Effectiveness of eHealth weight management interventions in overweight and obese adults from low socioeconomic groups: a systematic review

Prediction of Snacking Behavior Involving Snacks Having High Levels of Saturated Fats, Salt, or Sugar Using Only Information on Previous Instances of Snacking: Survey- and App-Based Study

BACKGROUND

Consuming high amounts of foods or beverages with high levels of saturated fats, salt, or sugar (HFSS) can be harmful for health. Many snacks fall into this category (HFSS snacks). However, the palatability of these snacks means that people can sometimes struggle to reduce their intake. Machine learning algorithms could help in predicting the likely occurrence of HFSS snacking so that just-in-time adaptive interventions can be deployed. However, HFSS snacking data have certain characteristics, such as sparseness and incompleteness, which make snacking prediction a challenge for machine learning approaches. Previous attempts have employed several potential predictor variables and have achieved considerable success. Nevertheless, collecting information from several dimensions requires several potentially burdensome user questionnaires, and thus, this approach may be less acceptable for the general public.

OBJECTIVE

Our aim was to consider the capacity of standard (unmodified in any way; to tailor to the specific learning problem) machine learning algorithms to predict HFSS snacking based on the following minimal data that can be collected in a mostly automated way: day of the week, time of the day (divided into time bins), and location (divided into work, home, and other).

METHODS

A total of 111 participants in the United Kingdom were asked to record HFSS snacking occurrences and the location category over a period of 28 days, and this was considered the UK dataset. Data collection was facilitated by a purpose-specific app (Snack Tracker). Additionally, a similar dataset from the Netherlands was used (Dutch dataset). Both datasets were analyzed using machine learning methods, including random forest regressor, Extreme Gradient Boosting regressor, feed forward neural network, and long short-term memory. We additionally employed 2 baseline statistical models for prediction. In all cases, the prediction problem was the time to the next HFSS snack from the current one, and the evaluation metric was the mean absolute error.

RESULTS

The ability of machine learning methods to predict the time of the next HFSS snack was assessed. The quality of the prediction depended on the dataset, temporal resolution, and machine learning algorithm employed. In some cases, predictions were accurate to as low as 17 minutes on average. In general, machine learning methods outperformed the baseline models, but no machine learning method was clearly better than the others. Feed forward neural network showed a very marginal advantage.

CONCLUSIONS

The prediction of HFSS snacking using sparse data is possible with reasonable accuracy. Our findings offer a foundation for further exploring how machine learning methods can be used in health psychology and provide directions for further research.

Umbrella review of social inequality in digital interventions targeting dietary and physical activity behaviors

Digital interventions are increasingly utilized as a lever to promote population health, yet not everyone may equally benefit from them. This umbrella review pooled the insights from available systematic and scoping reviews regarding potential social inequalities in digital intervention uptake, engagement and effectiveness, focusing on the promotion of weight-related behaviors (diet, physical activity, sedentary behavior) and weight loss (maintenance) in adults. Six databases were searched from 1970 to October 2023. Forty-six reviews were included, of which most focused on physical activity and intervention effectiveness. Age and gender/ sex differences were most frequently studied. Most reviews found digital interventions to be effective irrespective of age, while men benefitted more from digital interventions than women. Other inequality indicators (e.g., income, education) were rarely studied, despite them being potential causes of a digital divide. A more systematic and thorough exploration of inequalities in digital health is required to promote health for all.

Efficacy of in-person versus digital enhanced lifestyle interventions in adults with overweight and obesity

Background

Lifestyle interventions (LIs) are the cornerstone for obesity management. The Mayo Clinic Diet (MCD) offers two approaches for LIs: the In-Person LI (IPLI) and the Digital Enhanced LI (DELI). The IPLI includes a 2-day in-person program with monthly follow-ups, whereas the DELI provides on-demand digital tools. The comparative efficacy of these approaches is currently unknown.

Methods

This retrospective study included two cohorts of adults with a body mass index (BMI) of ≥25 kg/m2 and weight metrics at least 3 months after starting either the IPLI or DELI program. The primary endpoint was the total body weight loss percentage (TBWL%) at 6 months.

Results

The study included 133 participants in the IPLI cohort (mean age 46.3 years, 65.4 % female, BMI 36.4) and 9603 in the DELI cohort (mean age 60.1 years, 85.0 % female, BMI 33.1). The DELI group achieved superior TBWL% at 1, 3, and 6 months compared to the IPLI group (3.4 % vs. 1.5 %, 4.7 % vs. 2.4 %, 5.3 % vs. 2.9 %, respectively; p < 0.001). After adjusting for age, gender, and starting weight, the DELI group maintained a higher TBWL% (difference 2.0 %; 95 % CI [1.0, 3.0], p < 0.001) and a greater proportion of participants achieved >5 % TBWL at 6 months (OR 1.66; 95 % CI [1.08, 2.55], p < 0.023).

Conclusion

The DELI approach resulted in superior weight loss outcomes compared to the IPLI. Further research is needed to explore how digital tools can improve weight loss effectiveness.

Influence of eHealth Literacy and Health Promotion Behavior on Body Mass Index of Workers in the Public Sector

Background

Adequate eHealth literacy and health promotion behavior (HPB) are important to achieve good health-related quality of life. There is limited information on the influence of eHealth literacy and HPB on body mass index (BMI) in our setting and among public service workers.

Objectives

This study assessed the eHealth literacy, HPB, and BMI of public service workers and determined the influence of eHealth literacy and HPB on BMI.

Design

A descriptive cross-sectional design was adopted.

Methods

A simple random sampling technique was used to select 440 public service workers from civil service of redacted. A structured questionnaire was used to collect data on socio-demographics, eHealth literacy, and HPB. Weight and height were measured and BMI was calculated. Data were analyzed using frequency, percentage, mean, standard deviation, and logistic regression analysis. The significant level was set at 0.05.

Results

More than one quarter (28.2%) of respondents had low eHealth literacy, and more than one third (42.5%) had inadequate (30.0% fair and 12.5% poor) HPB. An average (50.5%) had a level of obesity that ranged from preobesity to type 2 obesity. There was a significant association between eHealth literacy and HPB with the BMI of respondents at p < .05.

Conclusion

There was inadequate eHealth literacy and HPB among public service workers. An average of the workers had a level of obesity that ranged from pre-obesity to type 2 obesity. There was a significant association between eHealth literacy and BMI and also between HPB and BMI of respondents. Community health professionals should assist public service workers to develop competencies and skills useful in evaluating health information on the Internet and applying such information to make informed decisions.

An exploration of customers' perceptions, preferences, experiences, and feasibility of offering standardized portions in restaurants

Excess caloric intake increases the risk of weight gain, and diet-related chronic diseases. Restaurants play an integral role in the portions of food people consume. Standardization of portion sizes in restaurants can help customers recognize appropriate portions. Through customer interviews, we aimed to assess and understand the feasibility, perceptions, and acceptability of standardized portions in restaurants. Kaiser Permanente partnered with three restaurants in Southern California to create alternative menu options of meals that would not exceed 700 calories. Kaiser Permanente members who lived within a 5-mile radius of the restaurants were informed through email about the study. Customers (N=33), who dined at one of the restaurants participated in a one-on-one semi-structured interview. Interviews were recorded, typed, transcribed verbatim, and analyzed using thematic analysis. Four themes emerged from the analysis: 1) Customers perceive standard portions as a better choice and the benefits outweigh regular portions; 2) Individual and restaurant-related factors may influence portion preferences; 3) Restaurant portions are perceived to be in excess of what customers need; and 4) Portion standardization is an evolving area for restaurants. Our findings suggest positive perceptions and acceptance of standardized portions among restaurant customers. Customer awareness and restaurant standardization procedures can improve customers' dining experience.

eHealth in obesity care

Obesity in adults is a growing health concern. Although effective, current treatment options have not been able to overcome the various factors that contribute toward rising obesity rates. eHealth might hold the capacity to improve the effectiveness, delivery and flexibility of some of these treatments. Here, we show that eHealth lifestyle change interventions delivered through smartphones (mHealth) can facilitate significant weight loss, making mHealth an attractive adjunct to clinical obesity care. However, evidence is currently limited to short-term effects, and is also lacking with regards to effectiveness based on socioeconomic status and ethnic group. This raises concerns around the potential and inadvertent widening of obesity prevalence disparities between groups as mHealth lifestyle change interventions are increasingly used in obesity care. Thus, we also describe opportunities to address these concerns and gaps in evidence.