AI-Based Wastewater Sampling Predicts COVID Hospital Admissions

It is possible to accurately predict hospital admission numbers due to COVID-19 up to four weeks in advance using an Artificial Intelligence (AI) based system together with COVID wastewater sampling, new research shows.

The study, published in the journal Nature Communications, used wastewater data from 159 counties in the US, covering nearly 100 million Americans, along with US hospital admission records, to develop the prediction model.

The research was led by Professor Qilin Wang and Dr Xuan Li from the University of Technology Sydney together with researchers from UNSW Sydney, Delft University of Technology and Morgan State University.

Dr Li was recently awarded a two-year grant from the Australian Academy of Science WH Gladstones Population and Environment Fund to develop an Australian-based wastewater prediction model.

"COVID-19 still poses a heavy burden on healthcare systems around the world. The number of Australians in hospital with Covid-19 peaked at around 5500 and continues to fluctuate. Rapid increases in patient numbers can stress frontline healthcare capacity and increase fatality rates," Dr Li said.

"Current prediction methods are based on COVID-19 laboratory testing, or self-testing and reporting, however this does not pick up asymptomatic cases, and many countries are moving away from rigorous testing requirements," she said.

Professor Wang said the research shows wastewater surveillance combined with AI-based modelling can be a cost-effective early warning system, allowing public health officials to better prepare for and manage pandemic waves, and efficiently allocate limited healthcare resources.

"Wastewater monitoring is already conducted in many countries, but it is limited to showing whether COVID-19 is present in a region, as well as a rough estimation of whether the burden is increasing or decreasing.

"We used artificial intelligence to pick up patterns and changes in the data and learn from this to increase the accuracy of predictions.

"Variables that can influence hospital admissions include changing behaviour due to public policies, vaccination rates, holidays and weather. The established model can help accurately predict the hospitalisation needs due to COVID-19 in the region," he said.

Dr Li hopes to extend her research to include other infectious diseases that can be detected through wastewater-based epidemiology, including food-borne pathogens, such as salmonella and E-coli, and viruses such as flu, norovirus and hepatitis A.

"My PhD focused on sewer design to reduce concrete corrosion, however I graduated right around the time of COVID-19 and saw an opportunity to monitor and study the pandemic," said Dr Li.

"I'm grateful for the opportunity to receive the WH Gladstones award, particularly as an early career researcher, to explore the potential to create early-warning systems for COVID-19 and other diseases. I hope this work can benefit the community and inspire other women in science."

Li X, Liu H, Gao L, Sherchan SP, Zhou T, Khan SJ, van Loosdrecht MCM, Wang Q.
Wastewater-based epidemiology predicts COVID-19-induced weekly new hospital admissions in over 150 USA counties.
Nat Commun. 2023 Jul 28;14(1):4548. doi: 10.1038/s41467-023-40305-x

Most Popular Now

AI Catches One-Third of Interval Breast …

An AI algorithm for breast cancer screening has potential to enhance the performance of digital breast tomosynthesis (DBT), reducing interval cancers by up to one-third, according to a study published...

Great plan: Now We need to Get Real abou…

The government's big plan for the 10 Year Health Plan for the NHS laid out a big role for delivery. However, the Highland Marketing advisory board felt the missing implementation...

Researchers Create 'Virtual Scienti…

There may be a new artificial intelligence-driven tool to turbocharge scientific discovery: virtual labs. Modeled after a well-established Stanford School of Medicine research group, the virtual lab is complete with an...

From WebMD to AI Chatbots: How Innovatio…

A new research article published in the Journal of Participatory Medicine unveils how successive waves of digital technology innovation have empowered patients, fostering a more collaborative and responsive health care...

New AI Tool Accelerates mRNA-Based Treat…

A new artificial intelligence (AI) model can improve the process of drug and vaccine discovery by predicting how efficiently specific mRNA sequences will produce proteins, both generally and in various...

AI also Assesses Dutch Mammograms Better…

AI is detecting tumors more often and earlier in the Dutch breast cancer screening program. Those tumors can then be treated at an earlier stage. This has been demonstrated by...

RSNA AI Challenge Models can Independent…

Algorithms submitted for an AI Challenge hosted by the Radiological Society of North America (RSNA) have shown excellent performance for detecting breast cancers on mammography images, increasing screening sensitivity while...

AI could Help Emergency Rooms Predict Ad…

Artificial intelligence (AI) can help emergency department (ED) teams better anticipate which patients will need hospital admission, hours earlier than is currently possible, according to a multi-hospital study by the...

Head-to-Head Against AI, Pharmacy Studen…

Students pursuing a Doctor of Pharmacy degree routinely take - and pass - rigorous exams to prove competency in several areas. Can ChatGPT accurately answer the same questions? A new...

NHS Active 10 Walking Tracker Users are …

Users of the NHS Active 10 app, designed to encourage people to become more active, immediately increased their amount of brisk and non-brisk walking upon using the app, according to...

New AI Tool Illuminates "Dark Side…

Proteins sustain life as we know it, serving many important structural and functional roles throughout the body. But these large molecules have cast a long shadow over a smaller subclass...

Deep Learning-Based Model Enables Fast a…

Stroke is the second leading cause of death globally. Ischemic stroke, strongly linked to atherosclerotic plaques, requires accurate plaque and vessel wall segmentation and quantification for definitive diagnosis. However, conventional...