The World Health Organization estimates that 10 million annual deaths could occur as a direct result of drug-resistant infections globally by 2050, but developing new antibiotics requires a substantial amount of time and money.
The cost of producing a new antibiotic, a medication taken for a short period of time, is comparable to the amount it would require for a new cancer drug, a medication taken for months or years. The demanding cost, long drug approval periods and the easy access to generic drugs creates little motive for the development of new antibiotics, according to the release.
However, AI and machine learning significantly reduces time by cutting the number of experiments needed for screening potential drugs and reduces cost by filtering out unpromising compounds, according to the report.
Additionally, researchers have proven the effectiveness of AI-identified antibiotics in killing Acinetobacter baumannii, a common bacteria in hospital infections.
Experts told Scientific American the use of AI to identify antibiotic candidates is in its infancy, and the candidates identified by AI would still need to undergo the long process to become a drug on the market. Still, Jocelyn Ulrich, deputy vice president for policy and research at Pharmaceutical Research and Manufacturers of America, said, “I’d say there’s immense potential and immense excitement around some of these tools.”
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.
