Researchers at Children’s Hospital Los Angeles are working to understand how a condition that can be difficult to spot, known as patient-ventilator asynchrony — PVA for short — may affect children who need ventilator support. The research is an area that has not been widely studied until now, according to an Aug. 7 news release.
Machine learning, an AI-powered tool that can be trained to detect patterns and analyze data, is central to the ongoing research funded by the NIH and led by Robinder Khemani, MD, the attending physician in pediatric intensive care at Children’s Hospital Los Angeles.
"There are many types of PVA, but we still don’t know which PVA subtypes are most harmful or are the most frequent," Dr. Khemani said in a statement. "We need to develop a common set of definitions and measurements, especially for pediatric patients."
For their research, a team of experts, including Dr. Khemani, will accumulate measurements from and then combine that information with an analysis of data from 350 other children in clinical trials, including one that is testing a ventilator strategy. This will then inform the team what adjustments, data and measurements to use when developing the machine learning algorithm.
"By the end of this project, we hope to have developed these algorithms and validate that they work in three different hospitals using data from many different children," Dr. Khemani said in a statement. "Simultaneously we will build a tool to automatically detect PVA by analyzing ventilator data through machine-learning algorithms. We will test how well the tool helps providers to identify the minute-to-minute changes in patients and potentially alert the bedside team that an adjustment to the ventilator may be needed."