In this study, researchers at UCLA Medical Center in Los Angeles applied machine learning to arterial pressure waveforms to develop an algorithm that predicted intraoperative hypotension 15 minutes before it occurred in 84% of cases.
Two sets of data were used to build the algorithm. One set consisted of 1,334 patient records with 545,959 minutes of arterial pressure waveform recordings, which included 25,461 episodes of hypotension. A second data set included 204 patient records with 33,236 minutes of waveform recordings and 1,923 episodes of hypotension.
The researchers found the algorithm accurately predicted intraoperative hypotension 15 minutes before it occurred in 84% of cases, 10 minutes before in 84% of cases, and 5 minutes before in 87% of cases.
This is the first time machine learning and computer science techniques have been applied to complex physiological signals obtained during surgery, the authors say.Read More >>