This work aims to predict in-hospital mortality in the open-source Physionet ICU database from features extracted from the time series of physiological variables using neural network models and other machine learning techniques. We developed an effective and efficient greedy algorithm for feature selection, reducing the number of potential features from 205 to a best subset of only 47. The average of five trials of 10-fold cross validation shows an accuracy of (86.23±0.14)%, a sensitivity of (50.29±0.22)%, a specificity of (92.01 ± 0.21)%, a positive prediction value of (50.29±0.50)%, a negative prediction value of (92.01±0.00)%, and a Lemeshow score of 119.55±9.87. By calibrating the predicted mortality probability using an optimization approach, we can improve the Lemeshow score to 27.51±4.38. The developed model has the potential for application in ICU machines to improve the quality of care and to evaluate the effect of treatment or drugs.
- Dynamic Systems and Control Division
Prediction of ICU In-Hospital Mortality Using Artificial Neural Networks
- Views Icon Views
- Share Icon Share
- Search Site
Xia, H, Keeney, N, Daley, BJ, Petrie, A, & Zhao, X. "Prediction of ICU In-Hospital Mortality Using Artificial Neural Networks." Proceedings of the ASME 2013 Dynamic Systems and Control Conference. Volume 3: Nonlinear Estimation and Control; Optimization and Optimal Control; Piezoelectric Actuation and Nanoscale Control; Robotics and Manipulators; Sensing; System Identification (Estimation for Automotive Applications, Modeling, Therapeutic Control in Bio-Systems); Variable Structure/Sliding-Mode Control; Vehicles and Human Robotics; Vehicle Dynamics and Control; Vehicle Path Planning and Collision Avoidance; Vibrational and Mechanical Systems; Wind Energy Systems and Control. Palo Alto, California, USA. October 21–23, 2013. V003T43A001. ASME. https://doi.org/10.1115/DSCC2013-3768
Download citation file: