Predicting Changes in Systolic and Diastolic Blood Pressure of Hypertensive Patients in Indonesia Using Machine Learning.

PURPOSE OF REVIEW: This retrospective study investigated factors that influence the occurrence of decreased systolic and diastolic blood pressure including sociodemographic and economic factors, hypertension duration, cigarette consumption, alcohol consumption, duration of smoking, type of cigarettes, exercise, salt consumption, sleeping pills consumption, insomnia, and diabetes. These factors were applied to predict the reality of systolic and diastolic decrease using the machine learning algorithm Naïve Bayes, artificial neural network, logistic regression, and decision tree. RECENT FINDINGS: The increase in blood pressure, both systolic and diastolic, is very harmful to the health because uncontrolled high systolic and diastolic blood pressure can cause various diseases such as congestive heart failure, kidney failure, and cardiovascular disease. There have been many studies examining the factors that influence the occurrence of hypertension, but few studies have used machine learning to predict hypertension. The machine learning models performed well and can be used for predicting whether a person with hypertension with certain characteristics will experience a decrease in their systolic or diastolic blood pressure after treatment with antihypertensive drugs.

Artificial neural network machine learning prediction of the smoking behavior and health risks perception of Indonesian health professionals.

Health professionals (HPs) can play an important role in influencing the smoking behavior of their patients and the implementation of smoke-free workplace policies. In some countries physicians and dentists may not have a no-smoking policy in place. Breathing in other people's tobacco smoke (second-hand smokers) increase the risk of smoking related diseases. Environmental Tobacco smoke ETS causes a similar range of diseases to active smoking, including various cancers, heart disease, stroke, and respiratory diseases. Little is known about the smoking-related attitudes and clinical practices of HPs in Indonesia. Evidence suggests that high smoking rates remain among male HPs; however, the risk perceptions and attitudes to smoking among Indonesian HPs have not been investigated using prediction model artificial neural networks. For this reason, we developed and validated an artificial neural network (ANN) to identify HPs with smoking behavior. The study population consisted of 240 HPs, including 108 (45%) physicians, and 132 (55%) dentists, with more female (n=159) than male participants (n=81) for both professions. Participants were randomly divided into two sets, the training (192) and test (48) sets. The input variables included gender, profession (doctor or dentist), knowledge regarding smoking-related diseases and awareness of smoking provided to their patients, smoke-free policy in place at their workplace, and smoking status. ANN was constructed with data from the training and selection sets and validated in the test set. The performance of ANN was simultaneously evaluated by discrimination and calibration. After the training, we completed the process using the test dataset with a multilayer perceptron network, determined by 36 input variables. Our results suggested that our final ANN concurrently had good precision (89%), accuracy (81%), sensitivity (85%), and area under the curve (AUC; 70%). ANN can be used as a promising tool for the prediction of smoking status based on health risk perceptions of HPs in Indonesia.

Comparative efficacy of digital cognitive behavioral therapy for insomnia: A systematic review and network meta-analysis.

The comparative efficacy of various approaches of digital cognitive behavioral therapy for insomnia (CBTi) is still unclear. This network meta-analysis explored the comparative efficacy of digital CBTi approaches in adults with insomnia. Four electronic databases were searched from inception to June 27, 2020. Primary outcomes were self-reported total sleep time (TST), sleep onset latency (SOL), wake after sleep onset (WASO), sleep efficiency (SE), and insomnia symptoms; these were measured using sleep diaries or valid questionnaires. A random-effects network meta-analysis in a frequentist framework was used. Fifty-four randomized controlled trials comprising 11,815 participants were included. Compared with usual care, web-based CBTi with a therapist demonstrated significantly longer TST (mean difference [MD]: 23.19 min, 95% confidence interval [CI]: 18.98-27.39 min), shorter SOL (MD: -18.76 min, 95% CI -24.20 to -13.31 min), lower WASO (MD: -31.40 min, 95% CI: -36.26 to -26.55 min), and greater SE (MD: 10.37%, 95% CI: 8.08%-12.65%). The surface under the cumulative ranking curve indicates that web-based CBTi with therapists is most likely to be ranked the highest among all treatments, and thus, this network meta-analysis suggests that such a treatment is the optimal intervention for improving sleep duration and SE as well as the reductions in SOL and WASO. PROSPERO REGISTRATION NUMBER: CRD42020171134.

Parent educators for teenage smoking behavior.

Background Several studies have shown that there is a significant relationship between teenagers and parental smoking behavior. This study was to empower parent (smokers and non-smokers) to raise parents' concern, to describe teenagers' knowledge about smoking and its dangers, to reduce the status of teenage smoking behavior, and to decrease the number of cigarettes smoked/day. Methods This was a quasi-experimental study, with a pretest-posttest group design. The respondents were 649 students from the 8th grade in junior high schools from three provinces in Indonesia divided into two intervention groups and one control group. The dependent variable was the implementation of parent educators (smokers and non-smokers) who were trained about smoking and its dangers. Data were analyzed by analysis of variance (ANOVA) and the Kruskal-Wallis test, with a significant level of 0.05. Results The results showed that the smoking parent educator model increased the frequency of parent concern significantly and improved knowledge about the dangers of smoking insignificantly; whereas the non-smoker parent educator model decreased the number of respondents' frequent smoking status insignificantly and reduced the number of cigarettes smoked /day by the frequent smoker respondents significantly. Conclusion The parent educator model can be used for preventing teenage smoking behavior.

Jayapura Teenagers Smoking Behavior.

Smoking behavior is a threat for Indonesian teenagers, including in the city of Jayapura, Papua province. The purpose of this study was to access Jayapura teenagers smoking behavior and knowledge including parents and other family members. The study was conducted on 78 respondents (grade 7, aged 11-14 years old), using cluster random sampling for selecting the public and private junior high school in Jayapura. The data collected was smoking behavior of respondents, parents and other family members (using self-reported questionnaire), and respondents' knowledge about the dangers of smoking (using tests with Cronbach's alpha 0.701). Data were analyzed descriptively and analytically using Chi-square, 95 % level of significant. The results showed 29.3 % of teenagers, 69.23 % of parents and 25.6 % of other family members were smokers, their knowledge was low (an average score of 60.81 out of 100), there was no significant statistical relationship between knowledge and smoking behavior among respondents (p = 0.079), and there is no significant relationship between teenagers behavior with the behavior of the parents (p = 0.609) and other family members (p = 0.578), 87 % of teenagers became smokers because there were individuals who smoke at home.