Researchers at the University of Zurich have made a significant breakthrough in detecting antibiotic resistance in bacteria using artificial intelligence. Led by Professor Adrian Egli, the team utilized GPT-4, a powerful AI model developed by OpenAI, to analyze antibiotic resistance. The researchers created an AI system called "EUCAST-GPT-expert" that follows strict EUCAST guidelines for interpreting antimicrobial resistance mechanisms. By incorporating the latest data and expert rules, the system was tested on hundreds of bacterial isolates, helping to identify resistance to life-saving antibiotics.
While human experts were more accurate in determining resistance, the AI system performed well in detecting certain types of resistance and could help standardize and speed up the diagnostic process. According to Egli, "Antibiotic resistance is a growing threat worldwide, and we urgently need faster, more reliable tools to detect it." The study highlights the transformative potential of AI in healthcare, with the possibility of reducing variability and subjectivity in manual readings, improving patient outcomes.
↧