Thumbnail Image
Publication

Machine learning-enabled medical device materials (MLMDM)

Betz, Kaitlyn M.
; 
Lowe, Beatrice L.
; 
Hirsch, Daniela P.
; 
Hawkins, Clinton L.
; 
Pak, Alexander J.
; 
Lowe, Terry C.
Citations
Altmetric:
Advisor
Editor
Date
2024-04
Date Issued
Date Submitted
Keywords
Collections
2024 Spring Undergraduate Research Symposium
Show all metadata
Files
Thumbnail Image
Betz_Kaitlyn_UGR2024.pdf
Adobe PDF, 4.45 MB
Research Projects
Organizational Units
Journal Issue
URI
https://hdl.handle.net/11124/179045
 https://doi.org/10.25676/11124/179045
Embargo Expires
Abstract
Machine learning (ML) methods can provide exceptional enhancements to both the performance and manufacturing of medical device materials. Enhanced materials and methods to make them can transform medical device fabrication and healthcare. Improved quality assurance and real-time error detection become feasible with ML algorithms. Fabrication steps can be implemented with greater precision, efficiency, and waste minimization. Production parameters can be fine-tuned, including the prospect of tailoring materials and devices to individuals, enabling personalized care. We highlight three examples of ML technologies under development in our Transdisciplinary Nanostructured Materials Research Team (TNMRT). We are developing Convolutional Neural Networks (CNN) to develop 1) antimicrobial copper surface nanostructures, 2) ferrofluid methods to detect magnetic phases in stainless steel, and 3) optical image analyses to predict alloy formability to fabricate surgical devices.
Associated Publications
Rights
Copyright of the original work is retained by the author.
Embedded videos