Collaborative Filtering for Identifying Prescription Omissions in an ICU

Anima Singh, John Guttag

Abstract

Medication errors in critical care are frequent and can lead to adverse consequences. One important category of errors is prescription omission, i.e., failure to prescribe a potentially useful medication. Studies have shown that failure to prescribe a medication can result in adverse consequences leading to patient morbidity or even patient mortality (Aspden et al., 2007; Olsen et al., 2007). In this paper, we present a machine learning based approach to building a system that can be used to provide physicians with an ordered list of possible omissions. We investigated three different collaborative filtering approaches as well as simple prevalence and co-occurrence methods. When evaluated on over 19,000 ICU admissions, each of the CF approaches outperformed both prevalence and co-occurrence based methods. This work highlights the importance of capturing a multi-scale view of the prescription data for the task of identifying omissions. Our results suggest that latent factor models and neighborhood models are better at capturing different kinds of omissions. Latent factor models demonstrated improved performance on identifying omission of rarely prescribed medications while neighborhood models were slightly better at identifying omissions of commonly prescribed medications.

References

  1. Aspden, P., Wolcott, J., Bootman, J. L., and Cronenwett, L. R. (2007). Preventing Medication Errors: Quality Chasm Series. The National Academies Press.
  2. Cullen, D., Sweitzer, B., Bates, D., Burdick, E., Edmondson, A., and Leape., L. (1997). Preventable adverse drug events in hospitalized patients: a comparative study of intensive care and general care units. Critical Care Medicine, 25(8):1289-1297.
  3. Hasan, S., Duncan, G. T., Neill, D. B., and Padman, R. (2011). Automatic detection of omissions in medication lists. Journal of the American Medical Informatics Association : JAMIA, 18(4):449-58.
  4. Li, Y., Hu, J., Zhai, C., and Chen, Y. (2010). Improving one-class collaborative filtering by incorporating rich user information. In Proceedings of the 19th ACM international conference on Information and knowledge management, CIKM 7810, pages 959-968, New York, NY, USA. ACM.
  5. Olsen, S., Neale, G., Schwab, K., Psaila, B., Patel, T., Chapman, E. J., and Vincent, C. (2007). Hospital staff should use more than one method to detect adverse events and potential adverse events: incident reporting, pharmacist surveillance and local real-time record review may all have a place. Quality & safety in health care, 16(1):40-4.
  6. Rothschild, J., Landrigan, C., Cronin, J., Kaushal, R., Lockley, S., Burdick, E., Stone, P., Lilly, C., Katz, J., Czeisler, C., and Bates, D. (2005). The critical care safety study: The incidence and nature of adverse events and serious medical errors in intensive care. Critical Care Medicine, 33(8):1694-1700.
  7. Saeed, M., Lieu, C., Raber, G., and Mark, R. (2002). Mimic ii: A massive temporal icu patient database to support research in intelligent patient monitoring. In Computers in Cardiology, 2002, pages 641 - 644.
  8. Xie, J., Leishman, S., Tian, L., Lisuk, D., Koo, S., and Blume, M. (2012). Feature Engineering in User's Music Preference Prediction. Journal of Machine Learning Research: Workshop and Conference Proceedings, 18:183-197.
  9. Zamir, S. and Gabriel, K. R. (1979). Lower Rank Approximation of Matrices by Least Squares With Any Choice of Weights. Technometrics, 21(4).
Download


Paper Citation


in Harvard Style

Singh A. and Guttag J. (2013). Collaborative Filtering for Identifying Prescription Omissions in an ICU . In Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2013) ISBN 978-989-8565-37-2, pages 58-64. DOI: 10.5220/0004233900580064


in Bibtex Style

@conference{healthinf13,
author={Anima Singh and John Guttag},
title={Collaborative Filtering for Identifying Prescription Omissions in an ICU},
booktitle={Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2013)},
year={2013},
pages={58-64},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004233900580064},
isbn={978-989-8565-37-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2013)
TI - Collaborative Filtering for Identifying Prescription Omissions in an ICU
SN - 978-989-8565-37-2
AU - Singh A.
AU - Guttag J.
PY - 2013
SP - 58
EP - 64
DO - 10.5220/0004233900580064