MEMP PhD Thesis Defense (1:00pm): Daphne Schlesinger

Physiology-inspired deep learning for improved heart failure management

Heart failure is an increasingly prevalent condition, which is associated with significant morbidity and mortality. While there has been profound progress in the development of pharmacotherapy and specialized devices for heart failure in recent decades, challenges remain in disease diagnosis and management. One of the key issues is that central hemodynamics and cardiac mechanics, the quantities that characterize the state of a heart failure patient, are difficult to measure. Deep learning methods have shown promise for addressing problems in clinical medicine but are fundamentally limited by their opacity to interpretation, which inhibits model trust and adoption. In this thesis, we propose physiology-inspired deep learning approaches to improve heart failure management. First, we describe a deep learning model to non-invasively infer central hemodynamics from the 12-lead electrocardiogram, a signal commonly obtained during a normal clinical visit. The model is also associated with a trust score formulated based on physiologic knowledge. We then extend this work to develop a new model for the single lead electrocardiogram, which is successfully applied to a prospective wearable device data set without fine-tuning, enabling at-home central hemodynamic monitoring. Finally, we propose a novel deep learning framework that explicitly incorporates knowledge of cardiovascular physiology, allowing for the direct inference of cardiac mechanics in patients with heart failure in the intensive care setting. The approach is evaluated on both a synthetic data set and on clinical data. The suite of methods described can advance heart failure care by enabling non-invasive central hemodynamic monitoring and minimally-invasive inference of cardiac mechanics.

Thesis Supervisor:
Collin M. Stultz, MD, PhD
Nina T. and Robert H. Rubin Professor, Electrical Engineering & Computer Science and Institute for Medical Engineering & Science, MIT

Thesis Committee Chair:
Thomas Heldt, PhD
W.M. Keck Career Development Professor, Electrical and Biomedical Engineering, MIT

Thesis Reader:
Peter Szolovits, PhD
Professor, Electrical Engineering and Computer Science, MIT

------------------------------------------------------------------------------------------------------

Zoom invitation –

Daphne Schlesinger is inviting you to a scheduled Zoom meeting.

Topic: Daphne’s Thesis Defense
Time: Jan 30, 2024 01:00 PM 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/95653181153
Password: cardiology

One tap mobile

+16465588656,,95653181153# US (New York)
+16699006833,,95653181153# US (San Jose)

Meeting ID: 956 5318 1153

US: +1 646 558 8656 or +1 669 900 6833

International Numbers: https://mit.zoom.us/u/aJqAAXr48 

Join by SIP
95653181153 [at] zoomcrc.com (95653181153[at]zoomcrc[dot]com)

Join by Skype for Business
https://mit.zoom.us/skype/95653181153