The quality of primary healthcare services and life expectancy have been significantly impacted by advances in medical science and technology in recent decades. However, new challenges have emerged as a result of rising elderly demographics and global events such as pandemics, requiring innovative medical strategies and solutions. Mobile and embedded image-based medical applications have been shown to be effective in a variety of medical fields, and video-based medical solutions and recent research offer promising opportunities for improving and transforming primary healthcare services, particularly in the areas of non-invasive, contactless, and remote diagnosis assistance. While many advanced computer vision-based healthcare and medical diagnosis methods have been developed, their practical implementation as embedded or remote solutions remains a challenge. This dissertation aims to enable the use of computer vision for medical diagnosis assistance from facial and body behavior in camera-based embedded devices (such as mobile phones or smart glasses) or via remote video connections (e.g., video conference services). During the research new methods and techniques are developed towards an effective biosignal extraction, demonstrating it through several medical use cases and their application in real scenarios. By addressing the challenges and peculiarities of these implementations, this research seeks to provide a better understanding of how to build the future of remote primary healthcare platforms.

2023