AI-powered diagnostics achieving above 99 percent accuracy could help combat antibiotic resistance, a public health crisis causing more than a million global deaths annually.

Antibiotic resistance causes more than a million global deaths annually and contributes to nearly 5 million more. Traditional diagnostics to identify resistant infections take two to three days; for every hour of delayed treatment in infections like sepsis, the risk of death increases by between 4 to 9 percent.

AI-based diagnostics are achieving accuracy above 99 percent without additional laboratory infrastructure, according to Ara Darzi, director of the Institute of Global Health Innovation at Imperial College London. The UK's National Health Service is working with Google DeepMind on an AI system that identified previously unknown mechanisms of resistance in 48 hours—a discovery that took Imperial College London researchers a decade to understand.

A 2024 report in The Lancet predicted that drug-resistant infections could cause 40 million deaths by 2050. Major pharmaceutical companies have reduced antibiotic development due to an economic model that discourages investment; new antibiotics must be reserved to prevent resistance, but companies profit from high-volume sales. The UK began a pilot program in 2024 using a Netflix-style subscription payment model in which the government pays a fixed annual fee for access to new antibiotics, and Sweden is experimenting with a partially delinked model.