The incorporation of machine learning in clinical trials could improve research of effective drug treatments in the brain. It could also provide information on drug side-effects previously missed by conventional statistical tests, according to a study published in Brain.
Currently, many clinical drug trials fail to achieve results in the human brain after showing promise in the brains of animals. In response, researchers in this study aimed to provide evidence to the benefits of using machine learning in clinical trials.
"The real value of machine learning lies not so much in automating things we find easy to do naturally, but formalizing very complex decisions,” said the study's lead author, Parashkev Nachev (UCL Institute of Neurology). “Machine learning can combine the intuitive flexibility of a clinician with the formality of the statistics that drive evidence-based medicine. Models that pull together 1,000s of variables can still be rigorous and mathematically sound. We can now capture the complex relationship between anatomy and outcome with high precision.”
The study analyzed data on stroke patients to identify the pattern of brain damage caused by the stroke and created a large collection of anatomical registered images of stroke. Researchers then simulated a meta-analysis of hypothetical drugs to view treatment effects that could be caught by machine learning. The machine learning also looked for the presence or absence of damage across the brain.
“Our algorithm learned the entire pattern of damage across the brain instead, employing thousands of variables at high anatomical resolution. By illuminating the complex relationship between anatomy and clinical outcome, it enabled us to detect therapeutic effects with far greater sensitivity than conventional techniques," explained the study's first author, Tianbo Xu (UCL Institute of Neurology).