.41), whereas no difference was detected in male retirees who returned to work (OR: 1.17; 95% CI: 0.80-1.72) in the adjusted models. Among women, the association did not remain significant after multivariate adjustment for confounders. Our results showed gender differences in diet quality between workers and working and nonworking retirees possibly because of worse diet quality among men than among women. Work cessation after retirement is mandatory to improve diet quality among male retirees.
- Clustering analysis and machine learning algorithms in the prediction of dietary patterns: Cross-sectional results of the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil)(2022) SILVA, Vanderlei Carneiro; GORGULHO, Bartira; MARCHIONI, Dirce Maria; ARAUJO, Tania Aparecida de; SANTOS, Itamar de Souza; LOTUFO, Paulo Andrade; BENSENOR, Isabela MartinsBackground Machine learning investigates how computers can automatically learn. The present study aimed to predict dietary patterns and compare algorithm performance in making predictions of dietary patterns. Methods We analysed the data of public employees (n = 12,667) participating in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). The K-means clustering algorithm and six other classifiers (support vector machines, naive Bayes, K-nearest neighbours, decision tree, random forest and xgboost) were used to predict the dietary patterns. Results K-means clustering identified two dietary patterns. Cluster 1, labelled the Western pattern, was characterised by a higher energy intake and consumption of refined cereals, beans and other legumes, tubers, pasta, processed and red meats, high-fat milk and dairy products, and sugary beverages; Cluster 2, labelled the Prudent pattern, was characterised by higher intakes of fruit, vegetables, whole cereals, white meats, and milk and reduced-fat milk derivatives. The most important predictors were age, sex, per capita income, education level and physical activity. The accuracy of the models varied from moderate to good (69%-72%). Conclusions The performance of the algorithms in dietary pattern prediction was similar, and the models presented may provide support in screener tasks and guide health professionals in the analysis of dietary data.
- Factors Contributing to Traffic Accidents in Hospitalized Patients in Terms of Severity and Functionality(2023) CANONICA, Alexandra Carolina; ALONSO, Angelica Castilho; SILVA, Vanderlei Carneiro da; BOMBANA, Henrique Silva; MUZAURIETA, Aurelio Alberto; LEYTON, Vilma; GREVE, Julia Maria D'AndreaTrauma-related injuries in traffic-accident victims can be quite serious. Evaluating the factors contributing to traffic accidents is critical for the effective design of programs aimed at reducing traffic accidents. Therefore, this study identified which factors related to traffic accidents are associated with injury severity in hospitalized victims. Factors related to traffic accidents, injury severity, disability and data collected from blood toxicology were evaluated, along with associated severity and disability indices with data collected from toxicology on victims of traffic accidents at the largest tertiary hospital in Latin America. One hundred and twenty-eight victims of traffic accidents were included, of whom the majority were young adult men, motorcyclists, and pedestrians. The most frequent injuries were traumatic brain injury and lower-limb fractures. Alcohol use, hit-and-run victims, and longer hospital stays were shown to lead to greater injury severity. Women, elderly individuals, and pedestrians tend to suffer greater disability post-injury. Therefore, traffic accidents occur more frequently among young male adults, motorcyclists, and those who are hit by a vehicle, with trauma to the head and lower limbs being the most common injury. Injury severity is greater in pedestrians, elderly individuals and inebriated individuals. Disability was higher in older individuals, in women, and in pedestrians.
- Physical and pulmonary capacities of individuals with severe coronavirus disease after hospital discharge: A preliminary cross-sectional study based on cluster analysis(2021) ALONSO, Angelica Castilho; SILVA-SANTOS, Paulo Roberto; QUINTANA, Marilia Simoes Lopes; SILVA, Vanderlei Carneiro da; BRECH, Guilherme Carlos; BARBOSA, Lorena Goncalves; POMPEU, Jose Eduardo; SILVA, Erika Christina Gouveia e; SILVA, Elizabeth Mendes da; GODOY, Caroline Gil de; GREVE, Julia Maria D'AndreaOBJECTIVE: This study aimed to analyze the physical and pulmonary capacities of hospitalized patients with severe coronavirus disease and its correlation with the time of hospitalization and complications involved. METHODS: A total of 54 patients, aged >= 18 years of both sexes, were evaluated 2-4 months after hospital discharge in Sao Paulo, Brazil. The physical characteristics analyzed were muscle strength, balance, flexibility, and pulmonary function. The K-means cluster algorithm was used to identify patients with similar physical and pulmonary capacities, related to the time of hospitalization. RESULTS: Two clusters were derived using the K-means algorithm. Patients allocated in cluster 1 had fewer days of hospitalization, intensive care, and intubation than those in cluster 2, which reflected a better physical performance, strength, balance, and pulmonary condition, even 2-4 months after discharge. Days of hospitalization were inversely related to muscle strength, physical performance, and lung function: hand grip D (r= -0.28, p=0.04), Short Physical Performance Battery score (r= -0.28, p=0.03), and forced vital capacity (r= -0.29, p=0.03). CONCLUSION: Patients with a longer hospitalization time and complications progressed with greater loss of physical and pulmonary capacities.
- Quality of life and socio-demographic factors associated with nutritional risk in Brazilian community-dwelling individuals aged 80 and over: cluster analysis and ensemble methods(2024) BRECH, Guilherme Carlos; SILVA, Vanderlei Carneiro da; ALONSO, Angelica Castilho; MACHADO-LIMA, Adriana; SILVA, Daiane Fuga da; MICILLO, Glaucia Pegorari; BASTOS, Marta Ferreira; AQUINO, Rita de Cassia deIntroductionThe aim of the present study was to use cluster analysis and ensemble methods to evaluate the association between quality of life, socio-demographic factors to predict nutritional risk in community-dwelling Brazilians aged 80 and over.MethodsThis cross-sectional study included 104 individuals, both sexes, from different community locations. Firstly, the participants answered the sociodemographic questionnaire, and were sampled for anthropometric data. Subsequently, the Mini-Mental State Examination (MMSE) was applied, and Mini Nutritional Assessment Questionnaire (MAN) was used to evaluate their nutritional status. Finally, quality of life (QoL) was assessed by a brief version of World Health Organizations' Quality of Life (WHOQOL-BREF) questionnaire and its older adults' version (WHOQOL-OLD).ResultsThe K-means algorithm was used to identify clusters of individuals regarding quality-of-life characteristics. In addition, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) algorithms were used to predict nutritional risk. Four major clusters were derived. Although there was a higher proportion of individuals aged 80 and over with nutritional risk in cluster 2 and a lower proportion in cluster 3, there was no statistically significant association. Cluster 1 showed the highest scores for psychological, social, and environmental domains, while cluster 4 exhibited the worst scores for the social and environmental domains of WHOQOL-BREF and for autonomy, past, present, and future activities, and intimacy of WHOQOL-OLD.ConclusionHandgrip, household income, and MMSE were the most important predictors of nutritional. On the other hand, sex, self-reported health, and number of teeth showed the lowest levels of influence in the construction of models to evaluate nutritional risk. Taken together, there was no association between clusters based on quality-of-life domains and nutritional risk, however, predictive models can be used as a complementary tool to evaluate nutritional risk in individuals aged 80 and over.