Design and development of IoT systems that collect data from users to automatically assess their health status and to help make decisions at a preventive or intervention level. The data is collected from questionnaires, environmental and physiological sensors, the latter with wearables such as smart watches, bracelets, headbands, rings, and medical elements such as: oximeter, nasopharyngeal cannula, etc. The data is processed using artificial intelligence techniques such as machine learning or deep learning (such as SVN, Bayesian networks, decision trees, etc.) to identify characteristics that allow users to be classified. We have experimented with it to detect frailty and dependency in the elderly, we are also working on detecting activity, stress and basic emotions. At the architectural level, we work with several alternatives for data storage and processing: cloud, fog and edge computing, also using intermediate mobile devices such as smartphones and ad-hoc networks created between them, in such a way that we can achieve more flexibility and efficiency. . We have already implemented an app that automatically connects the data from the sensors and displays the results in the form of graphs.