A transferable machine learning model for real-time forecast of epidemic dynamics and pre-trigger event warning

Abstract

Wastewater-based epidemiology (WBE) is emerging as an effective tool to provide early warnings of potential disease outbreaks within communities through detecting the presence of pathogens in wastewater before clinical cases are reported. Nevertheless, quantitative prediction of future clinical case is challenging as uncertainties of dynamic shedding and disease transmission patterns can lead to complex correlation between wastewater viral concentration and clinical cases. Such complexities, augmented by factors such as viral variant, public behavioral change, etc., make it challenging to develop empirical models or data-driven models to provide accurate prediction of disease case for public health policy makings. To address this gap, this study developed an iterative data-driven framework utilizing Long-Short Time Memory (LSTM) neural networks for multi-timestep real-time predictions of future clinical cases based on WBE. The proposed LSTM model structure integrates both wastewater and historical clinical data as inputs. The prediction framework enables the update of LSTM model as more WBE dataset become available to enhance its adaptability to evolving pandemic stages. This framework was applied for real-time forecasting of COVID-19 clinical cases based on dataset of Ohio Wastewater Monitoring Project from July 2020 to October 2023. The developed iterative LSTM models were proven to achieve excellent performance in making clinical case predictions at different stages of COVID-19 pandemic. Early warning threshold of viral surge was defined by moving percentile method and results showed that the model achieved over 90% accuracy in future clinical case prediction and therefore demonstrated high reliability in pre-warning of potential disease outbreaks. This framework was also found to possess strong transferability across diverse geographic regions. The impacts of social policies and events on model predictions as well as the ramification of this model for future pandemics warning are discussed.

Keywords

Wastewater-based epidemiology / Transferable machine learning model / Pandemics warning / Social policy

References

[1] AbdeldayemOM, DabbishAM, HabashyMM, MostafaMK, ElhefnawyM, AminL, Al-SakkariEG, RagabA, ReneER. Viral outbreaks detection and surveillance using wastewater-based epidemiology, viral air sampling, and machine learning techniques: A comprehensive review and outlook. Science of the Total Environment, 2022, 803. 149834

[2] AberiP, ArabzadehR, InsamH, MarktR, MayrM, KreuzingerN, RauchW. Quest for optimal regression models in SARS-CoV-2 wastewater based epidemiology. International Journal of Environmental Research and Public Health, 2021, 182010778.

[3] AhmedW, TscharkeB, BertschPM, BibbyK, BivinsA, ChoiP, ClarkeL, DwyerJ, EdsonJ, NguyenTMH, O’BrienJW, SimpsonSL, ShermanP, ThomasKV, VerhagenR, ZauggJ, MuellerJF. SARS-CoV-2 RNA monitoring in wastewater as a potential early warning system for COVID-19 transmission in the community: A temporal case study. Science of the Total Environment, 2021, 761. 144216

[4] AlanaziSA, KamruzzamanMM, AlruwailiM, AlshammariN, AlqahtaniSA, KarimeA. Measuring and preventing COVID-19 using the SIR model and machine learning in smart health care. Journal of Healthcare Engineering, 2020, 20208857346.

[5] AlbastakiA, NajiM, LootahR, AlmeheiriR, AlmullaH, AlmarriI, AlreyamiA, AdenA, AlghafriR. First confirmed detection of SARS-COV-2 in untreated municipal and aircraft wastewater in Dubai, UAE: The use of wastewater based epidemiology as an early warning tool to monitor the prevalence of COVID-19. Science of the Total Environment, 2021, 760. 143350

[6] BibbyK, BivinsA, WuZ, NorthD. Making waves: Plausible lead time for wastewater based epidemiology as an early warning system for COVID-19. Water Research, 2021, 202. 117438

[7] BohrerovaZ, BrinkmanNE, ChakravartiR, ChattopadhyayS, FaithSA, GarlandJ, HerrinJ, HullN, JahneM, KangD-W, KeelySP, LeeJ, LemeshowS, LenhartJ, LytmerE, MalgaveD, MiaoL, Minard-SmithA, MouX, NagarkarM, QuinteroA, SavonaFDR, SenkoJ, SlonczewskiJL, SpurbeckRR, SovicMG, TaylorRT, WeaversLK, WeirM. Ohio Coronavirus Wastewater Monitoring Network: Implementation of statewide monitoring for protecting public health. Journal of Public Health Management and Practice, 2023, 29(6): 845-853.

[8] BowmanLR, TejedaGS, CoelhoGE, SulaimanLH, GillBS, McCallPJ, OlliaroPL, RanzingerSR, QuangLC, RammRS, KroegerA, PetzoldMG. Alarm variables for dengue outbreaks: A multi-centre study in Asia and Latin America. PLoS ONE, 2016, 116. e0157971

[9] ChengHY, JianSW, LiuDP, NgTC, HuangWT, LinHH. Contact tracing assessment of COVID-19 transmission dynamics in Taiwan and risk at different exposure periods before and after symptom onset. JAMA Internal Medicine, 2020, 180(9): 1156-1163.

[10] Fazli, M., & Shakeri, H. (2022). Leveraging wastewater monitoring for COVID-19 forecasting in the US: A deep learning study. arXiv preprint arXiv:2212.08798.

[11] GaoQ, LiuZ, XiangJ, TongM, ZhangY, WangS, ZhangY, LuL, JiangB, BiP. Forecast and early warning of hand, foot, and mouth disease based on meteorological factors: Evidence from a multicity study of 11 meteorological geographical divisions in mainland China. Environmental Research, 2021, 192. 110301

[12] HochreiterS, SchmidhuberJ. Long short-term memory. Neural Computation, 1997, 9(8): 1735-1780.

[13] JiangG, WuJ, WeidhaasJ, LiX, ChenY, MuellerJ, LiJ, KumarM, ZhouX, AroraS, HaramotoE, SherchanS, OriveG, LertxundiU, HondaR, KitajimaM, JacksonG. Artificial neural network-based estimation of COVID-19 case numbers and effective reproduction rate using wastewater-based epidemiology. Water Research, 2022, 218. 118451

[14] La RosaG, IaconelliM, ManciniP, FerraroGB, VeneriC, BonadonnaL, LucentiniL, SuffrediniE. First detection of SARS-CoV-2 in untreated wastewaters in Italy. Science of the Total Environment, 2020, 736. 139652

[15] LaiM, CaoY, WulffSS, RobinsonTJ, McGuireA, BishaB. A time series based machine learning strategy for wastewater-based forecasting and nowcasting of COVID-19 dynamics. Science of the Total Environment, 2023, 897. 165105

[16] LiX, KulandaiveluJ, ZhangS, ShiJ, SivakumarM, MuellerJ, LubyS, AhmedW, CoinL, JiangG. Data-driven estimation of COVID-19 community prevalence through wastewater-based epidemiology. Science of the Total Environment, 2021, 789. 147947

[17] LodderW, de Roda HusmanAM. SARS-CoV-2 in wastewater: Potential health risk, but also data source. The Lancet Gastroenterology & Hepatology, 2020, 5(6): 533-534.

[18] LongB, CariusBM, ChavezS, LiangSY, BradyWJ, KoyfmanA, GottliebM. Clinical update on COVID-19 for the emergency clinician: Presentation and evaluation. The American Journal of Emergency Medicine, 2022, 54: 46-57.

[19] MonteiroS, RenteD, CunhaMV, GomesMC, MarquesTA, LourençoAB, CardosoE, ÁlvaroP, SilvaM, CoelhoN, VilaçaJ, MeirelesF, BrôcoN, CarvalhoM, SantosR. A wastewater-based epidemiology tool for COVID-19 surveillance in Portugal. Science of the Total Environment, 2022, 804. 150264

[20] O’BrienDA, ClementsCF. Early warning signal reliability varies with COVID-19 waves. Biology Letters, 2021, 171220210487.

[21] Peng, L., Yang, W., Zhang, D., Zhuge, C., & Hong, L. (2020). Epidemic analysis of COVID-19 in China by dynamical modeling. arXiv preprint arXiv:2002.06563.

[22] PoloD, Quintela-BalujaM, CorbishleyA, JonesDL, SingerAC, GrahamDW, RomaldeJL. Making waves: Wastewater-based epidemiology for COVID-19—approaches and challenges for surveillance and prediction. Water Research, 2020, 186. 116404

[23] RókaE, KhayerB, KisZ, KovácsLB, SchulerE, MagyarN, MálnásiT, OraveczO, PályiB, PándicsT, VarghaM. Ahead of the second wave: Early warning for COVID-19 by wastewater surveillance in Hungary. Science of the Total Environment, 2021, 786. 147398

[24] SherchanSP, ShahinS, WardLM, TandukarS, AwTG, SchmitzB, AhmedW, KitajimaM. First detection of SARS-CoV-2 RNA in wastewater in North America: A study in Louisiana, USA. Science of the Total Environment, 2020, 743. 140621

[25] VaughanL, ZhangM, GuH, RoseJB, NaughtonCC, MedemaG, AllanV, RoikoA, BlackallL, ZamyadiA. An exploration of challenges associated with machine learning for time series forecasting of COVID-19 community spread using wastewater-based epidemiological data. Science of the Total Environment, 2023, 858. 159748

[26] WiersingaWJ, RhodesA, ChengAC, PeacockSJ, PrescottHC. Pathophysiology, transmission, diagnosis, and treatment of coronavirus disease 2019 (COVID-19): A review. JAMA, 2020, 324(8): 782-793.

[27] XiaoA, WuF, BushmanM, ZhangJ, ImakaevM, ChaiPR, DuvalletC, EndoN, EricksonTB, ArmasF, ArnoldB, ChenH, ChandraF, GhaeliN, GuX, HanageWP, LeeWL, MatusM, McElroyKA, MonizK, RhodeSF, ThompsonJ, AlmEJ. Metrics to relate COVID-19 wastewater data to clinical testing dynamics. Water Research, 2022, 212. 118070

[28] XuX, ZhengX, LiS, LamNS, WangY, ChuDKW, PoonLLM, TunHM, PeirisM, DengY, LeungGM, ZhangT. The first case study of wastewater-based epidemiology of COVID-19 in Hong Kong. Science of the Total Environment, 2021, 790. 148000

[29] ZhaoL, ZouY, DavidRE, WithingtonS, McFarlaneS, FaustRA, NortonJ, XagorarakiI. Simple methods for early warnings of COVID-19 surges: Lessons learned from 21 months of wastewater and clinical data collection in Detroit, Michigan, United States. Science of the Total Environment, 2023, 864. 161152

[30] ZhaoL, ZouY, LiY, MiyaniB, SpoonerM, GentryZ, JacobiS, DavidRE, WithingtonS, McFarlaneS, FaustR, SheetsJ, KayeA, BrozJ, GosineA, MobleyP, BuschAWU, NortonJ, XagorarakiI. Five-week warning of COVID-19 peaks prior to the Omicron surge in Detroit, Michigan using wastewater surveillance. Science of the Total Environment, 2022, 844. 157040

[31] ZhuY, OishiW, SaitoM, KitajimaM, SanoD. Early warning of COVID-19 in Tokyo via wastewater-based epidemiology: How feasible it really is?. Journal of Water and Environment Technology, 2021, 19(3): 170-183.

Funding

National Science Foundation(1638320)

RIGHTS & PERMISSIONS

The Author(s)