LONDON, Nov. 15 (Xinhua) -- A team of researchers have demonstrated that machine learning could be an effective tool in determining whether a new drug works in the brain, according to a study released on Wednesday by the University College London (UCL).
Machine learning is a type of artificial intelligence that allows software applications to become more accurate in predicting outcomes without being explicitly programmed.
"Current statistical models are too simple. They fail to capture complex biological variations across people, discarding them as mere noise. We suspected this could partly explain why so many drug trials work in simple animals, but fail in the complex brains of humans," said the study's lead author, Dr. Parashkev Nachev from UCL.
The team believes that machines capable of modelling the human brain in its full complexity may uncover treatment effects that would otherwise be missed.
In this study, they simulated a large-scale meta-analysis of a set of hypothetical drugs based on key information extracted from large-scale data from stroke patients. The aim was to see if treatment effects of different magnitudes that would have been missed by conventional statistical analysis could be identified with machine learning.
Stroke trials tend to use relatively few, crude variables, such as the size of the lesion, ignoring whether the lesion is centred on a critical area or at the edge of it, but the team's algorithm "learned the entire pattern of damage across the brain instead, employing thousands of variables at high anatomical resolution," said the study's first author Tianbo Xu from UCL.
By illuminating the complex relationship between anatomy and clinical outcome, it enabled the team to detect therapeutic effects with far greater sensitivity than conventional techniques, explained Xu.
The findings demonstrate that machine learning could be invaluable to medical science, especially when the system under study, such as the brain, is highly complex.
"The real value of machine learning lies not so much in automating things we find easy to do naturally, but formalizing very complex decisions. Machine learning can combine the intuitive flexibility of a clinician with the formality of the statistics that drive evidence-based medicine," said Nachev.
The study has been published in the journal Brain.
