Clinical Data Science at Children's Hospital Los Angeles

When:
Friday, October 19, 2018, 11:00 am - 12:00 pm PSTiCal
Where:
6th floor large conference room
This event is open to the public.
Type:
AI Seminar
Speaker:
David Ledbetter, CHLA
Video Recording:
https://bluejeans.com/s/uunsf
Description:

Directed by Dr. Randall Wetzel and in partnership with the Laura P. and Leland K. Whittier Foundation, the Virtual Pediatric Intensive Care Unit (VPICU) at Children’s Hospital Los Angeles (CHLA) strives to bring the benefits of information technology to the treatment regime for critically ill children across the country.

For over a decade, the VPICU  has cultivated robust resources to develop novel solutions for some of the most challenging questions in pediatric critical care.

VPICU data scientists partner with CHLA physicians to solve a wide array of problems encountered at patients’ bedsides.  Our data scientists frequently attend rounds and shadow the care team  in the ICU, where they gain an appreciation for current practices and learn the context to which their work will be applied.  In turn, members of the care team learn how to leverage historic data to engineer a broad spectrum of clinical decision support tools.

The VPICU has a data science internship program that teams up aspiring data scientists with CHLA critical care physicians to solve real clinical problems, such as early detection of heparin resistance. Examples of previous intern projects will be presented and discussed.

Mr. David Ledbetter has an extensive and deep understanding of decision theory. He has experience implementing various decision engines, including recurrent and convolutional neural networks. His particular area of focus is in performance estimation, where he has demonstrated a tremendous ability to accurately predict performance on new data in nonstationary, real-world scenarios. David has worked on a number of real-world detection projects, including detecting circulating tumor cells in blood, automatic target recognition utilizing CNNs from satellite imagery, make/model car classification for the Los Angeles Police Department using CNNs, and acoustic right whale call detection from underwater sonobuoys. Recently, David has been developing RNNs to generate personalized treatment recommendations to optimize patient outcomes using electronic medical records from 15 years of data collected from the Children's Hospital Los Angeles Pediatric Intensive Care Unit.

 

« Return to Upcoming Events