Algorithm predicts low blood pressure during surgery with 84% accuracy
Researchers have developed an algorithm capable of predicting low blood pressure, that could occur during surgery with 84 percent accuracy. Study findings were published June 11 in Anesthesiology.
Detecting hypotension early crucial in reducing patient harm during surgery. In this study, researchers outlined the development of a machine learning algorithm capable of predicting hypotension early. The algorithm observes signs from data that could predict the onset of hypotension in surgical patients.
"Physicians haven't had a way to predict hypotension during surgery, so they have to be reactive, and treat it immediately without any prior warning. Being able to predict hypotension would allow physicians to be proactive instead of reactive," said lead researcher Maxime Cannesson, MD, PhD, professor of anesthesiology and vice chair for perioperative medicine at UCLA Medical Center in Los Angeles. "By finding a way to predict hypotension, we can avoid its complications, which can include postoperative heart attack and acute kidney injury, that can lead to death in some cases."
Researchers developed the algorithm with two data sets. The first contained data of 1,334 patient records with 545,959 minutes of arterial pressure waveform recordings—a total of 25,461 incidents of hypotension. The second set, which was used for validation of the algorithm, contained 204 patient records with 33,236 minutes of arterial pressure waveform recordings and 1,923 episodes of hypotension.
Overall, 2.6 million bits of information were used to build the algorithm. When tested, the algorithm showed it could accurately predict intraoperative hypotension 15 minutes before it occurred in 84 percent of cases. The algorithm also predicted hypotension 10 minutes before in 84 percent of cases and 5 minutes before 87 percent of the time.
"It is the first-time machine learning and computer science techniques have been applied to complex physiological signals obtained during surgery," Cannesson said. "Although future studies are needed to evaluate the real-time value of such algorithms in a broader set of clinical conditions and patients, our research opens the door to the application of these techniques to many other physiological signals, such as EKG for cardiac arrhythmia prediction or EEG for brain function. It could lead to a whole new field of investigation in clinical and physiological sciences and reshape our understanding of human physiology."
Cara joined TriMed Media in 2016 and is currently a Senior Writer for Clinical Innovation & Technology. Originating from Detroit, Michigan, she holds a Bachelors in Health Communications from Grand Valley State University.