AI can reduce the number of animals needed for research

AI reduces the use of laboratory mice in research Keystone-SDA

Researchers at Swiss Federal Institute of Technology ETH Zurich have developed a new, AI-supported method that analyses the behaviour of mice in the laboratory more efficiently. As a result, biomedical research requires fewer laboratory mice.

The method uses automatic behavioural analysis by means of image recognition and artificial intelligence (AI). Mice are filmed and the video recordings are automatically analysed, writes ETH Zurich in a press releaseExternal link issued on Thursday.

+Get the most important news from Switzerland in your inbox

The analysis of animal behaviour often involves days of laborious manual work, writes the institute. In recent years, leading research laboratories around the world have switched to powerful automated behavioural analysis. But this generates mountains of data and the more extensive the data and the finer the differences in behaviour to be recorded, the greater the risk of misinterpretation, according to the ETH Zurich.

Stress resistance tested

The Swiss researchers’ new method now makes it possible to obtain meaningful results even with a smaller group of animals and to identify subtle behavioral differences between the animals. The new approach also helps to reduce the number of test animals. And the standardisation of tests can be increased.

Using the new method, the Swiss team has already been able to find out how mice react to stress and certain drugs in animal experiments. And that acute and chronic stress change the behaviour of mice differently.

Adapted from German by DeepL/ac

How we work

This news story has been written and carefully fact-checked by an external editorial team. At SWI swissinfo.ch we select the most relevant news for an international audience and use automatic translation tools such as DeepL to translate it into English. Providing you with automatically translated news gives us the time to write more in-depth articles.

If you want to know more about how we work, have a look here, if you want to learn more about how we use technology, click here, and if you have feedback on this news story please write to [e-mail].