Predictive Modeling of Emerging Antibiotic Resistance Trends
Antibiotic resistance is constantly evolving, requiring frequent reevaluation of resistance patterns to guide treatment of bacterial infections. Antibiograms, aggregate antimicrobial susceptibility reports, are critical for evaluating the likelihood of antibiotic effectiveness. However, these antibiograms provide outdated resistance knowledge. Thus, this research employs predictive modeling of historic antibiograms to forecast the current year’s resistance rates. Utilizing subsets of the expansive 15-year Massachusetts statewide antibiogram dataset, we demonstrate the effectiveness of using our model selector PYPER with regression-based models to forecast current antimicrobial susceptibility. A PYPER variant is effective since it leverages the fact that different antibiotic-bacteria-location combinations have different antimicrobial susceptibility trends over time. In addition, we discuss relative weighting of the regression-variant models, the impact of location granularity, and the ability to forecast multiple years into the future.
KeywordsAntimicrobial resistance Antibiograms Regression Support vector regression Autoregressive integrated moving average Model selection
This work is supported by WPI and the US Department of Education P200A150306: GAANN Fellowships to Support Data-Driven Computing Research. We thank Jian Zou, PhD and Tom Hartvigsen at WPI, Matthew Tlachac at University of Minnesota, and Alfred DeMaria, MD and Monina Klevens, DMD at MDPH for their input on this work. We thank the DSRG community at WPI for providing a stimulating research environment.
- 3.Bureau of Infectious Disease and Laboratory Sciences: 2015 statewide antibiogram report. Massachusetts State Public Health Laboratory (2016). Accessed 24 Jan 2017Google Scholar
- 4.Centers for Disease Control and Prevention: Antibiotic resistance threats in the United States, 2013. U.S. Department of Health and Human Services (2015). https://www.cdc.gov/drugresistance/pdf/ar-threats-2013-508.pdf
- 5.Centers For Disease Control and Prevention: About Antimicrobial Resistance. Antibiotic/Antimicrobial Resistance (2018). https://www.cdc.gov/drugresistance/about.html. Accessed May 2018
- 7.Food and Drug Administration: Stewardship guidelines. The National Antimicrobial Resistance Monitoring System (2016)Google Scholar
- 11.Moore, D.: The Basic Practice of Statistics, 4th edn. WH Freeman, New York (2007)Google Scholar
- 12.Nau, R.: Statistical forecasting: notes on regression and time series analysis. Fuqua School of Buisness, Duke University, (2018). https://people.duke.edu/~rnau/411home.htm. Accessed May 2018
- 13.O’Neill, J.: Tackling Drug-Resistant Infections Globally: Final Report and Reccomendations. The Review on Antimicrobial Resistance (2016). https://amr-review.org/sites/default/files/160525_Final%20paper_with%20cover.pdf
- 16.Tlachac, M., Rundensteiner, E., Barton, K., Troppy, S., Beaulac, K., Doron, S.: Predicting future antibiotic susceptibility using regression-based methods on longitudinal Massachusetts antibiogram data. In: Proceedings of the 11th International Conference on Health Informatics (2018)Google Scholar
- 17.Tlachac, M., et al.: CASSIA: an assistant for identifying clinically and statistically significant decreases in antimicrobial susceptibility. In: 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI) (2018)Google Scholar
- 18.Ventola, L.: The antibiotic resistance crisis. Pharm. Ther. 40(4), 277–283 (2015)Google Scholar
- 19.World Health Organization: Antimicrobial resistance global report on surveillance 2014. World Health Organization (2014). http://apps.who.int/iris/bitstream/handle/10665/112642/9789241564748_eng.pdf