Qualitative Data-Driven Generative Design for Personalized Wearable Scalp Cooling Devices

Following an extensive research and development phase [1,2,3], in a funded project conducted over the past few years, personalized scalp cooling caps are developed with generative design tools using cranial data collected from healthcare professionals to provide an optimally fitting wearable cryotherapy device utilizing CAD packages and design tools. Recent research [4] demonstrated personalized cooling caps are essential to improve Scalp Cooling success rates/efficacy to over 80% through a perfect fit. Perfect fit requires extensive iterative research with multidisciplinary global healthcare professionals, scientists, and Designers. Following a study where cranial parameters were studied that could provide the optimal fit of head wearable designs, several pilot studies were able to prove a 93.8% accuracy rate against control for human head data collection. Following this, collected data would be used to generate CAD models to be 3D printed, providing accurately fitting cooling caps that represented the measured patient's head with high precision. This approach utilizes a qualitative approach to mass customization whereby individuals’ cranial data drives the generative design of CAD models for mass personalization. Generative design applies algorithms to parameters to generate hundreds of thousands of design variations [5]. It is a powerful design tool that allows you to exploit additive manufacturing potential [6] fully. The Generative design process is largely viewed as a collaborative, interdisciplinary activity that is more flexible [7], allowing for multiple stakeholders to have their input in the design process to develop a more suitable product. Generative design has been used in mass customization to fully harness the design opportunities provided by advanced manufacturing technologies to improve user satisfaction [8]. Data-driven design data-driven frameworks can be improved by integrating multiple types of data to improve the automation level and performance and boost design efficiency [8]. Similar approaches have investigated data-driven customization for ankle braces [9] and glasses [10]. Parametric design's ability to produce variations and bespoke products [11], combined with digital fabrication's ability to physicalize this variation, enables mass production of non-standard products [12]. Many companies are adopting parametric-oriented digital interfaces that allow the user to change design parameters to personalize a product.