A prototype AI chatbot tool has been developed to help pull together vital human, animal and environmental health information to support the global response to antimicrobial resistance (AMR).
AMR is when microorganisms that cause infections, such as bacteria and viruses, change over time and no longer respond to antibiotic medicines.
It makes serious conditions such as HIV, tuberculosis and malaria more difficult to treat and increases the risk of severe illness, disease spread and death.
In 2015 the World Health Organization (WHO) formulated a Global Action Plan to co-ordinate efforts to tackle AMR.
As a result, 194 WHO member states committed to developing country-specific One Health AMR National Action Plans (NAPs).
The One Health model recognises the interconnection between people, animals, plants, and their shared environment.
However, inadequate logistical capacity, funding, and poor access to essential information can hinder informed NAP policymaking, especially in low-to-middle-income countries.
Now an international team of researchers including Professor David Graham from our Biosciences Department has created an AI tool to bridge critical gaps in knowledge.
The large language model tool developed by the research team, called the AMR-Policy GPT, contains information from AMR-related policy documents from 146 countries.
It works in similar way to established AI chatbots such as ChatGPT, but has a focusing element that encourages more current, accurate, and contextually relevant information on AMR compared with more generic chatbots.
The research has been published in the journal Environmental Science & Technology.
The researchers stress that the primary purpose of AMR-Policy GPT is an ‘intelligent’ information source to assist in the policymaking process - like having a smart friend in the room.
It is not designed to write comprehensive NAPs.
The researchers will continue to build on the prototype and explore how it can be further improved and expanded following feedback from users.
In the future they would like to integrate even more scientific knowledge with policy information to create an enhanced AMR-Policy GPT.
/prod01/prodbucket01/media/durham-university/central-news-and-events-images/83431-1920X290.jpg)