Layered Learning for Early Anomaly Detection: Predicting Critical Health Episodes
Critical health events represent a relevant cause of mortality in intensive care units of hospitals, and their timely prediction has been gaining increasing attention. This problem is an instance of the more general predictive task of early anomaly detection in time series data. One of the most common approaches to solve this problem is to use standard classification methods. In this paper we propose a novel method that uses a layered learning architecture to solve early anomaly detection problems. One key contribution of our work is the idea of pre-conditional events, which denote arbitrary but computable relaxed versions of the event of interest. We leverage this idea to break the original problem into two layers, which we hypothesize are easier to solve. Focusing on critical health episodes, the results suggest that the proposed approach is advantageous relative to state of the art approaches for early anomaly detection. Although we focus on a particular case study, the proposed method is generalizable to other domains.
KeywordsTime series Early anomaly detection Healthcare Layered learning
Vitor Cerqueira is supported by a FCT PhD research grant (SFRH/BD/135705/2018).
- 3.Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y.: xgboost: eXtreme gradient boosting, 2017. R package version 0.6-4 (2015)Google Scholar
- 4.Decroos, T., Dzyuba, V., Van Haaren, J., Davis, J.: Predicting soccer highlights from spatio-temporal match event streams. In: AAAI, pp. 1302–1308 (2017)Google Scholar
- 5.Fawcett, T., Provost, F.: Activity monitoring: noticing interesting changes in behavior. In: Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 53–62. ACM (1999)Google Scholar
- 6.Ferreira, C., Gama, J., Matias, L., Botterud, A., Wang, J.: A survey on wind power ramp forecasting. Technical report, Argonne National Lab. (ANL), Argonne, IL (United States) (2011)Google Scholar
- 11.Lee, J., Mark, R.: A hypotensive episode predictor for intensive care based on heart rate and blood pressure time series. In: Computing in Cardiology, pp. 81–84. IEEE (2010)Google Scholar
- 13.Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation-based anomaly detection. ACM Trans. Knowl. Discov. Data (TKDD) 6(1), 3 (2012)Google Scholar
- 16.Saeed, M., Lieu, C., Raber, G., Mark, R.G.: MIMIC II: a massive temporal ICU patient database to support research in intelligent patient monitoring. In: Computers in Cardiology, pp. 641–644. IEEE (2002)Google Scholar
- 19.Tsur, E., Last, M., Garcia, V.F., Udassin, R., Klein, M., Brotfain, E.: Hypotensive episode prediction in ICUs via observation window splitting. In: Brefeld, U., et al. (eds.) ECML PKDD 2018. LNCS (LNAI), vol. 11053, pp. 472–487. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-10997-4_29CrossRefGoogle Scholar
- 20.Weiss, G.M., Hirsh, H.: Learning to predict rare events in event sequences. In: KDD, pp. 359–363 (1998)Google Scholar