Towards an Intelligent Stethoscope

Introduction

Screenshot 2015-07-12 09.51.31Though in some ways replaced by ultrasound technology, cardiac auscultation–using a stethoscope to listen to a patient’s heart–remains an important screening modality for recognizing heart disease. Auscultation serves as a cost-effective screening tool for heart disease and is of particular importance in several clinical scenarios. Less emphasis has been placed on training US clinicians in auscultation, however, making this something of a “lost art.” This may delay a patient’s diagnosis of heart disease.

Solution

Using a digital stethoscope for input, a trained machine learning algorithm could help support the listener with an interpretation of heart Screenshot 2015-07-12 09.54.47sounds. Much of the work I performed was in the important phases of training called normalization and feature selection. Normalization involves making small optimizations on the original sounds that help reduce uninformative variation. Feature selection then determines which characteristics are most important for distinguishing normal sounds from abnormal sounds.

Challenges

  • Obtaining standardized patient heart sounds
  • Normalizing heart sounds of different amplitudes and rates
  • Dividing heart sound signals into individual beats
  • Developing a strategy for selecting optimal features to train a neural network

Awards

  • Dupont Award for Research in Medicine and Health
  • New York Academy of Sciences Francine Salom Memorial Award
  • Bausch and Lomb Science Award

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s