How AI Could Help Combat Antibiotic Resistance

Antibiotic resistance is a rapidly worsening public health crisis, causing more than 1 million deaths each year worldwide and contributing to nearly 5 million additional deaths. These infections are more difficult and expensive to treat than traditional infections and result in longer hospital stays, increasing costs for hospitals and patients.

Treatment relies mainly on guesswork on the part of doctors. Ara Darzi, surgeon and director of the Institute for Global Health Innovation at Imperial College London, says AI-based diagnostics offer a better solution.

“We find ourselves right now, in 2026, at the first real inflection point in this crisis,” Darzi told WIRED Health in London on April 16.

The overuse and misuse of antibiotics and the lack of development of new drugs have fueled the rise of resistant microbes. When bacteria are exposed to levels of antibiotics that don’t kill them immediately, they develop defense mechanisms to survive. Unnecessary prescriptions allow bacteria to develop immunity, rendering life-saving medications ineffective. That means a shrinking list of treatment options for patients with serious infections.

The problem will get worse. A 2024 report in The Lancet predicts that drug-resistant infections could cause 40 million deaths by 2050.

Traditional diagnostics to determine an antibiotic-resistant infection typically take two to three days because they require culturing bacteria from a sample. But for some infections, like sepsis, patients don’t have that time. For every hour of delay in treatment, the risk of death increases by 4 to 9 percent. While waiting for test results, doctors must use judgment in choosing which antibiotics to use.

AI-based diagnostics could help inform these decisions. “AI-based diagnostics achieve greater than 99% accuracy without additional laboratory infrastructure,” Darzi said.

These types of rapid diagnostics are especially needed in rural and remote areas around the world, he added. The World Health Organization estimates that antibiotic resistance is highest in Southeast Asia and the Eastern Mediterranean, where one in three reported infections were resistant in 2023. In Africa, one in five infections was resistant.

AI could also help discover new drugs for resistant infections and predict the spread of resistant bacteria. The UK’s National Health Service is working with Google DeepMind to develop an AI system to combat antibiotic resistance. In a demonstration, the system identified previously unknown resistance mechanisms in just 48 hours, unraveling a mystery that had taken researchers at Imperial College London a decade to understand.

Combined with an automated laboratory, Darzi said it is now possible to run hundreds of parallel experiments around the clock. Deep learning models can now analyze billions of molecular structures in days, while generative AI is used to design compounds that do not exist in nature.

Yet major pharmaceutical companies have abandoned antibiotic development due to a failing business model. New antibiotics should be reserved to prevent resistance, but pharmaceutical companies profit from their high-volume sales. Companies have little incentive to stay in the race.

Darzi argued that new payment models are needed to encourage the development of new antibiotics. In 2024, the UK launched a pilot program for a Netflix-style payment model in which the government pays a fixed annual subscription to a pharmaceutical company for access to new antibiotics, not for the volume prescribed. Sweden is also experimenting with a partially dissociated model.

“The question that will determine the shape of medicine for the next 100 years is not whether we have the tools to answer it. We have the tools,” he said. “The question is whether we have the character to take seriously what we see.”