Fairness of Machine Learning Algorithms for Predicting Foregone Preventive Dental Care for Adults.

Importance: Access to routine dental care prevents advanced dental disease and improves oral and overall health. Identifying individuals at risk of foregoing preventive dental care can direct prevention efforts toward high-risk populations. Objective: To predict foregone preventive dental care among adults overall and in sociodemographic subgroups and to assess the algorithmic fairness. Design, Setting, and Participants: This prognostic study was a secondary analyses of longitudinal data from the US Medical Expenditure Panel Survey (MEPS) from 2016 to 2019, each with 2 years of follow-up. Participants included adults aged 18 years and older. Data analysis was performed from December 2022 to June 2023. Exposure: A total of 50 predictors, including demographic and socioeconomic characteristics, health conditions, behaviors, and health services use, were assessed. Main Outcomes and Measures: The outcome of interest was foregoing preventive dental care, defined as either cleaning, general examination, or an appointment with the dental hygienist, in the past year. Results: Among 32 234 participants, the mean (SD) age was 48.5 (18.2) years and 17 386 participants (53.9%) were female; 1935 participants (6.0%) were Asian, 5138 participants (15.9%) were Black, 7681 participants (23.8%) were Hispanic, 16 503 participants (51.2%) were White, and 977 participants (3.0%) identified as other (eg, American Indian and Alaska Native) or multiple racial or ethnic groups. There were 21 083 (65.4%) individuals who missed preventive dental care in the past year. The algorithms demonstrated high performance, achieving an area under the receiver operating characteristic curve (AUC) of 0.84 (95% CI, 0.84-0.85) in the overall population. While the full sample model performed similarly when applied to White individuals and older adults (AUC, 0.88; 95% CI, 0.87-0.90), there was a loss of performance for other subgroups. Removing the subgroup-sensitive predictors (ie, race and ethnicity, age, and income) did not impact model performance. Models stratified by race and ethnicity performed similarly or worse than the full model for all groups, with the lowest performance for individuals who identified as other or multiple racial groups (AUC, 0.76; 95% CI, 0.70-0.81). Previous pattern of dental visits, health care utilization, dental benefits, and sociodemographic characteristics were the highest contributing predictors to the models' performance. Conclusions and Relevance: Findings of this prognostic study using cohort data suggest that tree-based ensemble machine learning models could accurately predict adults at risk of foregoing preventive dental care and demonstrated bias against underrepresented sociodemographic groups. These results highlight the importance of evaluating model fairness during development and testing to avoid exacerbating existing biases.

A Machine Learning Prediction Model for Immediate Graft Function After Deceased Donor Kidney Transplantation.

BACKGROUND: After kidney transplantation (KTx), the graft can evolve from excellent immediate graft function (IGF) to total absence of function requiring dialysis. Recipients with IGF do not seem to benefit from using machine perfusion, an expensive procedure, in the long term when compared with cold storage. This study proposes to develop a prediction model for IGF in KTx deceased donor patients using machine learning algorithms. METHODS: Unsensitized recipients who received their first KTx deceased donor between January 1, 2010, and December 31, 2019, were classified according to the conduct of renal function after transplantation. Variables related to the donor, recipient, kidney preservation, and immunology were used. The patients were randomly divided into 2 groups: 70% were assigned to the training and 30% to the test group. Popular machine learning algorithms were used: eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine, Gradient Boosting classifier, Logistic Regression, CatBoost classifier, AdaBoost classifier, and Random Forest classifier. Comparative performance analysis on the test dataset was performed using the results of the AUC values, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score. RESULTS: Of the 859 patients, 21.7% (n = 186) had IGF. The best predictive performance resulted from the eXtreme Gradient Boosting model (AUC, 0.78; 95% CI, 0.71-0.84; sensitivity, 0.64; specificity, 0.78). Five variables with the highest predictive value were identified. CONCLUSIONS: Our results indicated the possibility of creating a model for the prediction of IGF, enhancing the selection of patients who would benefit from an expensive treatment, as in the case of machine perfusion preservation.

Machine Learning for Hypertension Prediction: a Systematic Review.

PURPOSE OF REVIEW: To provide an overview of the literature regarding the use of machine learning algorithms to predict hypertension. A systematic review was performed to select recent articles on the subject. RECENT FINDINGS: The screening of the articles was conducted using a machine learning algorithm (ASReview). A total of 21 articles published between January 2018 and May 2021 were identified and compared according to variable selection, train-test split, data balancing, outcome definition, final algorithm, and performance metrics. Overall, the articles achieved an area under the ROC curve (AUROC) between 0.766 and 1.00. The algorithms most frequently identified as having the best performance were support vector machines (SVM), extreme gradient boosting (XGBoost), and random forest. Machine learning algorithms are a promising tool to improve preventive clinical decisions and targeted public health policies for hypertension. However, technical factors such as outcome definition, availability of the final code, predictive performance, explainability, and data leakage need to be consistently and critically evaluated.

Neonatal mortality prediction with routinely collected data: a machine learning approach.

BACKGROUND: Recent decreases in neonatal mortality have been slower than expected for most countries. This study aims to predict the risk of neonatal mortality using only data routinely available from birth records in the largest city of the Americas. METHODS: A probabilistic linkage of every birth record occurring in the municipality of São Paulo, Brazil, between 2012 e 2017 was performed with the death records from 2012 to 2018 (1,202,843 births and 447,687 deaths), and a total of 7282 neonatal deaths were identified (a neonatal mortality rate of 6.46 per 1000 live births). Births from 2012 and 2016 (N = 941,308; or 83.44% of the total) were used to train five different machine learning algorithms, while births occurring in 2017 (N = 186,854; or 16.56% of the total) were used to test their predictive performance on new unseen data. RESULTS: The best performance was obtained by the extreme gradient boosting trees (XGBoost) algorithm, with a very high AUC of 0.97 and F1-score of 0.55. The 5% births with the highest predicted risk of neonatal death included more than 90% of the actual neonatal deaths. On the other hand, there were no deaths among the 5% births with the lowest predicted risk. There were no significant differences in predictive performance for vulnerable subgroups. The use of a smaller number of variables (WHO's five minimum perinatal indicators) decreased overall performance but the results still remained high (AUC of 0.91). With the addition of only three more variables, we achieved the same predictive performance (AUC of 0.97) as using all the 23 variables originally available from the Brazilian birth records. CONCLUSION: Machine learning algorithms were able to identify with very high predictive performance the neonatal mortality risk of newborns using only routinely collected data.

Predictors of tooth loss: A machine learning approach.

INTRODUCTION: Little is understood about the socioeconomic predictors of tooth loss, a condition that can negatively impact individual's quality of life. The goal of this study is to develop a machine-learning algorithm to predict complete and incremental tooth loss among adults and to compare the predictive performance of these models. METHODS: We used data from the National Health and Nutrition Examination Survey from 2011 to 2014. We developed multiple machine-learning algorithms and assessed their predictive performances by examining the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive values. RESULTS: The extreme gradient boosting trees presented the highest performance in the prediction of edentulism (AUC = 88.7%; 95%CI: 87.1, 90.2), the absence of a functional dentition (AUC = 88.3% 95%CI: 87.3,89.3) and for predicting missing any tooth (AUC = 83.2%; 95%CI, 82.0, 84.4). Although, as expected, age and routine dental care emerged as strong predictors of tooth loss, the machine learning approach identified additional predictors, including socioeconomic conditions. Indeed, the performance of models incorporating socioeconomic characteristics was better at predicting tooth loss than those relying on clinical dental indicators alone. CONCLUSIONS: Future application of machine-learning algorithm, with longitudinal cohorts, for identification of individuals at risk for tooth loss could assist clinicians to prioritize interventions directed toward the prevention of tooth loss.

[Quality of diet and daily spending on food by adults with cardiovascular disease in Brazil]. / Qualidade da dieta e despesa diária com alimentação em adultos com doença cardiovascular no Brasil.

Adherence to a healthy diet depends on factors such as food prices, while studies in developed countries have identified higher costs of more nutritional foods. The current study aimed to assess the direct food expenditures by adults with cardiovascular disease in Brazil, investigating the relationship between cost and quality of diet. The study used data from a randomized clinical trial, the BALANCE Program. The current study is a cross-sectional baseline analysis of participants with high adherence to the trial, conducted in 35 sites in all five major geographic regions of Brazil. Food consumption by 1,160 individuals was collected with a 24-hour dietary recall (24HR), quality of diet was measured with the Diet Quality Index Revised (DQI-R), and direct food costs were estimated from market prices. No significant differences were observed between tertiles of adherence in the direct costs of food or individual characteristics. When all the 24HR were analyzed, there was no correlation between cost and quality of diet (r = 0.38; p = 0.17), while analysis by tertiles showed a weak correlation in the lowest tertile of adherence (r = -0.112; p = 0.03). The study showed absence of differences between direct costs of healthy versus unhealthy foods, a finding that can serve as an incentive for adherence to food recommendations in Brazil, thereby minimizing barriers to the adoption of healthy lifestyles.

A adesão a uma alimentação saudável depende de fatores como os preços dos alimentos, sendo que alguns estudos conduzidos em países desenvolvidos apontam para um maior custo de uma alimentação de melhor qualidade nutricional. O objetivo do presente trabalho foi avaliar o custo direto da alimentação de indivíduos adultos com doença cardiovascular no Brasil, investigando a relação entre o custo e a qualidade da dieta. Foram utilizados os dados de um ensaio clínico randomizado, o BALANCE Program. A investigação atual é uma análise transversal no momento inicial dos participantes com alta adesão ao estudo realizado em 35 centros das cinco regiões brasileiras. O consumo alimentar de amostra com 1.160 indivíduos foi coletado pelo recordatório alimentar de 24 horas (R24h), a avaliação da qualidade da dieta pelo Índice da Qualidade da Dieta Revisado (IQD-R) e os custos diretos da alimentação foram estimados por meio de preços de mercado. Não foram observadas diferenças significativas no custo direto da alimentação ou características dos indivíduos entre os tercis de adesão. Quando analisados todos os recordatórios não houve correlação entre custo e qualidade da dieta (r = 0,38; p = 0,17), já a análise por tercis mostrou fraca correlação entre o menor tercil de adesão (r = -0,112; p = 0,03). O presente estudo apontou ausência de diferenças entre os custos diretos da alimentação classificada como saudável e daquela com a pior qualidade nutricional, o que pode ser um incentivo à adesão às orientações alimentares no Brasil, minimizando barreiras à adoção de estilos de vida saudáveis.

La adhesión a una alimentación saludable depende de factores como los precios de los alimentos, siendo que algunos estudios realizados en países desarrollados apuntan hacia un mayor coste de una alimentación de mejor calidad nutricional. El objetivo del presente estudio fue evaluar el coste directo de la alimentación en individuos adultos con enfermedad cardiovascular en Brasil, investigando la relación entre el coste y la calidad de la dieta. Se utilizaron los datos de un ensayo clínico aleatorio, el BALANCE Program. La investigación actual es un análisis transversal desde el principio con participantes de alta adhesión al estudio, realizado en 35 centros de las cinco regiones brasileñas. El consumo alimentario de la muestra con 1.160 individuos fue recogido mediante el recordatorio alimentario de 24 horas (R24h), la evaluación de la calidad de la dieta se evaluó mediante el Índice de Calidad de la Dieta Revisado (IQD-R por sus siglas en portugués) y los costes directos de la alimentación se estimaron mediante precios de mercado. No se observaron diferencias significativas en el coste directo de la alimentación o características de los individuos entre los terciles de adhesión. Cuando se analizaron todos los recordatorios no hubo correlación entre coste y calidad de la dieta (r = 0,38; p = 0,17), ya en el análisis por terciles hubo una débil correlación entre el menor tercil de adhesión (r = -0,112; p = 0,03). El presente estudio apuntó una ausencia de diferencias entre los costes directos de la alimentación clasificada como saludable y aquella con peor calidad nutricional, lo que puede ser un incentivo para la adhesión a las orientaciones alimentarias en Brasil, minimizando barreras para la adopción de estilos de vida saludables.

Qualidade da dieta e despesa diária com alimentação em adultos com doença cardiovascular no Brasil / Quality of diet and daily spending on food by adults with cardiovascular disease in Brazil / Calidad de la dieta y gasto diario en alimentación de adultos con enfermedad cardiovascular en Brasil

A adesão a uma alimentação saudável depende de fatores como os preços dos alimentos, sendo que alguns estudos conduzidos em países desenvolvidos apontam para um maior custo de uma alimentação de melhor qualidade nutricional. O objetivo do presente trabalho foi avaliar o custo direto da alimentação de indivíduos adultos com doença cardiovascular no Brasil, investigando a relação entre o custo e a qualidade da dieta. Foram utilizados os dados de um ensaio clínico randomizado, o BALANCE Program. A investigação atual é uma análise transversal no momento inicial dos participantes com alta adesão ao estudo realizado em 35 centros das cinco regiões brasileiras. O consumo alimentar de amostra com 1.160 indivíduos foi coletado pelo recordatório alimentar de 24 horas (R24h), a avaliação da qualidade da dieta pelo Índice da Qualidade da Dieta Revisado (IQD-R) e os custos diretos da alimentação foram estimados por meio de preços de mercado. Não foram observadas diferenças significativas no custo direto da alimentação ou características dos indivíduos entre os tercis de adesão. Quando analisados todos os recordatórios não houve correlação entre custo e qualidade da dieta (r = 0,38; p = 0,17), já a análise por tercis mostrou fraca correlação entre o menor tercil de adesão (r = -0,112; p = 0,03). O presente estudo apontou ausência de diferenças entre os custos diretos da alimentação classificada como saudável e daquela com a pior qualidade nutricional, o que pode ser um incentivo à adesão às orientações alimentares no Brasil, minimizando barreiras à adoção de estilos de vida saudáveis.

Adherence to a healthy diet depends on factors such as food prices, while studies in developed countries have identified higher costs of more nutritional foods. The current study aimed to assess the direct food expenditures by adults with cardiovascular disease in Brazil, investigating the relationship between cost and quality of diet. The study used data from a randomized clinical trial, the BALANCE Program. The current study is a cross-sectional baseline analysis of participants with high adherence to the trial, conducted in 35 sites in all five major geographic regions of Brazil. Food consumption by 1,160 individuals was collected with a 24-hour dietary recall (24HR), quality of diet was measured with the Diet Quality Index Revised (DQI-R), and direct food costs were estimated from market prices. No significant differences were observed between tertiles of adherence in the direct costs of food or individual characteristics. When all the 24HR were analyzed, there was no correlation between cost and quality of diet (r = 0.38; p = 0.17), while analysis by tertiles showed a weak correlation in the lowest tertile of adherence (r = -0.112; p = 0.03). The study showed absence of differences between direct costs of healthy versus unhealthy foods, a finding that can serve as an incentive for adherence to food recommendations in Brazil, thereby minimizing barriers to the adoption of healthy lifestyles.

La adhesión a una alimentación saludable depende de factores como los precios de los alimentos, siendo que algunos estudios realizados en países desarrollados apuntan hacia un mayor coste de una alimentación de mejor calidad nutricional. El objetivo del presente estudio fue evaluar el coste directo de la alimentación en individuos adultos con enfermedad cardiovascular en Brasil, investigando la relación entre el coste y la calidad de la dieta. Se utilizaron los datos de un ensayo clínico aleatorio, el BALANCE Program. La investigación actual es un análisis transversal desde el principio con participantes de alta adhesión al estudio, realizado en 35 centros de las cinco regiones brasileñas. El consumo alimentario de la muestra con 1.160 individuos fue recogido mediante el recordatorio alimentario de 24 horas (R24h), la evaluación de la calidad de la dieta se evaluó mediante el Índice de Calidad de la Dieta Revisado (IQD-R por sus siglas en portugués) y los costes directos de la alimentación se estimaron mediante precios de mercado. No se observaron diferencias significativas en el coste directo de la alimentación o características de los individuos entre los terciles de adhesión. Cuando se analizaron todos los recordatorios no hubo correlación entre coste y calidad de la dieta (r = 0,38; p = 0,17), ya en el análisis por terciles hubo una débil correlación entre el menor tercil de adhesión (r = -0,112; p = 0,03). El presente estudio apuntó una ausencia de diferencias entre los costes directos de la alimentación clasificada como saludable y aquella con peor calidad nutricional, lo que puede ser un incentivo para la adhesión a las orientaciones alimentarias en Brasil, minimizando barreras para la adopción de estilos de vida saludables.

Multilevel Analysis of the Patterns of Physical-Mental Multimorbidity in General Population of São Paulo Metropolitan Area, Brazil.

Chronic diseases are often comorbid and present a weighty burden for communities in the 21st century. The present investigation depicted patterns of multimorbidity in the general population and examined its association with the individual- and area-level factors in an urban sample of non-elderly adults of Brazil. Data were from the cross-sectional São Paulo Megacity Mental Health Survey, a stratified multistage area probability sampling investigation. Trained interviewers assessed mental morbidities and asked about physical conditions for 1,571 community-dwelling women and 1,142 men, aged between 18 and 64 years. Principal component analysis depicted patterns of physical-mental multimorbidity, by sex. Following, the patterns of multimorbidity were subjected to multilevel regression analysis, taking into account individual- and area-level variables. Three patterns of clustering were found for women: 'irritable mood and headache', 'chronic diseases and pain', and 'substance use disorders'. Among men, the patterns were: 'chronic pain and respiratory disease', 'psychiatric disorders', and 'chronic diseases'. Multilevel analyses showed associations between multimorbidity patterns and both individual- and area-level determinants. Our findings call for a reformulation of health-care systems worldwide, especially in low-resource countries. Replacing the single-disease framework by multi-disease patterns in health-care settings can improve the ability of general practitioners in the health-care of person-centred needs.

Contextual and individual inequalities of multimorbidity in Brazilian adults: a cross-sectional national-based study.

OBJECTIVES: The study aims to evaluate the magnitude of multimorbidity in Brazilian adults, as well to measure their association with individual and contextual factors stratified by Brazilian states and regions. METHODS: A national-based cross-sectional study was carried out in 2013 with Brazilian adults. Multimorbidity was evaluated by a list of 22 physical and mental morbidities (based on self-reported medical diagnosis and Patient Health Questionnaire-9 for depression). The outcome was analysed taking ≥2 and ≥3 diseases as cut-off points. Factor analysis (FA) was used to identify disease patterns and multilevel models were used to test association with individual and contextual variables. RESULTS: The sample comprised 60 202 individuals. Multimorbidity frequency was 22.2% (95% CI 21.5 to 22.9) for ≥2 morbidities and 10.2% (95% CI 9.7 to 10.7) for ≥3 morbidities. In the multilevel adjusted models, females, older people, those living with a partner and having less schooling presented more multiple diseases. No linear association was found according to wealth index but greater outcome frequency was found in individuals with midrange wealth index. Living in states with higher levels of education and wealthier states was associated with greater multimorbidity. Two patterns of morbidities (cardiometabolic problems and respiratory/mental/muscle-skeletal disorders) explained 92% of total variance. The relationship of disease patterns with individual and contextual variables was similar to the overall multimorbidity, with differences among Brazilian regions. CONCLUSIONS: In Brazil, at least 19 million adults had multimorbidity. Frequency is similar to that found in other Low and and Middle Income Countries. Contextual and individual social inequalities were observed.

Income inequality is associated with adolescent fertility in Brazil: a longitudinal multilevel analysis of 5,565 municipalities.

BACKGROUND: Brazil has one of the highest adolescent fertility rates in the world. Income inequality has been frequently linked to overall adolescent health, but studies that analyzed its association with adolescent fertility have been performed only in developed countries. Brazil, in the past decade, has presented a rare combination of increasing per capita income and decreasing income inequality, which could influence future desirable pathways for other countries. METHODS: We analyzed every live birth from 2000 and from 2010 in each of the 5,565 municipalities of Brazil, a total of 6,049,864 births, which included 1,247,145 (20.6%) births from women aged 15 to 19. Income inequality was assessed by the Gini Coefficient and adolescent fertility by the ratio between the number of live births from women aged 15 to 19 and the number of women aged 15 to 19, calculated for each municipality. We first applied multilevel models separately for 2000 and 2010 to test the cross-sectional association between income inequality and adolescent fertility. We then fitted longitudinal first-differences multilevel models to control for time-invariant effects. We also performed a sensitivity analysis to include only municipality with satisfactory birth record coverage. RESULTS: Our results indicate a consistent and positive association between income inequality and adolescent fertility. After controlling for per capita income, college access, youth homicide rate and adult fertility, higher income inequality was significantly associated with higher adolescent fertility for both 2000 and 2010. The longitudinal multilevel models found similar results. The sensitivity analysis indicated that the results for the association between income inequality and adolescent fertility were robust. Adult fertility was also significantly associated with adolescent fertility in the cross-sectional and longitudinal models. CONCLUSION: Income inequality is expected to be a leading concern for most countries in the near future. Our results suggest that changes in income inequality are positively and consistently associated with changes in adolescent fertility.

Income inequality and mortality: results from a longitudinal study of older residents of São Paulo, Brazil.

OBJECTIVES: We determined whether community-level income inequality was associated with mortality among a cohort of older adults in São Paulo, Brazil. METHODS: We analyzed the Health, Well-Being, and Aging (SABE) survey, a sample of community-dwelling older adults in São Paulo (2000-2007). We used survival analysis to examine the relationship between income inequality and risk for mortality among older individuals living in 49 districts of São Paulo. RESULTS: Compared with individuals living in the most equal districts (lowest Gini quintile), rates of mortality were higher for those living in the second (adjusted hazard ratio [AHR] = 1.44, 95% confidence interval [CI] = 0.87, 2.41), third (AHR = 1.96, 95% CI = 1.20, 3.20), fourth (AHR = 1.34, 95% CI = 0.81, 2.20), and fifth quintile (AHR = 1.74, 95% CI = 1.10, 2.74). When we imputed missing data and used poststratification weights, the adjusted hazard ratios for quintiles 2 through 5 were 1.72 (95% CI = 1.13, 2.63), 1.41 (95% CI = 0.99, 2.05), 1.13 (95% = 0.75, 1.70) and 1.30 (95% CI = 0.90, 1.89), respectively. CONCLUSIONS: We did not find a dose-response relationship between area-level income inequality and mortality. Our findings could be consistent with either a threshold association of income inequality and mortality or little overall association.