Effect of Mobile Health Interventions on Lifestyle and Anthropometric Characteristics of Uncontrolled Hypertensive Participants: Secondary Analyses of a Randomized Controlled Trial.

Our objective was to evaluate the effect of a mobile health (mHealth) intervention on lifestyle adherence and anthropometric characteristics among individuals with uncontrolled hypertension. We performed a randomized controlled trial (ClinicalTrials.gov NCT03005470) where all participants received lifestyle counseling at baseline and were randomly allocated to receive (1) an automatic oscillometric device to measure and register blood pressure (BP) via a mobile application, (2) personalized text messages to stimulate lifestyle changes, (3) both mHealth interventions, or (4) usual clinical treatment (UCT) without technology (control). The outcomes were achieved for at least four of five lifestyle goals (weight loss, not smoking, physical activity, moderate or stopping alcohol consumption, and improving diet quality) and improved anthropometric characteristics at six months. mHealth groups were pooled for the analysis. Among 231 randomized participants (187 in the mHealth group and 45 in the control group), the mean age was 55.4 ± 9.5 years, and 51.9% were men. At six months, achieving at least four of five lifestyle goals was 2.51 times more likely (95% CI: 1.26; 5.00, p = 0.009) to be achieved among participants receiving mHealth interventions. The between-group difference reached clinically relevant, but marginally significant, reduction in body fat (-4.05 kg 95% CI: -8.14; 0.03, p = 0.052), segmental trunk fat (-1.69 kg 95% CI: -3.50; 0.12, p = 0.067), and WC (-4.36 cm 95% CI: -8.81; 0.082, p = 0.054), favoring the intervention group. In conclusion, a six-month lifestyle intervention supported by application-based BP monitoring and text messages significantly improves adherence to lifestyle goals and is likely to reduce some anthropometric characteristics in comparison with the control without technology support.

Technologies for Innovative Monitoring to Reduce Blood Pressure and Change Lifestyle Using Mobile Phones in Adult and Elderly Populations (TIM Study): Protocol for a Randomized Controlled Trial.

BACKGROUND: Hypertension is a growing problem worldwide, markedly in low- and middle-income countries, where the rate of control slightly decreased. The overall prevalence of hypertension in Brazil is 28.7% among adult individuals and 68.9% in the population aged 60 years and older, and less than a third of patients have controlled blood pressure (BP). The use of technologies-mobile phones and the internet-to implement interventions to reduce blood pressure can minimize costs and diminish cardiovascular risk. Interventions through text messaging and electronic BP monitoring present divergent results. OBJECTIVE: This trial evaluates the effectiveness of interventions-personalized messages and telemonitoring of BP-to reduce systolic BP and improve lifestyle compared to the usual care of patients with hypertension (control group). METHODS: This factorial randomized controlled trial enrolls individuals aged 30 to 75 years who have a mobile phone and internet access with the diagnosis of hypertension under drug treatment with up to 2 medications and uncontrolled BP. Eligible participants should have both increased office BP and 24-hour BP with ambulatory BP monitoring. Participants with severe hypertension (systolic BP ≥180 or diastolic BP ≥110 mm Hg), life threatening conditions, low life expectancy, recent major cardiovascular event (last 6 months), other indications for the use of antihypertensive medication, diagnosis of secondary hypertension, pregnant or lactating women, or those unable to understand the interventions are excluded. Participants are randomly allocate to 1 of 4 experimental arms: (1) Telemonitoring of blood pressure (TELEM) group: receives an automatic oscillometric device to measure BP, (2) telemonitoring by text message (TELEMEV) group: receives personalized, standardized text messages to stimulate lifestyle changes and adhere with BP-lowering medication, (3) TELEM-TELEMEV group: receives both interventions, and (4) control group: receives usual clinical treatment (UCT). Data collection is performed in a clinical research center located in a referent hospital. The primary outcomes are reduction of systolic BP assessed by 24-hour ambulatory BP monitoring (primary outcome) and change of lifestyle (based on dietary approaches to stop hypertension (DASH)-type diet, sodium restriction, weight loss or control, increase of physical activity). RESULTS: This study was funded by two Brazilian agencies: the National Council for Scientific and Technological Development and Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul. Enrollment was completed at the end of 2017 (N=231), the follow-up is ongoing, and data analysis is expected to begin in early 2019. A reduction of 24-hour systolic BP of approximately 8.8 [SD 13.1] mm Hg for participants in the BP monitoring group versus 3.4 [SD 11.6] mm Hg in the UCT group is expected. A similar reduction in the text messaging group is expected. CONCLUSIONS: The use of mobile technologies connected to the internet through mobile phones promotes time optimization, cost reduction, and better use of public health resources. However, it has not been established whether simple interventions such as text messaging are superior to electronic BP monitoring and whether both outperform conventional counseling. TRIAL REGISTRATION: ClinicalTrials.gov NCT03005470; https://clinicaltrials.gov/ct2/show/NCT03005470 (Archived by WebCite at http://www.webcitation.org/70AoANESu). Plataforma Brasil CAAE 31423214.0.0000.5327. REGISTERED REPORT IDENTIFIER: RR1-10.2196/9619.

Comparison of machine-learning algorithms to build a predictive model for detecting undiagnosed diabetes - ELSA-Brasil: accuracy study.

CONTEXT AND OBJECTIVE:: Type 2 diabetes is a chronic disease associated with a wide range of serious health complications that have a major impact on overall health. The aims here were to develop and validate predictive models for detecting undiagnosed diabetes using data from the Longitudinal Study of Adult Health (ELSA-Brasil) and to compare the performance of different machine-learning algorithms in this task. DESIGN AND SETTING:: Comparison of machine-learning algorithms to develop predictive models using data from ELSA-Brasil. METHODS:: After selecting a subset of 27 candidate variables from the literature, models were built and validated in four sequential steps: (i) parameter tuning with tenfold cross-validation, repeated three times; (ii) automatic variable selection using forward selection, a wrapper strategy with four different machine-learning algorithms and tenfold cross-validation (repeated three times), to evaluate each subset of variables; (iii) error estimation of model parameters with tenfold cross-validation, repeated ten times; and (iv) generalization testing on an independent dataset. The models were created with the following machine-learning algorithms: logistic regression, artificial neural network, naïve Bayes, K-nearest neighbor and random forest. RESULTS:: The best models were created using artificial neural networks and logistic regression. -These achieved mean areas under the curve of, respectively, 75.24% and 74.98% in the error estimation step and 74.17% and 74.41% in the generalization testing step. CONCLUSION:: Most of the predictive models produced similar results, and demonstrated the feasibility of identifying individuals with highest probability of having undiagnosed diabetes, through easily-obtained clinical data.

Comparison of machine-learning algorithms to build a predictive model for detecting undiagnosed diabetes - ELSA-Brasil: accuracy study / Comparação de algoritmos de aprendizagem de máquina para construir um modelo preditivo para detecção de diabetes não diagnosticada - ELSA-Brasil: estudo de acurácia

ABSTRACT CONTEXT AND OBJECTIVE: Type 2 diabetes is a chronic disease associated with a wide range of serious health complications that have a major impact on overall health. The aims here were to develop and validate predictive models for detecting undiagnosed diabetes using data from the Longitudinal Study of Adult Health (ELSA-Brasil) and to compare the performance of different machine-learning algorithms in this task. DESIGN AND SETTING: Comparison of machine-learning algorithms to develop predictive models using data from ELSA-Brasil. METHODS: After selecting a subset of 27 candidate variables from the literature, models were built and validated in four sequential steps: (i) parameter tuning with tenfold cross-validation, repeated three times; (ii) automatic variable selection using forward selection, a wrapper strategy with four different machine-learning algorithms and tenfold cross-validation (repeated three times), to evaluate each subset of variables; (iii) error estimation of model parameters with tenfold cross-validation, repeated ten times; and (iv) generalization testing on an independent dataset. The models were created with the following machine-learning algorithms: logistic regression, artificial neural network, naïve Bayes, K-nearest neighbor and random forest. RESULTS: The best models were created using artificial neural networks and logistic regression. ­These achieved mean areas under the curve of, respectively, 75.24% and 74.98% in the error estimation step and 74.17% and 74.41% in the generalization testing step. CONCLUSION: Most of the predictive models produced similar results, and demonstrated the feasibility of identifying individuals with highest probability of having undiagnosed diabetes, through easily-obtained clinical data.

RESUMO CONTEXTO E OBJETIVO: Diabetes tipo 2 é uma doença crônica associada a graves complicações de saúde, causando grande impacto na saúde global. O objetivo foi desenvolver e validar modelos preditivos para detectar diabetes não diagnosticada utilizando dados do Estudo Longitudinal de Saúde do Adulto (ELSA-Brasil) e comparar o desempenho de diferentes algoritmos de aprendizagem de máquina. TIPO DE ESTUDO E LOCAL: Comparação de algoritmos de aprendizagem de máquina para o desenvolvimento de modelos preditivos utilizando dados do ELSA-Brasil. MÉTODOS: Após selecionar 27 variáveis candidatas a partir da literatura, modelos foram construídos e validados em 4 etapas sequenciais: (i) afinação de parâmetros com validação cruzada (10-fold cross-validation); (ii) seleção automática de variáveis utilizando seleção progressiva, estratégia "wrapper" com quatro algoritmos de aprendizagem de máquina distintos e validação cruzada para avaliar cada subconjunto de variáveis; (iii) estimação de erros dos parâmetros dos modelos com validação cruzada; e (iv) teste de generalização em um conjunto de dados independente. Os modelos foram criados com os seguintes algoritmos de aprendizagem de máquina: regressão logística, redes neurais artificiais, naïve Bayes, K vizinhos mais próximos e floresta aleatória. RESULTADOS: Os melhores modelos foram criados utilizando redes neurais artificiais e regressão logística alcançando, respectivamente, 75,24% e 74,98% de média de área sob a curva na etapa de estimação de erros e 74,17% e 74,41% na etapa de teste de generalização. CONCLUSÃO: A maioria dos modelos preditivos produziu resultados semelhantes e demonstrou a viabilidade de identificar aqueles com maior probabilidade de ter diabetes não diagnosticada com dados clínicos facilmente obtidos.

Improving Preventive Healthcare with an User-centric Mobile Tele-monitoring Model.

Chronic diseases are an important field to tackle due to increasing healthcare risk factors, including population nutritional habits, lack of physical exercise, and population aging. Diabetes mellitus, hypertension, and obesity currently affect millions of people, and this statistic grows every year and is responsible for numerous deaths everyday. Many of those deaths could be delayed by following a steady monitoring strategy over such a population, which would prevent vital signs from reaching critical stages and providing knowledge for these patients about their health. This paper introduces Mobilicare, a mobile health promotion system designed to: (i) monitor remotely a patient's vital signs in real time; (ii) support a health service in a Healthcare Center; and (iii) allow self-awareness of the disease and improve motivation. Our approach was applied to two distinct chronic patient management programs. The results showed the commitment of elder patients and the contribution of Mobilicare to the maintenance of a patient's health stability.