Abstract
Postsurgical hospital acquired infections (HAIs) are viewed as a quality benchmark in healthcare due to their association with morbidity, mortality and high cost. The prediction of HAIs allows for implementing prevention strategies at early stages to reduce postsurgical complications. In the United States, the National Surgical Quality Improvement Program (NSQIP) maintains a registry considered a “gold-standard” for HAIs outcome reporting, but it relies heavily on costly manual chart review and therefore only includes a small percent of surgery cases from each participating site. Most HAI prediction models rely on a wide range of weak risk factors, which are combined into models with many parameters and require larger sample sizes than available from NSQIP at a single health system. In this study, we propose an alternative approach to develop a robust prediction model, using the few NSQIP cases efficiently. Rather than training the HAIs prediction models directly on the small number of NSQIP patients, we leverage a simple detection model which detects HAIs after the fact on postoperative data and use this detection model to label a large non-NSQIP perioperative dataset on which prediction models are constructed. Detection models rely on strong signals requiring fewer samples to learn. We evaluate this approach in a single academic health system with 115,202 surgeries (10,354 in NSQIP). The prediction models were evaluated on the NSQIP “gold-standard” labels. While organ-space surgical site infection showed comparable performance, the proposed model demonstrated better performance for prediction of superficial surgical site infection, sepsis or septic shock, pneumonia, and urinary tract infection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Khan, N.A., Quan, H., Bugar, J.M., Lemaire, J.B., Brant, R., Ghali, W.A.: Association of postoperative complications with hospital costs and length of stay in a tertiary care center. J. Gen. Intern. Med. 21(2), 177–180 (2006). https://doi.org/10.1111/j.1525-1497.2006.00319.x
Lawson, E.H., et al.: Association between occurrence of a postoperative complication and readmission. Ann. Surg. 258(1), 10–18 (2013). https://doi.org/10.1097/SLA.0b013e31828e3ac3
Horan, T.C., Andrus, M., Dudeck, M.A.: CDC/NHSN surveillance definition of health care–associated infection and criteria for specific types of infections in the acute care setting. Am. J. Infect. Control 36(5), 309–332 (2008). https://doi.org/10.1016/j.ajic.2008.03.002
Dimick, J.B., Pronovost, P.J., Cowan, J.A., Lipsett, P.A., Stanley, J.C., Upchurch, G.R.: Variation in postoperative complication rates after high-risk surgery in the United States. Surgery 134(4), 534–540 (2003). https://doi.org/10.1016/S0039-6060(03)00273-3
Tourani, R., Murphree, D.H., Melton-Meaux, G., Wick, E., Kor, D.J., Simon, G.J.: The value of aggregated high-resolution intraoperative data for predicting post-surgical infectious complications at two independent sites. Stud. Health Technol. Inform. 264, 398–402 (2019). https://doi.org/10.3233/SHTI190251
Leaper, D., Ousey, K.: Evidence update on prevention of surgical site infection. Curr. Opin. Infect. Dis. 28(2), 158–163 (2015). https://doi.org/10.1097/QCO.0000000000000144
Seamon, M.J., Wobb, J., Gaughan, J.P., Kulp, H., Kamel, I., Dempsey, D.T.: The effects of intraoperative hypothermia on surgical site infection. Ann. Surg. 255(4), 789–795 (2012). https://doi.org/10.1097/SLA.0b013e31824b7e35
Chang, Y.-J., et al.: Predicting hospital-acquired infections by scoring system with simple parameters. PLoS One 6(8), e23137 (2011). https://doi.org/10.1371/journal.pone.0023137
Hu, Z., Simon, G.J., Arsoniadis, E.G., Wang, Y., Kwaan, M.R., Melton, G.B.: Automated detection of postoperative surgical site infections using supervised methods with electronic health record data. Stud. Health Technol. Inform. 216, 706–710 (2015). https://doi.org/10.3233/978-1-61499-564-7-706
Ma, S., Statnikov, A.: Methods for computational causal discovery in biomedicine. Behaviormetrika 44(1), 165–191 (2017). https://doi.org/10.1007/s41237-016-0013-5
Kalisch, M., Mächler, M., Colombo, D., Maathuis, M.H., Bühlmann, P.: Causal inference using graphical models with the R package pcalg. J. Stat. Softw. 47(11), 1–26 (2012). https://doi.org/10.18637/jss.v047.i11
Acknowledgements
This work was supported in part by NIGMS award R01 GM 120079, AHRQ award R01 HS024532, and the NCATS University of Minnesota CTSA UL1 TR002494. The views expressed in this manuscript are those of the authors and do not necessarily reflect the views of the funding agencies.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, Y., Tourani, R., Sheka, A., Wick, E., Melton, G.B., Simon, G. (2020). Innovative Method to Build Robust Prediction Models When Gold-Standard Outcomes Are Scarce. In: Michalowski, M., Moskovitch, R. (eds) Artificial Intelligence in Medicine. AIME 2020. Lecture Notes in Computer Science(), vol 12299. Springer, Cham. https://doi.org/10.1007/978-3-030-59137-3_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-59137-3_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59136-6
Online ISBN: 978-3-030-59137-3
eBook Packages: Computer ScienceComputer Science (R0)