AI chatbot developed to aid governments in tackling drug resistance

Scientists have developed an AI chatbot similar to ChatGPT to help governments devise effective policies for battling drug resistance.

Antimicrobial Resistance (AMR), where disease-causing bacteria and viruses no longer respond to the medicines designed to treat them, contributes to millions of deaths a year and results in health care costs of up to US$412 billion a year, according to the World Health Organization (WHO).

In low- and middle-income countries, poor sanitation, limited access to quality medicines, and inappropriate antibiotic use are fueling the rise in AMR, while serious conditions such as HIV, tuberculosis and malaria are becoming more difficult to treat.

In 2015, the WHO came up with a Global Action Plan to tackle AMR under the One Health model, which recognizes the interconnection between people, animals, plants, and their shared environment.

But “major gaps exist between aspirations and actions” when it comes to developing the necessary policies in low-to-middle-income countries, according to a study published in the journal Environmental Science and Technology.

‘Smart friend’

The international team of researchers from the Chinese Academy of Sciences and Durham University, UK, created an AI chatbot designed to bridge these gaps and assist in the preparation of National Action Plans.

The large language model tool, called the AMR-Policy GPT, contains information from AMR-related policy documents from 146 countries.

“AMR-Policy GPT is a conversational chatbot,” said David Graham, an environmental engineer at Durham University and lead co-author.

“It allows you to ask questions and provides you with answers related to the questions you ask.”

Unlike ChatGPT—which harvests everything from the wider information universe to answer your questions—AMR-Policy GPT filters for quality, selecting technical information relevant to the subject, according to the researchers.

“It’s like having a smart friend in the room,” Graham told SciDev.Net.

While the tool cannot formulate policy, it draws on national policy plans, grey literature, and other policy guidance from intergovernmental agencies to encourage lawmakers to consider various policy options, says Graham.

So, if you are in a country, for example, in Sub-Saharan Africa, and you have hardly any information around your own country, you can ask the bot and it looks around at information that’s related to your question and your place.”

David Graham, environmental engineer at Durham University

“Ideally, the tool provides decision-makers with well-researched information from across all disciplines, including animal agriculture, crops, water quality and infectious diseases.”

Although it’s designed with policy in mind, the tool can be used by anyone to ask any questions about AMR. “And you don’t have to have advanced knowledge of AI,” added Graham.

As good as the data

Emmanuel Mukambo, a medical doctor and dementia researcher in Zambia, says AI is transforming how global health challenges are tackled by making information more accessible and easier to analyse.

“AI allows us to process large amounts of data quickly, uncover patterns, and gain insights that we might otherwise miss,” he told SciDev.Net.

But he cautioned: “AI is only as good as the data it learns from.”

In the case of dementia, most of this comes from studies done in Western countries, said Mukambo, adding: “This makes it hard to apply those findings to places like Africa, where research hasn’t kept pace.

“AI tools have the potential to make a real difference in this part of the world, but only if we use them to amplify voices and stories that have been overlooked for too long,” he said.