Cardiovascular disease (CVD) is a global health concern, particularly among older adults, linked to fat and sugar-rich diet, inactivity, tobacco smoking, as well as genetic factors. Regular exercise and a balanced diet are recommended to reduce CVD risk. Recently, the use of computer of mobile phone application platforms have become promenent tools for personal health interventions and guidance. Although research findings of the efficacy of mobile health apps has had mixed results, improved user health and lowered risk of CVD has been seen with regular engagement. Shae, an AI-driven mobile health platform, offers personalized lifestyle guidance based on an individual's phenotype. The aim of this study is to assess whether engagement with the online platform, Shae, decreases Framingham non-laboratory CVD risk score over time.The study collected data from 1684 participants who engaged with the Shae online platform for at least 3-months between May 2014 and March 2018. After applying exclusion criteria, 5225 complete assessment entries remained for analysis. The Shae platform assessed health, predicted future risks, and recommended personalized interventions. Data included anthropometric measurements and survey responses, converted for standardized analysis. Descriptive statistics were calculated for participants' characteristics and compared across gender and age groups, in alignment with established cardiovascular disease (CVD) risk factors. A linear mixed-effect regression model was employed to assess changes in CVD risk over time. This research aimed to evaluate the impact of personalized health interventions on CVD risk in diverse demographic groups.CVD risk score, when adjusted for age, decreased by 11.2% following 24 months of engagement with the Shae app, with men 45 years and older seeing the largest decrease (16.1%), and the lowest decrease seen in women under 55 years (10%). Use of the Shae app was primarily by women (85%).This study assessed the impact of engagement with the mHealth app, Shae, on reducing CVD risk. Results revealed a significant CVD risk reduction, notably in men over 45. mHealth apps like Shae provide personalized health assessments, activity tracking, nutrition advice, and medication reminders, enabling proactive cardiovascular health management. Increased physical activity and better blood pressure control were key factors in risk reduction. Tailored interventions for high-risk groups align with previous research. Given the importance of preventing CVD, mHealth apps hold promise. This 24-month study offers robust insights, and the focus on individual phenotypes enhances engagement and health outcomes.

Malnutrition is a serious and prevalent health problem in the older population, and especially in hospitalised or institutionalised subjects. Accurate and early risk detection is essential for malnutrition management and prevention. M-health services empowered with Artificial Intelligence (AI) may lead to important improvements in terms of a more automatic, objective, and continuous monitoring and assessment. Moreover, the latest Explainable AI (XAI) methodologies may make AI decisions interpretable and trustworthy for end users.This paper presents a novel AI framework for early and explainable malnutrition risk detection based on heterogeneous m-health data. We performed an extensive model evaluation including both subject-independent and personalised predictions, and the obtained results indicate Random Forest (RF) and Gradient Boosting as the best performing classifiers, especially when incorporating body composition assessment data. We also investigated several benchmark XAI methods to extract global model explanations. Model-specific explanation consistency assessment indicates that each selected model privileges similar subsets of the most relevant predictors, with the highest agreement shown between SHapley Additive ExPlanations (SHAP) and feature permutation method. Furthermore, we performed a preliminary clinical validation to verify that the learned feature-output trends are compliant with the current evidence-based assessment.