Computerized decision support and machine learning applications for the prevention and treatment of childhood obesity: A systematic review of the literature.

BACKGROUND: Digital health interventions based on tools for Computerized Decision Support (CDS) and Machine Learning (ML), which take advantage of new information, sensing and communication technologies, can play a key role in childhood obesity prevention and treatment. OBJECTIVES: We present a systematic literature review of CDS and ML applications for the prevention and treatment of childhood obesity. The main characteristics and outcomes of studies using CDS and ML are demonstrated, to advance our understanding towards the development of smart and effective interventions for childhood obesity care. METHODS: A search in the bibliographic databases of PubMed and Scopus was performed to identify childhood obesity studies incorporating either CDS interventions, or advanced data analytics through ML algorithms. Ongoing, case, and qualitative studies, along with those not providing specific quantitative outcomes were excluded. The studies incorporating CDS were synthesized according to the intervention's main technology (e.g., mobile app), design type (e.g., randomized controlled trial), number of enrolled participants, target age of children, participants' follow-up duration, primary outcome (e.g., Body Mass Index (BMI)), and main CDS feature(s) and their outcomes (e.g., alerts for caregivers when BMI is high). The studies incorporating ML were synthesized according to the number of subjects included and their age, the ML algorithm(s) used (e.g., logistic regression), as well as their main outcome (e.g., prediction of obesity). RESULTS: The literature search identified 8 studies incorporating CDS interventions and 9 studies utilizing ML algorithms, which met our eligibility criteria. All studies reported statistically significant interventional or ML model outcomes (e.g., in terms of accuracy). More than half of the interventional studies (n = 5, 63 %) were designed as randomized controlled trials. Half of the interventional studies (n = 4, 50 %) utilized Electronic Health Records (EHRs) and alerts for BMI as means of CDS. From the 9 studies using ML, the highest percentage targeted at the prognosis of obesity (n = 4, 44 %). In the studies incorporating more than one ML algorithms and reporting accuracy, it was shown that decision trees and artificial neural networks can accurately predict childhood obesity. CONCLUSIONS: This review has found that CDS tools can be useful for the self-management or remote medical management of childhood obesity, whereas ML algorithms such as decision trees and artificial neural networks can be helpful for prediction purposes. Further rigorous studies in the area of CDS and ML for childhood obesity care are needed, considering the low number of studies identified in this review, their methodological limitations, and the scarcity of interventional studies incorporating ML algorithms in CDS tools.

Cross-sectional associations of objectively-measured sleep characteristics with obesity and type 2 diabetes in the PREDIMED-Plus trial.

Study Objectives: To examine independent and combined associations of sleep duration and sleep variability with body composition, obesity and type 2 diabetes (T2D) in elders at high cardiovascular risk. Methods: Cross-sectional analysis of 1986 community-dwelling elders with overweight/obesity and metabolic syndrome from PREDIMED-Plus trial. Associations of accelerometry-derived sleep duration and sleep variability with body mass index (BMI), waist circumference (WC) and body composition were assessed fitting multivariable-adjusted linear regression models. Prevalence ratios (PR) and 95% confidence intervals (CI) for obesity and T2D were obtained using multivariable-adjusted Cox regression with constant time. "Bad sleepers" (age-specific non-recommended sleep duration plus sleep variability above the median) and "good sleepers" (age-specific recommended sleep duration plus sleep variability below the median) were characterized by combining sleep duration and sleep variability, and their associations with these outcomes were examined. Results: One hour/night increment in sleep duration was inversely associated with BMI (ß -0.38 kg/m2 [95% CI -0.54, -0.23]), WC (ß -0.86 cm [95% CI -1.25, -0.47]), obesity (PR 0.96 [95% CI 0.93, 0.98]), T2D (PR 0.93 [95% CI 0.88, 0.98]) and other DXA-derived adiposity-related measurements (android fat and trunk fat, all p < .05). Each 1-hour increment in sleep variability was positively associated with T2D (PR 1.14 [95% CI 1.01, 1.28]). Compared with "good sleepers," "bad sleepers" were positively associated with obesity (PR 1.12 [95% CI 1.01, 1.24]) and T2D (PR 1.62 [95% CI 1.28, 2.06]). Conclusions: This study revealed cross-sectional associations of sleep duration with adiposity parameters and obesity. Sleep duration and sleep variability were associated with T2D. Considering simultaneously sleep duration and sleep variability could have additional value, particularly for T2D, as they may act synergistically.