Traditional health systems mostly rely on rules created by experts to offer adaptive interventions to patients. However, with recent advances in artificial intelligence (AI) and machine learning (ML) techniques, health-related systems are becoming more sophisticated with higher accuracy in providing more personalized interventions or treatments to individual patients. In this paper, we present an extensive literature review to explore the current trends in ML-based adaptive systems for health and well-being. We conduct a systematic search for articles published between January 2011 and April 2022 and selected 87 articles that met our inclusion criteria for review. The selected articles target 18 health and wellness domains including disease management, assistive healthcare, medical diagnosis, mental health, physical activity, dietary management, health monitoring, substance use, smoking cessation, homeopathy remedy finding, patient privacy, mobile health (mHealth) apps finder, clinician knowledge representation for neonatal emergency care, dental and oral health, medication management, disease surveillance, medical specialty recommendation, and health awareness. Our review focuses on five key areas across the target domains: data collection strategies, model development process, ML techniques utilized, model evaluation techniques, as well as adaptive or personalization strategies for health and wellness interventions. We also identified various technical and methodological challenges including data volume constraints, data quality issues, data diversity or variability issues, infrastructure-related issues, and suitability of interventions which offer directions for future work in this area. Finally, we offer recommendations for tackling these challenges, leveraging on technological advances such as multimodality, Cloud technology, online learning, edge computing, automatic re-calibration, Bluetooth auto-reconnection, feedback pipeline, federated learning, explainable AI, and co-creation of health and wellness interventions.

Adults are recommended to engage in 150 min of moderate (MPA) to vigorous (VPA) aerobic physical activity per week, with the public health message of obtaining 3000 steps in 30 min. There is a paucity of research on step rate thresholds that correspond to absolute MVPA (moderate = 3 METs, vigorous = 6 METs) with no research evaluating adult relative MVPA (moderate = 40% VO_2max, vigorous = 60% VO_2max). Anthropometric differences also influence intensity-related step rate thresholds. The purpose of this study was to identify step rates across a range of walking intensities so that mathematical models incorporating anthropometric factors could be used to identify individualized MVPA step rate thresholds. Forty-three adults (25♀; age = 39.4 ± 15.2 years) completed a staged treadmill walking protocol with pedometers and indirect calorimetry: six-minutes at 2.4, 3.2, 4.0, 5.6, 6.4, 7.2 km/h. Mathematical modelling revealed absolute and relative MPA step rate thresholds of ~100 steps/minute (spm) and ~125 spm, respectively. VPA corresponded to step rates of ~133 spm and ~139 spm for absolute and relative thresholds respectively. The current public message of 3000 steps in 30 min is valid for absolute MPA. However, VPA is achieved at higher thresholds than previously reported, more than 130 spm for healthy adults.

Health care providers (HCPs) are entrusted with providing credible health-related information to their patients/clients. Patients/clients who receive physical activity and exercise (PAE) advice from an HCP typically increase their PAE level. However, most HCPs infrequently discuss PAE or prescribe PAE, due to the many challenges (e.g., time, low confidence) they face during regular patient care. The purpose of this study was to ascertain HCPs’ perspectives of what could be done to promote PAE in health care. HCPs (n = 341) across Nova Scotia completed an online self-reflection survey regarding their current PAE practices and ideas to promote PAE. The sample consisted of 114 physicians, 114 exercise professionals, 65 dietitians, and 48 nurses. Quantitative textual analysis (frequency of theme ÷ number of respondents) was performed to identify common themes to promote PAE in health care. In the pooled sample, the primary theme cited was to increase the availability of community programs (24.1% of respondents), followed by more educational opportunities for providers (22.5%), greater promotion of PAE from HCPs (17.1%), reducing financial barriers experienced by patients/clients (16.3%), and increasing availability of qualified exercise professionals (15.0%). Altogether, increased PAE education and greater availability of affordable community PAE programs incorporating qualified exercise professionals, would reduce barriers preventing routine PAE promotion and support the promotion of PAE in Nova Scotia.

Mobile and tablet apps, ubiquitous and pervasive computing, wearable computing and domotics for health.

Canadian 24 h movement guidelines recommend engaging in >150 min/week of moderate–vigorous-intensity physical activity and ≤8 h/day of sedentary time. Half of Canadian post-secondary students do not meet physical activity or sedentary time guidelines. This pan-Canadian study aimed to (1) identify commonly cited motivators/barriers to exercise, and (2) determine which motivators/barriers were most influential for attaining physical and sedentary activity guidelines. A total of 341 respondents (279 females, 23 ± 4 years old, 53% met activity guidelines, 49% met sedentary guidelines) completed an online survey regarding undergraduate student lifestyle behaviours. Improved physical health (74% of respondents), mental health (67%), physical appearance (60%), and athletic performance (28%) were the most common motivators to exercise. The most common barriers were school obligations (68%), time commitments (58%), job obligations (32%), and lack of available fitness classes (26%). Students citing improved athletic performance (odds ratio (OR) = 1.94, p = 0.02) were more likely to adhere to activity guidelines, while those who selected physical health (OR = 0.56, p = 0.03) and physical appearance (OR = 0.46, p = 0.001) as motivators were less likely to meet activity guidelines. Students who cited school obligations as a barrier were less likely (OR = 0.59, p = 0.03) to meet sedentary guidelines. The motivators and barriers identified provide a foundation for university-led initiatives aimed at promoting physical activity and reducing sedentary time among undergraduate students. Strategies that positively re-frame students’ physical health and appearance-based motivations for exercise may be particularly useful in helping more students achieve national activity recommendations.

Adults and older adults are recommended to engage in 150 minutes of moderate (MPA) to vigorous (VPA) aerobic physical activity (MVPA) per week, with the heuristic message of 3000 steps in 30 minutes (100 steps per minute [spm]). However, this message is based on adult populations, with a paucity of research on step-rate thresholds that correspond to absolute MVPA (moderate=3 metabolic equivalents [METs], vigorous=6 METs) and relative MVPA (moderate=40% estimated METmax, vigorous=60% estimated METmax) in older persons, who have lower stride lengths and a lower exercise capacity. Also, there is a need to consider the influence of anthropometric differences when quantifying the relationship between step rate and intensity-related physical activity. This study assessed absolute and relative MVPA step-rate thresholds and anthropometric factors (ie, height, leg length, and body mass index [BMI]) in older adults. Nineteen older adults (7 females; age 69 years, SD 2, BMI 26 kg/m2, SD 4) completed a staged treadmill walking protocol: six minutes at 2.4, 3.2, 4.0, 5.6, and 6.4 km/h. Steps were manually counted and volume rate of oxygen consumed (VO2) was measured via indirect calorimetry. Aerobic fitness was estimated via the submaximal single-stage treadmill protocol. When BMI was considered, mixed effects modeling revealed absolute and relative MPA step-rate thresholds of 108 spm and 117 spm, respectively. Absolute and relative VPA corresponded to step rates of 135 spm and 132 spm, respectively. Neither height nor leg length improved the ability of the model to predict stepping cadence from METs. In general, older adults need to walk faster than 100 spm (ie, approximately 110 spm) to reach MPA and in excess of approximately 130 spm to achieve VPA, depending on BMI status. Health care professionals and researchers should adjust cadence-based recommendations for differences in BMI in their older patients and consider using relative intensity to most appropriately tailor their physical activity recommendations.