Joyce C. Ho
Skip Abstract Section
Abstract
Sepsis and septic shock are common and potentially fatal conditions that often occur in intensive care unit (ICU) patients. Early prediction of patients at risk for septic shock is therefore crucial to minimizing the effects of these complications. Potential indications for septic shock risk span a wide range of measurements, including physiological data gathered at different temporal resolutions and gene expression levels, leading to a nontrivial prediction problem. Previous works on septic shock prediction have used small, carefully curated datasets or clinical measurements that may not be available for many ICU patients. The recent availability of a large, rich ICU dataset called MIMIC-II has provided the opportunity for more extensive modeling of this problem. However, such a large clinical dataset inevitably contains a substantial amount of missing data. We investigate how different imputation selection criteria and methods can overcome the missing data problem. Our results show that imputation methods in conjunction with predictive modeling can lead to accurate septic shock prediction, even if the features are restricted primarily to noninvasive measurements. Our models provide a generalized approach for predicting septic shock in any ICU patient.
- Allgöwer, M. and Burri, C. 1967. Schockindex. Deutsche Medizinische Wodenschrif 46, 1--10.Google Scholar
- Arabi, Y. Y., Al Shirawi, N. N., Memish, Z. Z., Venkatesh, S. S., and Al-Shimemeri, A. A. 2003. Assessment of six mortality prediction models in patients admitted with severe sepsis and septic shock to the intensive care unit: A prospective cohort study. Critical Care 7, 5, R116--R122.Google ScholarCross Ref
- Batal, I., Fradkin, D., Harrison, J., Moerchen, F., and Hauskrecht, M. 2012. Mining recent temporal patterns for event detection in multivariate time series data. In Proceeding of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’12). ACM Press, New York, 280--288. Google ScholarDigital Library
- Bone, R. C., Balk, R. A., Cerra, F. B., Dellinger, R. P., Fein, A. M., Knaus, W. A., Schein, R. M., and Sibbald, W. J. 1992. Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis. The ACCP/SCCM Consensus Conference Committee. American College of Chest Physicians/Society of Critical Care Medicine. Chest 101, 6, 1644--1655.Google ScholarCross Ref
- Cremonesi, P., Koren, Y., and Turrin, R. 2010. Performance of recommender algorithms on top-n recommendation tasks. In Proceedings of the 4th ACM Conference on Recommender Systems. Google ScholarDigital Library
- Ferreira, F., Bota, D., Bross, A., Mélot, C., and Vincent, J. 2001. Serial evaluation of the SOFA score to predict outcome in critically ill patients. J. Amer. Med. Assoc. 286, 14, 1754.Google ScholarCross Ref
- Fialho, A. S., Cismondi, F., Vieira, S. M., Sousa, J. M. C., Reti, S. R., and Howell, M. D. 2010. Predicting outcomes of septic shock patients using feature selection based on soft computing techniques. In Proceedings of the 13th Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems. Springer, 65--74.Google Scholar
- Friedman, J., Hastie, T., and Tibshirani, R. 2010. Regularization paths for generalized linear models via coordinate descent. J. Statist. Softw. 33, 1, 1--22.Google ScholarCross Ref
- Hall, M. J., Williams, S. N., DeFrances, C. J., and Golosinskiy, A. 2011. Inpatient care for septicemia or sepsis: A challenge for patients and hospitals. NCHS Data Brief 62, 1--8.Google Scholar
- Hastie, T., Tibshirani, R., and Friedman, J. H. 2008. The Elements of Statistical Learning. Data Mining, Inference, and Prediction. Springer.Google Scholar
- Hastie, T., Tibshirani, R., Narasimhan, B., and Chu, G. 2012. Impute: Imputation for microarray data. R package version 1.30.0.Google Scholar
- Ho, J. C., Lee, C. H., and Ghosh, J. 2012. Imputation-enhanced prediction of septic shock in ICU patients. In Proceedings of the ACM SIGKDD Workshop on Health Informatics (HI-KDD’12).Google Scholar
- Jerez, J. M., Molina, I., García-Laencina, P. J., Alba, E., Ribelles, N., Martín, M., and Franco, L. 2010. Missing data imputation using statistical and machine learning methods in a real breast cancer problem. Artif. Intell. Med. 50, 2, 11--11. Google ScholarDigital Library
- Kennedy, C. E. and Turley, J. P. 2011. Time series analysis as input for clinical predictive modeling: Modeling cardiac arrest in a pediatric ICU. Theor. Biol. Med. Model. 8, 40.Google ScholarCross Ref
- Kumar, A., Roberts, D., Wood, K. E., Light, B., Parrillo, J. E., Sharma, S., Suppes, R., Feinstein, D., Zanotti, S., Taiberg, L., Gurka, D., Kumar, A., and Cheang, M. 2006. Duration of hypotension before initiation of effective antimicrobial therapy is the critical determinant of survival in human septic shock. Critical Care Med. 34, 6, 1589--1596.Google ScholarCross Ref
- Lagu, T., Lindenauer, P. K., Rothberg, M. B., Nathanson, B. H., Pekow, P. S., Steingrub, J. S., and Higgins, T. L. 2011. Development and validation of a model that uses enhanced administrative data to predict mortality in patients with sepsis. Critical Care Med. 39, 11, 2425--2430.Google ScholarCross Ref
- Le Gall, J. R., Loirat, P., Alperovitch, A., Glaser, P., Granthil, C., Mathieu, D., Mercier, P., Thomas, R., and Villers, D. 1984. A simplified acute physiology score for ICU patients. Critical Care Med. 12, 11, 975--977.Google ScholarCross Ref
- Lukaszewski, R. A., Yates, A. M., Jackson, M. C., Swingler, K., Scherer, J. M., Simpson, A. J., Sadler, P., McQuillan, P., Titball, R. W., Brooks, T. J. G., and Pearce, M. J. 2008. Presymptomatic prediction of sepsis in intensive care unit patients. Clinical Vacc. Immun. 15, 7, 1089--1094.Google ScholarCross Ref
- Nanni, L., Lumini, A., and Brahnam, S. 2012. A classifier ensemble approach for the missing feature problem. Artif. Intell. Med. 55, 1. Google ScholarDigital Library
- Nguyen, H. B., Corbett, S. W., Steele, R., Banta, J., Clark, R. T., Hayes, S. R., Edwards, J., Cho, T. W., and Wittlake, W. A. 2007. Implementation of a bundle of quality indicators for the early management of severe sepsis and septic shock is associated with decreased mortality. Critical Care Med. 35, 4, 1105--1112.Google ScholarCross Ref
- Paetz, J. 2003. Knowledge-based approach to septic shock patient data using a neural network with trapezoidal activation functions. Artif. Intell. Med. 28, 2, 207--230. Google ScholarDigital Library
- Pereira, R., Almeida, R., Kaymak, U., Vieira, S., Sousa, J., Reti, S., Howell, M., and Finkelstein, S. 2011. Predicting septic shock outcomes in a database with missing data using fuzzy modeling: Influence of pre-processing techniques on real-world data-based classification. In Proceedings of the IEEE International Conference on Fuzzy Systems (FUZZ’11). 2507--2512.Google Scholar
- Ribas, V. J., Vellido, A., Ruiz-Rodríguez, J. C., and Rello, J. 2012. Severe sepsis mortality prediction with logistic regression over latent factors. Expert Syst. Appl. Int. J. 39, 2. Google ScholarDigital Library
- Rivers, E., Nguyen, B., Havstad, S., Ressler, J., Muzzin, A., Knoblich, B., Peterson, E., Tomlanovich, M., and Early Goal-Directed Therapy Collaborative Group. 2001. Early goal-directed therapy in the treatment of severe sepsis and septic shock. New England J. Med. 345, 19, 1368--1377.Google ScholarCross Ref
- Roweis, S. 1998. EM algorithms for PCA and SPCA. In Proceedings of the Conference on Advances in Neural Information Processing Systems (NIPS’98). 626--632. Google ScholarDigital Library
- Saeed, M., Villarroel, M., Reisner, A. T., Clifford, G., Lehman, L.-W., Moody, G., Heldt, T., Kyaw, T. H., Moody, B., and Mark, R. G. 2011. Multiparameter intelligent monitoring in intensive care ii (mimic-ii): A public-access intensive care unit database. Critical Care Med. 39, 5, 952--960.Google ScholarCross Ref
- Shavdia, D. 2007. Septic shock: Providing early warnings through multivariate logistic regression models. Tech. rep., Harvard-MIT Division of Health Sciences and Technology.Google Scholar
- Stacklies, W., Redestig, H., Scholz, M., Walther, D., and Selbig, J. 2007. PcaMethods--A bioconductor package providing PCA methods for incomplete data. Bioinf. 23, 9, 1164--1167. Google ScholarDigital Library
- Thiel, S. W., Rosini, J. M., Shannon, W., Doherty, J. A., Micek, S. T., and Kollef, M. H. 2010. Early prediction of septic shock in hospitalized patients. J. Hospital Med. 5, 1, 19--25.Google ScholarCross Ref
- Troyanskaya, O. G., Cantor, M., Sherlock, G., Brown, P. O., Hastie, T., Tibshirani, R., Botstein, D., and Altman, R. B. 2001. Missing value estimation methods for DNA microarrays. Bioinf. 17, 6, 520--525.Google ScholarCross Ref
- Wang, F., Lee, N., Hu, J., Sun, J., and Ebadollahi, S. 2012. Towards heterogeneous temporal clinical event pattern discovery: A convolutional approach. In Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’12). Google ScholarDigital Library
- WSD Coalition. 2012. The world sepsis day fact sheet. http://www.world-sepsis-day.org/.Google Scholar
Index Terms
- Septic Shock Prediction for Patients with Missing Data
Recommendations
Machine Learning Methods for Septic Shock Prediction
AIVR 2018: Proceedings of the 2018 International Conference on Artificial Intelligence and Virtual RealitySepsis is an organ dysfunction life-threatening disease that is caused by a dysregulated body response to infection. Sepsis is difficult to detect at an early stage, and when not detected early, is difficult to treat and results in high mortality rates. ...
The value of missing information in severity of illness score development
Graphical abstractDisplay Omitted
Highlights- Missing information is ubiquitous in EHR.
- Knowing which variables are missing improves severity of illness scoring systems.
- Two imputation methods are employed.
- We use indicators to inform prediction models about missing and ...
Abstract ObjectiveWe aim to investigate the hypothesis that using information about which variables are missing along with appropriate imputation improves the performance of severity of illness scoring systems used to predict critical patient outcomes.
...Septic shock prediction and knowledge discovery through temporal pattern mining
AbstractSepsis is the body's adverse response to infection which can lead to septic shock and eventually death if not treated in a timely manner. Analyzing patterns in sepsis patients' health status over time can help predict septic shock ...
Highlights- A framework to identify relevant temporal patterns in data is proposed.
- Recent ...
Comments