• Kristian Solem, Bo Olde, and Leif Sörnmo.
• Department of Electrical and Information Technology, Lund University, Lund SE-220 00, Sweden. kristian.solem@gambro.com
• IEEE Trans Biomed Eng. 2010 Jul 1; 57 (7): 1611-9.

AbstractIntradialytic hypotension is the most common acute complication during conventional hemodialysis treatment. Prediction of such events is highly desirable in clinical routine for prevention. This paper presents a novel prediction method of acute symptomatic hypotension in which the photoplethysmographic signal is analyzed with respect to changes in amplitude, reflecting vasoconstriction, and cardiac output. The method is based on a statistical model in which the noise is assumed to have Laplacian amplitude distribution. The performance is evaluated on 11 hypotension-prone patients who underwent hemodialysis treatment, resulting in seven events with acute symptomatic hypotension and 17 without. The photoplethysmographic signal was continuously acquired during treatment as was information on blood pressure and oxygen saturation. Using leave-one-out cross validation, the proposed method predicted six out of seven hypotensive events, while producing 1 false prediction out of 17 possible. The performance was achieved when the prediction threshold was chosen to be in the range 57%-65% of the photoplethysmographic envelope at treatment onset.

20 keywords...

hide…