UNLV Develops AI to Detect Viruses Earlier for Rapid Response

Researchers at the University of Nevada, Las Vegas (UNLV), in collaboration with the Southern Nevada Water Authority and other partners, have developed an artificial intelligence algorithm to accelerate wastewater surveillance for emerging viruses and pathogens. Validated through analysis of nearly 3,700 wastewater samples collected between 2021 and 2023, the system accurately identified unique viral signatures with as few as two to five samples, preceding conventional clinical detection methods. This proactive approach, detailed in a study published on July 8, 2025, aims to enhance public health interventions by detecting outbreaks before patients seek treatment, and is one of over 30 collaborations between the involved organisations.

AI-Enhanced Wastewater Surveillance

Researchers are now exploring methods to accelerate wastewater surveillance, aiming to detect emerging viruses and novel variants before patients exhibit symptoms. A recent study led by the University of Nevada, Las Vegas (UNLV) demonstrates the potential of pairing wastewater sample surveillance with artificial intelligence to achieve this goal, with findings published in Nature Communications.

This research showcases the possibility of identifying future outbreaks before the first patient seeks clinical attention, representing a proactive shift in disease surveillance. The AI algorithm enables the determination of pathogen evolution without requiring direct human testing, proving particularly valuable for improving surveillance in rural communities and empowering health workers in resource-constrained settings.

The research team validated their approach by analysing nearly 3,700 wastewater samples collected from Southern Nevada treatment facilities between 2021 and 2023. Results indicated that the AI system could accurately identify unique signatures for different virus variants with as few as two to five samples, considerably earlier than existing methods. Traditional wastewater detection relies on prior knowledge of a variant’s genetic makeup and clinical data from tested patients, functioning as a reactive rather than proactive measure.

By proactively detecting patterns from multiple wastewater samples, the AI-enhanced system offers an even more effective tool for public health surveillance, particularly in identifying novel threats without requiring prior knowledge or patient testing data. This builds upon the existing benefits of wastewater surveillance, which enables timely and proactive public health responses by monitoring disease emergence and spread at a population level.

Since 2021, a collaborative effort involving UNLV, the Southern Nevada Water Authority (SNWA), the Southern Nevada Health District, and the Desert Research Institute has maintained a public wastewater surveillance dashboard tracking COVID-19 and other viruses. The Nature Communications study is one of over 30 collaborations between these organisations, along with the Cleveland Clinic Lou Ruvo Center for Brain Health, and represents one of the first applications of AI to enhance wastewater intelligence.

Accelerated Pathogen Detection

The study, titled ‘Early detection of emerging SARS-CoV-2 Variants from wastewater through genome sequencing and machine learning’, was published on July 8, 2025. Daniel Gerrity, principal research microbiologist at SNWA, highlights the value of wastewater surveillance in filling critical data gaps and improving understanding of public health conditions within a community, emphasising the positive impact of collaboration between SNWA, UNLV, and other partners.

This research represents one of the first applications of AI to enhance wastewater intelligence, building upon over 30 collaborations between UNLV, the Southern Nevada Water Authority (SNWA), the Southern Nevada Health District, the Desert Research Institute, and the Cleveland Clinic Lou Ruvo Center for Brain Health since 2021. These organisations have jointly maintained a public wastewater surveillance dashboard tracking COVID-19 and other viruses.

Collaborative Public Health Infrastructure

The research team’s approach was validated through the analysis of nearly 3,700 wastewater samples collected from Southern Nevada treatment facilities between 2021 and 2023. Results indicated the AI system could accurately identify unique signatures for different virus variants with as few as two to five samples, considerably earlier than existing methods. Traditional wastewater detection methods function as a reactive measure, relying on prior knowledge of a variant’s genetic makeup and clinical data from tested patients.

This new method builds upon the existing benefits of wastewater surveillance, which enables timely and proactive public health responses by monitoring disease emergence and spread at a population level. By proactively detecting patterns from multiple wastewater samples, the AI-enhanced system offers an even more effective tool for public health surveillance, particularly in identifying novel threats without requiring prior knowledge or patient testing data. The study, titled ‘Early detection of emerging SARS-CoV-2 Variants from wastewater through genome sequencing and machine learning’, was published on July 8, 2025.