Doctoral Thesis: Tackling Key Challenges to Guide Clinical Decisions in Cardiovascular Diseases

Thursday, May 5
2:00 pm

36-428

Wangzhi Dai

Abstract:
Machine learning models in healthcare have been widely used in a number of contexts ranging from clinical risk stratification to image-guided diagnosis and prognostication. Nevertheless, key challenges remain from both clinical and technical perspectives. In the case of prediction models, for example, predicting the occurrence of rare clinical events is often hard, mainly due to extreme class imbalance in the training data. Estimating treatment effect, on the other hand, is hindered by the fact that the common support assumption is not a priori guaranteed to be valid in non-randomized data. This thesis develops and applies approaches that address these challenges in order to obtain clinically useful insights.
In the first part of the thesis, we aim to tackle these obstacles in the context of Acute Coronary Syndrome (ACS) – a condition where blood flow to the heart suddenly becomes compromised. We use a contrastive Variational Autoencoder, an approach that models both the majority and minority classes as having shared latent properties, to address predicting rare adverse clinical outcomes after ACS and quantifying common support for estimating the effect of therapies for ACS. In the second part of the thesis, we turn to a challenging clinical problem that uses ultrasound imaging for diagnosis and prognostication. Cardiac ultrasound (or echocardiography) plays a central role in the diagnosis and management of patients with suspected aortic stenosis (AS) – a disorder where one of the valves in the heart does not fully open. A complete echocardiographic study is typically performed by a trained sonographer who acquires videos of multiple views of the heart and echocardiographers (cardiologists who specialize in the analysis of echocardiograms) interpret these videos, yielding clinically useful information. To facilitate the acquisition and interpretation of echocardiographic data, we developed a deep learning model that uses a single echocardiographic view (as opposed to use all of the acquired views) to diagnoses severe AS. Our approach may enable early detection of severe AS by non-specialists.

Details

  • Date: Thursday, May 5
  • Time: 2:00 pm
  • Location: 36-428
Additional Location Details:

Thesis Supervisor: Prof. Collin Stultz

Zoom link:
Please contact Wangzhi Dai (wzhdai@mit.edu) for a zoom link.