(Press-News.org) A new AI tool to predict the spread of infectious disease outperforms existing state-of-the-art forecasting methods.
The tool, created with federal support by researchers at Johns Hopkins and Duke universities, could revolutionize how public health officials predict, track and manage outbreaks of infectious diseases including flu and COVID-19.
“COVID-19 elucidated the challenge of predicting disease spread due to the interplay of complex factors that were constantly changing,” said author Lauren Gardner of Johns Hopkins, a modeling expert who created the COVID-19 dashboard that was relied upon by people worldwide during the pandemic. “When conditions were stable the models were fine. However, when new variants emerged or policies changed, we were terrible at predicting the outcomes because we didn’t have the modeling capabilities to include critical types of information. The new tool fills this gap.”
The work is newly published in Nature Computational Science.
During the coronavirus pandemic, the technology that underpins the new tool didn’t exist. The team for the first time uses large language modeling, the type of generative AI used most famously in ChatGPT, to predict the spread of disease.
Instead of treating prediction merely like a math problem, the model, which is named PandemicLLM, reasons with it, considering inputs such as recent infection spikes, new variants, and mask mandates.
The team fed the model streams of information, including data never used before in pandemic prediction tools, and found PandemicLLM could accurately predict disease patterns and hospitalization trends one to three weeks out, consistently outperforming other methods including the highest performing ones on the CDC’s CovidHub.
“A pressing challenge in disease prediction is trying to figure out what drives surges in infections and hospitalizations, and to build these new information streams into the modeling,” Gardner said.
The model relies on four types of data:
State-level spatial data including information on demographics, the healthcare system and political affiliations.
Epidemiological time series data such as reported cases, hospitalizations and vaccine rates.
Public health policy data including stringency and types of government policies.
Genomic surveillance data including information about the characteristics of disease variants and their prevalence.
After consuming this information, the model can predict how the various elements will come together to affect how the disease behaves.
To test it, the team retroactively applied it to the COVID-19 pandemic, drilling down on each U.S. state over 19 months. Compared to other models, the new tool was particularly successful when the outbreak was in flux.
“Traditionally we use the past to predict the future,” said author Hao “Frank” Yang, a Johns Hopkins assistant professor of Civil and Systems Engineering who specializes in developing reliable AI. “But that doesn’t give the model sufficient information to understand and predict what’s happening. Instead, this framework uses new types of real-time information.”
With the necessary data, the model can be adapted for any infectious disease, including bird flu, monkeypox and RSV.
The team is now exploring the capability of LLMs to replicate how individuals make decisions about their health, hoping such a model would help officials design safer and more effective policies.
“We know from COVID-19 that we need better tools so that we can inform more effective policies,” Gardner said. “There will be another pandemic, and these types of frameworks will be crucial for supporting public health response.”
Authors included: Johns Hopkins PhD student Hongru Du; Johns Hopkins graduate student Yang Zhao; Jianan Zhao of University of Montreal; Johns Hopkins PhD student Shaochong Xu, Xihong Lin of Harvard University and Duke University Prof. Yiran Chen.
END
New AI reimagines infectious disease forecasting
Tool first to use large language modeling to predict infectious disease risk
2025-06-06
ELSE PRESS RELEASES FROM THIS DATE:
Scientific community urges greater action against the silent rise of liver diseases
2025-06-06
During the first meeting of the Global Think-tank on Steatotic Liver Disease, supported by the Barcelona Institute for Global Health (ISGlobal) and held in the Palau Macaya of Barcelona on 5–6 June, more than 100 international experts issued a stark warning: millions of people will continue to go unseen by healthcare systems unless early detection and person-centred care for liver disease are prioritised without delay.
A common but invisible disease
Metabolic dysfunction-associated steatotic liver disease (MASLD) affects around 33% of adults globally. Its more aggressive form, metabolic dysfunction-associated steatohepatitis (MASH), is estimated to affect 5% of the general ...
Tiny but mighty: sophisticated next-gen transistors hold great promise
2025-06-06
Tokyo, Japan – Hailed as one of the greatest inventions of the 20th century, transistors are integral components of modern electronics that amplify or switch electrical signals. As electronics become smaller, it is becoming increasingly difficult to continue scaling down silicon-based transistors. Has the development of our electronics hit a wall?
Now, a research team led by the Institute of Industrial Science, The University of Tokyo, has sought a solution. As detailed in their new paper, to be issued in 2025 Symposium on VLSI Technology and Circuits , the team ditched the silicon and instead opted to create a transistor made from gallium-doped ...
World's first practical surface-emitting laser for optical fiber communications developed: advancing miniaturization, energy efficiency, and cost reduction of light sources
2025-06-06
Highlights
- Development of the world's first practical surface-emitting laser suitable for optical fiber communications systems.
- Utilization of quantum dots as an optical gain medium, enabled by NICT's high-precision crystal growth technology and Sony's advanced processing technology.
- A significant advancement toward miniaturization, reduced power consumption, and cost efficiency of light sources used in optical fiber communication systems.
Abstract
The National Institute of Information ...
Statins may reduce risk of death by 39% for patients with life-threatening sepsis
2025-06-06
Sepsis is when the immune system overshoots its inflammatory reaction to an infection, so strongly that the vital organs begin to shut down. It is life-threatening: each year in the US alone, approximately 750,000 patients are hospitalized for sepsis, of which approximately 27% die. In about 15% of cases, sepsis worsens into septic shock, characterized by dangerously low blood pressure and reduced blood flow to tissues. The risk of death from septic shock is even higher, between 30% and 40%.
The earlier patients with sepsis are treated, the better their prospects. Typically, they receive ...
Paradigm shift: Chinese scientists transform "dispensable" spleen into universal regenerative hub
2025-06-06
Dual Breakthroughs in Diabetes Cure and Organ Regeneration Redefine Medical Frontiers
NANJING, China – In a revolutionary one-two punch, Chinese research teams have successfully engineered the human spleen into a living bioreactor capable of curing diabetes and growing functional organs – achievements published back-to-back in Science Translational Medicine and Diabetes this month. This convergence of discoveries positions the long-underestimated spleen as a game-changing platform for regenerative medicine.
The Spleen Solution: From Biological Filter to Life-Saving Factory
Once considered expendable, the spleen now emerges as the body’s ...
Medieval murder: Records suggest vengeful noblewoman had priest assassinated in 688-year-old cold case
2025-06-06
A Cambridge criminologist has uncovered new evidence in the killing of a priest, John Forde, who had his throat cut on a busy London street almost seven centuries ago.
The case is among hundreds catalogued by the Medieval Murder Maps project at Cambridge University’s Institute of Criminology, a database of unnatural death in England during the 14th century. This one, however, has a few twists.
Records traced by Prof Manuel Eisner suggest that John Forde’s slaying in 1337 was a revenge killing orchestrated by a noblewoman ordered to enact years of degrading penance after the Archbishop of Canterbury discovered the clergyman was her lover – possibly from ...
Desert dust forming air pollution, new study reveals
2025-06-06
Dust particles thrown up from deserts such as the Saraha and Gobi are playing a previously unknown role in air pollution, a new study has found.
The international study published in National Science Review has revealed that contrary to long-held scientific assumptions, aged desert dust particles which were once considered too big and dry to host significant chemical reactions actually act as "chemical reactors in the sky"—facilitating the formation of secondary organic aerosols (SOA), a major component of airborne particles.
Published in a collaborative effort led by scientists ...
A turning point in the Bronze Age: the diet was changed and the society was transformed
2025-06-05
The bioarchaeological investigation of the Bronze Age cemetery of Tiszafüred-Majoroshalom has shed new light on an important period in Central European history. An international research team – led by Tamás Hajdu, associate professor at the Department of Anthropology at ELTE and Claudio Cavazzuti, senior assistant professor at the University of Bologna, has shown that around 1500 BC, radical changes occurred in people’s lives: they ate and lived differently, and the social system was also reorganized.
The ...
Drought-resilient plant holds promise for future food production, study finds
2025-06-05
For the first time, researchers have demonstrated in an intact plant a long-contested process that allows some plants to rebound from extended drought. The team of Colorado State University, University of Colorado and U.S. Department of Agriculture scientists says understanding this special trait could improve agricultural productivity and food security.
Drought costs the United States billions in agricultural losses and increased irrigation. Lost productivity lowers food availability and raises prices for ...
To spot toxic speech online, try AI
2025-06-05
Earlier this year, Facebook rolled back rules against some hate speech and abuse. Along with changes at X (formerly Twitter) that followed its purchase by Elon Musk, the shifts make it harder for social media users to avoid encountering toxic speech.
That doesn’t mean that social networks and other online spaces have given up on the massive challenge of moderating content to protect users. One novel approach relies on artificial intelligence. AI screening tools can analyze content on large scales while sparing human screeners the trauma of constant exposure to toxic speech.
But AI content ...
LAST 30 PRESS RELEASES:
Youngest in class at higher risk of mental health problems
American Heart Association announces new volunteer leaders for 2025-26
Gut microbiota analysis can help catch gestational diabetes
FAU’s Paulina DeVito awarded prestigious NSF Graduate Research Fellowship
Champions for change – Paid time off initiative just made clinical trials participation easier
Fentanyl detection through packaging
Prof. Eran Meshorer elected to EMBO for pioneering work in epigenetics
New 3D glacier visualizations provide insights into a hotter Earth
Creativity across disciplines
Consequences of low Antarctic sea ice
Hear here: How loudness and acoustic cues help us judge where a speaker is facing
A unique method of rare-earth recycling can strengthen the raw material independence of Europe and America
Epilepsy self-management program shows promise to control seizures, improve mood and quality of life
Fat may play an important role in brain metabolism
New study finds no lasting impact of pandemic pet ownership on human well-being
New insights on genetic damage of some chemotherapies could guide future treatments with less harmful side effects
Gut microbes could protect us from toxic ‘forever chemicals’
Novel modelling links sea ice loss to Antarctic ice shelf calving events
Scientists can tell how fast you're aging from a single brain scan
U.S. uterine cancer incidence and mortality rates expected to significantly increase by 2050
Public take the lead in discovery of new exploding star
What are they vaping? Study reveals alarming surge in adolescent vaping of THC, CBD, and synthetic cannabinoids
ECMWF - delivering forecasts over 10 times faster and cutting energy usage by 1000
Brazilian neuroscientist reveals how viral infections transform the brain through microscopic detective work
Turning social fragmentation into action through discovering relatedness
Cheese may really be giving you nightmares, scientists find
Study reveals most common medical emergencies in schools
Breathable yet protective: Next-gen medical textiles with micro/nano networks
Frequency-engineered MXene supercapacitors enable efficient pulse charging in TENG–SC hybrid systems
Developed an AI-based classification system for facial pigmented lesions
[Press-News.org] New AI reimagines infectious disease forecastingTool first to use large language modeling to predict infectious disease risk