Machine learning for digital diagnostics of antimicrobial resistance
If action is not taken, antimicrobial resistance (AMR) will cost $100 trillion and claim 10 million lives annually by 2050. The factors driving AMR extend beyond human healthcare, with implications in veterinary medicine, agriculture, and the environment. New and improved approaches for tackling AMR include better monitoring, rational drug use, different business models to generate antibiotics, innovation at all levels, and most importantly, a global approach.
This project assembles a transnational team (Canada, China, Finland, France) to apply new machine learning approaches for faster diagnosis and better monitoring of resistance. The initial focus will be on two major global pathogens that have developed multi-drug resistance: Pseudomonas aeruginosa and Streptococcus pneumoniae. The research team will develop machine learning that can orient treatment selection by assessing the level of resistance, providing a rationale for generating novel antibiotics, and assisting in the surveillance of human and livestock antimicrobial resistance.
This is one of five IDRC-funded projects developed through the Joint Programming Initiative on Antimicrobial Resistance (JPIAMR), an international collaborative platform that coordinates global funding to support collaborative research and action on antimicrobial resistance. Through the JPIAMR, IDRC has partnered with 18 other donor agencies to fund innovative research projects on diagnostics and surveillance strategies, as well as tools and technologies that can be used to detect and monitor antimicrobial resistance in human, veterinary, and environmental settings, particularly in low- and middle-income countries.