Hypotension Risk Prediction via Sequential Contrast Patterns of ICU Blood Pressure

Abstract

Acute hypotension is a significant risk factor for in-hospital mortality at intensive care units (ICUs). Prolonged hypotension can cause tissue hypoperfusion, leading to cellular dysfunction and severe injuries to multiple organs. Prompt medical interventions are thus extremely important for dealing with acute hypotensive episodes (AHE). Population level prognostic scoring systems for risk stratification of patients are suboptimal in such scenarios. However, the design of an efficient risk prediction system can significantly help in the identification of critical care patients, who are at risk of developing an AHE within a future time span. Towards this objective, a pattern mining algorithm is employed to extract informative sequential contrast patterns from hemodynamic data, for the prediction of hypotensive episodes. The hypotensive and normotensive patient groups are extracted from the MIMIC-II critical care research database, following an appropriate clinical inclusion criteria. The proposed method consists of a data preprocessing step to convert the blood pressure time series into symbolic sequences, using a symbolic aggregate approximation algorithm. Then, distinguishing subsequences are identified using the sequential contrast mining algorithm. These subsequences are used to predict the occurrence of an AHE in a future time window separated by a user-defined gap interval. Results indicate that the method performs well in terms of the prediction performance as well as in the generation of sequential patterns of clinical significance. Hence, the novelty of sequential patterns is in their usefulness as potential physiological biomarkers for building optimal patient risk stratification systems and for further clinical investigation of interesting patterns in critical care patients.

Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach

“…* email: pmousavi@cs.queensu.ca 90% of mean arterial blood pressure (MAP) readings were below 60 mmHg 6 . This definition of AHE has been commonly used in the literature when developing predictive models for the ICU since the initial challenge [9][10][11][12][13] . However, as discussed by Moody et al 6 , common false positive predictions of an AHE in many of these studies may have been annotated as an actual episode by a less restrictive definition and considered a true positive in practice.…”

Artificial Intelligence in Neuroanesthesiology and Neurocritical Care

“…Improvement in the prediction of adverse events such as hypotension has been shown using advanced ML models in critical care environments. 26 ML methods can predict the risk of postinduction hypotension. 27,28 These models enables detection and intervention up to 15 minutes before an event and have been generalized for use in the multicenter clinical environment.…”

A Flexible Pressure Sensor with Ink Printed Porous Graphene for Continuous Cardiovascular Status Monitoring

“…Thus, pulse signals contain various pieces of physiological information and have already been widely adopted in Western clinical examinations [ 1 ] and traditional Chinese medicine [ 2 ]. Monitoring detailed pulse information in real time can significantly reduce accidents due to cardiovascular problems in individuals [ 3 ]. However, due to the high cost and large scale of the pulse monitoring device, only the cardiovascular status of patients with severe conditions can be monitored in real time [ 4 ].…”