How AI Is Fighting Antibiotic Resistance

Antibiotic resistance has escalated into one of the fastest-growing public health emergencies of our time, claiming over a million lives each year and contributing to nearly 5 million more deaths globally. These resistant infections are not only harder to treat but also far more expensive, often leading to extended hospital stays that drive up costs for both medical facilities and patients.

Currently, physicians largely rely on guesswork when selecting treatments. Ara Darzi, a surgeon and director of the Institute of Global Health Innovation at Imperial College London, believes AI-powered diagnostics can change that. “We’re standing, right now, in 2026, at the first genuine inflection point in this crisis,” Darzi said on April 16 at WIRED Health in London.

The rise of resistant microbes has been fueled by the overuse and misuse of antibiotics, combined with a stagnant pipeline for new drug development. When bacteria encounter antibiotic levels too low to kill them, they develop defense mechanisms to survive. Unnecessary prescriptions only accelerate this process, rendering life-saving drugs ineffective and shrinking the list of viable treatment options for patients with serious infections.

The outlook is grim. A 2024 report in The Lancet projected that drug-resistant infections could cause 40 million deaths by 2050.

Traditional diagnostic methods for identifying antibiotic-resistant infections typically take two to three days, relying on culturing bacteria from a sample. For time-sensitive conditions like sepsis, that delay can be fatal. Every hour of delayed treatment raises the risk of death by 4 to 9 percent. While waiting for test results, doctors must rely on their best judgment when choosing antibiotics.

AI-based diagnostics could transform this decision-making process. “AI-powered diagnostics are achieving accuracy above 99 percent without additional laboratory infrastructure,” Darzi said.

These rapid diagnostics are particularly critical in rural and remote regions. The World Health Organization reports 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 showed resistance.

AI also holds promise for discovering new drugs to combat resistant infections and predicting the spread of resistant bacteria. The UK’s National Health Service is collaborating with Google DeepMind to develop an AI system aimed at tackling antibiotic resistance. In one demonstration, the system identified previously unknown resistance mechanisms in just 48 hours, solving a puzzle that had taken Imperial College London researchers a decade to unravel.

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

Despite these technological advances, major pharmaceutical companies have abandoned antibiotic development due to a broken economic model. New antibiotics must be reserved to prevent resistance, but pharma companies rely on high-volume sales for profit. There is little incentive for them to stay in the game.

Darzi argued that new payment models are essential to encourage antibiotic development. In 2024, the UK launched a pilot program using a Netflix-style subscription model, where the government pays a fixed annual fee to a pharmaceutical company for access to new antibiotics, regardless of how much is prescribed. Sweden is also experimenting with a partially delinked model.

“The question that will determine the shape of medicine for the next 100 years, is not whether we have the tools to respond. We have the tools,” Darzi said. “The question is whether we have the character to take seriously what we are seeing.”