Medical products, especially implants, are subject to the highest material requirements and require a high degree of individualization. Additively manufactured implants, including those made from Ti-6Al-4V, offer a large degree of flexibility and individualization in terms of design. However, due to the process, there is also the occurrence of internal defects. These defects are controlled below a volume percentage during the manufacturing process, but post-densification through hot isostatic pressing is often necessary. This process involves sealing the defects through high temperature and pressure, resulting in a final product with no internal defects.
In this tension between the requirements for implants, their individualization and functionalization, and their materials, there is great potential to rethink implant materials. Three thematic complexes can be derived from this:

• Functionalization: Antibacterial properties through alloy adjustment
• Improvement: Enhanced bone-implant integration through lattice structures (crack-resistant and auxetic structures)
• Safety: Reduced risks through a higher understanding across process steps

In all three thematic complexes, there is significant potential to accelerate processes and work more resource-efficiently by employing machine learning. The highly complex interplay of process parameters, conditions, alloy elements, and design influences on the micro and macro levels can be described using machine learning.
This presentation aims to highlight the approaches, research subjects, and goals of the thematic complexes investigated at Leibniz-IWT in the field of additive manufacturing, with a connection to medical technology and machine learning.