Abstract
Cardiac arrest (CA) is a devastating complication for children in the cardiac intensive care unit (CICU). We developed an “anytime" algorithm to predict CA, using the first few hours of EHR data for initial approximation, and then using information from subsequent time periods to augment the predictive model, improving performance at each iteration. Our initial empirical evaluation on EHR CICU data shows that the model achieves significantly higher performance than learning with all the available data at each iteration when predicting CA inside CICU.
S. Natarajan—Supported in part by NICHD grant 1R01HD101246 and The Precision Health Initiative of Indiana University.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Dietterich, T.G., Ashenfelter, A., Bulatov, Y.: Training conditional random fields via gradient tree boosting. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 28 (2004)
Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189–1232 (2001)
Getoor, L., Taskar, B.: Statistical Relational Learning (2007)
Meyer, L., et al.: Incidence, causes, and survival trends from cardiovascular-related sudden cardiac arrest in children and young adults 0 to 35 years of age: a 30-year review. Circulation 126(11), 1363–1372 (2012)
Natarajan, S., Khot, T., Kersting, K., Gutmann, B., Shavlik, J.: Gradient-based boosting for statistical relational learning: the relational dependency network case. Mach. Learn. 86(1), 25–56 (2012). https://doi.org/10.1007/s10994-011-5244-9
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Ruiz, V.M., et al.: Early prediction of clinical deterioration using data-driven machine learning modeling of electronic health records. J. Thorac. Cardiovasc. Surg. 164(1), 211–222 (2021)
Zilberstein, S.: Operational rationality through compilation of anytime algorithms. AI Mag. 16(2), 79–79 (1995)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Skinner, M.A., Yu, P., Raman, L., Natarajan, S. (2022). An Anytime Querying Algorithm for Predicting Cardiac Arrest in Children: Work-in-Progress. In: Michalowski, M., Abidi, S.S.R., Abidi, S. (eds) Artificial Intelligence in Medicine. AIME 2022. Lecture Notes in Computer Science(), vol 13263. Springer, Cham. https://doi.org/10.1007/978-3-031-09342-5_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-09342-5_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-09341-8
Online ISBN: 978-3-031-09342-5
eBook Packages: Computer ScienceComputer Science (R0)