MIT E25-111 and Zoom
(See below for full information)
Data-driven approaches for complex systems: leveraging machine learning, materials science, and manufacturing for new biomedical technologies
The advancement of human health and well-being often involves interdisciplinary problems and complex systems that are not yet fully understood. This thesis integrates computational and experimental approaches to enhance our understanding and control of engineered systems that lie at the interface of machine learning, materials science, and manufacturing. Specifically, this work demonstrates the design of supervised machine learning for biomedical engineering tasks, the optimization of soft granular biomaterials using data-driven approaches, and the proof-of-concept development of a new transcatheter additive manufacturing platform.
Part 1 develops an approach for high-resolution, multifactorial machine learning experiments. This workflow is applied to a diverse set of problems in the biomedical engineering domain, generating large meta-datasets covering all phases of the hierarchical machine learning optimization and evaluation process. I then describe the underlying patterns and heterogeneity in these rich datasets and delineate empirical guidelines for the rigorous and reliable adoption of machine learning for biomedical engineering problems. Part 2 leverages the insights from Part 1 to develop a flexible and robust data-driven modeling pipeline for complex soft matter. The pipeline can be applied after each round of empirical exploration to build predictive models, identify critical parameters, and generate data-driven design frameworks. I use this approach to optimize the structures, properties, and performance profiles of soft granular biomaterials for injection- and extrusion-based biomedical applications. Part 3 leverages the optimized materials from Part 2 to develop a microgel-based transcatheter additive manufacturing technology for minimally-invasive, patient-specific biofabrication. I present proof-of-concept data for critical features of the platform, including controlled transcatheter material delivery to distant target locations, rapid in situ structuration of arbitrary 3D constructs, and reliable scaffold stabilization to ensure long-term implant integrity. Taken together, this work opens new avenues for data-driven biomedical engineering and contributes to the development of new technologies to improve patient outcomes.
Thesis Supervisor:
Ellen T. Roche, PhD
Latham Family Career Development Professor; Associate Professor of Mechanical Engineering and of the Institute for Medical Engineering and Science, MIT
Thesis Committee Chair:
Lydia Bourouiba, PhD
Associate Professor of Civil and Environmental Engineering, Core Faculty of the Institute for Medical Engineering and Science, MIT
Thesis Readers:
Jennifer A. Lewis, PhD
Hansjörg Wyss Professor of Biologically Inspired Engineering, John A. Paulson School of Engineering and Applied Sciences, Harvard
Faez Ahmed, PhD
d'Arbeloff Career Development Professor in Engineering Design, Assistant Professor of Mechanical Engineering, MIT
------------------------------------------------------------------------------------------------------
Zoom invitation –
Connor Verheyen is inviting you to a scheduled Zoom meeting.
Topic: Connor Verheyen Thesis Defense
Time: May 16, 2023 09:00 AM Eastern Time (US and Canada)
Your participation is important to us: please notify hst [at] mit.edu (hst[at]mit[dot]edu), at least 3 business days in advance, if you require accommodations in order to access this event.
Join Zoom Meeting
https://mit.zoom.us/j/94457038942
Password: 807882
One tap mobile
+16465588656,,94457038942# US (New York)
+16699006833,,94457038942# US (San Jose)
Meeting ID: 944 5703 8942
US : +1 646 558 8656 or +1 669 900 6833
International Numbers: https://mit.zoom.us/u/ac5IxM9D6w
Join by SIP
94457038942 [at] zoomcrc.com
Join by Skype for Business
https://mit.zoom.us/skype/94457038942