Predicting acute hypotensive episodes based on HR baroreflex model estimation

A machine learning method for acute hypotensive episodes prediction using only non-invasive parameters

BACKGROUND AND OBJECTIVES

Accurate prediction of acute hypotensive episodes (AHE) is fundamentally important for timely and appropriate clinical decision-making, as it can provide medical professionals with sufficient time to accurately select more efficient therapeutic interventions for each specific condition. However, existing methods are invasive, easily affected by artifacts and can be difficult to acquire in a pre-hospital setting.

METHODS

In this study, 1055 patients' records were extracted from the Multiparameter Intelligent Monitoring in Intensive Care II database (MIMIC II), comprising of 388 AHE records and 667 non-AHE records. Six commonly used machine learning algorithms were selected and used to develop an AHE prediction model based on features extracted from seven types of non-invasive physiological parameters.

RESULTS

The optimal observation window and prediction gap were selected as 300 minutes and 60 minutes, respectively. For GBDT, XGB and AdaBoost, the optimal feature subsets contained only 39% of the overall features. An ensemble prediction model was developed using the voting method to achieve a more robust performance with an accuracy (ACC) of 0.822 and area under the receiver operating characteristic curve (AUC) of 0.878.

CONCLUSION

A novel machine learning method that uses only noninvasive physiological parameters offers a promising solution for easy and prompt AHE prediction in widespread scenario applications, including pre-hospital and in-hospital care.

Prediction of periventricular leukomalacia occurrence in neonates after heart surgery

This paper is concerned with predicting the occurrence of periventricular leukomalacia (PVL) using vital and blood gas data which are collected over a period of 12 h after the neonatal cardiac surgery. A data mining approach has been employed to generate a set of rules for classification of subjects as healthy or PVL affected. In view of the fact that blood gas and vital data have different sampling rates, in this study we have divided the data into two categories: 1) high resolution (vital), and 2) low resolution (blood gas), and designed a separate classifier based on each data category. The developed algorithm is composed of several stages; first, a feature pool has been extracted from each data category and the extracted features have been ranked based on the data reliability and their mutual information content with the output. An optimal feature subset with the highest discriminative capability has been formed using simultaneous maximization of the class separability measure and mutual information of a set. Two separate decision trees (DTs) have been developed for the classification purpose and more importantly to discover hidden relationships that exist among the data to help us better understand PVL pathophysiology. The DT result shows that high amplitude 20 min variations and low sample entropy in the vital data and the defined out of range index as well as maximum rate of change in blood gas data are important factors for PVL prediction. Low sample entropy represents lack of variability in hemodynamic measurement, and constant blood pressure with small fluctuations is an important indicator of PVL occurrence. Finally, using the different time frames of data collection, we show that the first 6 h of data contain sufficient information for PVL occurrence prediction.