OpenLB
Open Library of Bioscience
Advanced Search
Scientific reports
11 24, 2023;13 (1): 20670.

Optimizing campus-wide COVID-19 test notifications with interpretable wastewater time-series features using machine learning models.

Tuo Lin, Smruthi Karthikeyan, Alysson Satterlund, Robert Schooley, Rob Knight, Victor De Gruttola, Natasha Martin, Jingjing Zou
Author Information
  1. Tuo Lin: Department of Biostatistics, University of Florida, Gainesville, FL, 32608, USA.
  2. Smruthi Karthikeyan: Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA, 91125, USA.
  3. Alysson Satterlund: Student Affairs, University of California, San Diego, La Jolla, CA, 92093, USA.
  4. Robert Schooley: Division of Infectious Diseases and Global Public Health, Department of Medicine, University of California, San Diego, La Jolla, CA, 92093, USA.
  5. Rob Knight: Department of Pediatrics, University of California San Diego, La Jolla, CA, 92093, USA.
  6. Victor De Gruttola: Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla, CA, 92093, USA.
  7. Natasha Martin: Division of Infectious Diseases and Global Public Health, Department of Medicine, University of California, San Diego, La Jolla, CA, 92093, USA.
  8. Jingjing Zou: Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla, CA, 92093, USA. j2zou@ucsd.edu.
PMID: 38001346 DOI: 10.1038/s41598-023-47859-2

Abstract

During the COVID-19 pandemic, wastewater surveillance of the SARS CoV-2 virus has been demonstrated to be effective for population surveillance at the county level down to the building level. At the University of California, San Diego, daily high-resolution wastewater surveillance conducted at the building level is being used to identify potential undiagnosed infections and trigger notification of residents and responsive testing, but the optimal determinants for notifications are unknown. To fill this gap, we propose a pipeline for data processing and identifying features of a series of wastewater test results that can predict the presence of COVID-19 in residences associated with the test sites. Using time series of wastewater results and individual testing results during periods of routine asymptomatic testing among UCSD students from 11/2020 to 11/2021, we develop hierarchical classification/decision tree models to select the most informative wastewater features (patterns of results) which predict individual infections. We find that the best predictor of positive individual level tests in residence buildings is whether or not the wastewater samples were positive in at least 3 of the past 7 days. We also demonstrate that the tree models outperform a wide range of other statistical and machine models in predicting the individual COVID-19 infections while preserving interpretability. Results of this study have been used to refine campus-wide guidelines and email notification systems to alert residents of potential infections.

References

mSystems. 2021 Mar 2;6(2): [PMID: 33653938]
JAMA. 2021 Mar 16;325(11):1037-1038 [PMID: 33595644]
J Am Coll Health. 2022 Oct;70(7):1968-1974 [PMID: 33180683]
Sci Total Environ. 2021 Sep 10;786:147451 [PMID: 33971608]
Environ Sci Technol Lett. 2020 May 20;7(7):511-516 [PMID: 37566285]
Clin Infect Dis. 2021 Jan 27;72(2):319-322 [PMID: 33501967]
Bull World Health Organ. 2020 Sep 01;98(9):590-598 [PMID: 33012859]
Nature. 2022 Sep;609(7925):101-108 [PMID: 35798029]
Sci Rep. 2021 Mar 8;11(1):5372 [PMID: 33686189]
Int J Environ Res Public Health. 2021 Apr 22;18(9): [PMID: 33922263]
PLoS One. 2022 Nov 10;17(11):e0277154 [PMID: 36355921]
Sci Total Environ. 2020 Sep 20;736:139631 [PMID: 32474280]
Emerg Infect Dis. 2021 Sep;27(9):1-8 [PMID: 34424162]
Shanghai Arch Psychiatry. 2015 Apr 25;27(2):130-5 [PMID: 26120265]
Sci Total Environ. 2020 Aug 15;730:138875 [PMID: 32371231]
Health Serv Outcomes Res Methodol. 2022;22(2):163-191 [PMID: 34393618]
Nat Biotechnol. 2020 Oct;38(10):1151-1153 [PMID: 32958959]
MMWR Morb Mortal Wkly Rep. 2021 Jan 22;70(3):88-94 [PMID: 33476314]
Front Public Health. 2022 Jan 03;9:561710 [PMID: 35047467]
mSystems. 2021 Aug 31;6(4):e0079321 [PMID: 34374562]
Sci Total Environ. 2021 Oct 1;789:147947 [PMID: 34051491]
Sci Rep. 2021 Sep 30;11(1):19456 [PMID: 34593871]
Sci Total Environ. 2022 Jan 10;803:149834 [PMID: 34525746]
JAMA Netw Open. 2020 Jul 1;3(7):e2016818 [PMID: 32735339]
Environ Sci Technol Lett. 2021 Aug 23;8(9):792-798 [PMID: 37566372]
Sci Total Environ. 2022 Jan 20;805:150121 [PMID: 34534872]
Sci Total Environ. 2020 Aug 1;728:138764 [PMID: 32387778]
Water Res. 2022 Jun 30;218:118451 [PMID: 35447417]
J Am Med Inform Assoc. 2020 Jun 1;27(6):853-859 [PMID: 32208481]
Nat Biotechnol. 2020 Oct;38(10):1164-1167 [PMID: 32948856]
Proc Natl Acad Sci U S A. 2021 Sep 28;118(39): [PMID: 34518375]

MeSH Term

Humans
COVID-19
Pandemics
Time Factors
Wastewater
Wastewater-Based Epidemiological Monitoring
Machine Learning

Chemicals

Wastewater
Journal Article

Word Cloud

Similar Articles

Cited By