Improving clinical trials with machine learning

November 15, 2017, University College London
Credit: CC0 Public Domain

Machine learning could improve our ability to determine whether a new drug works in the brain, potentially enabling researchers to detect drug effects that would be missed entirely by conventional statistical tests, finds a new UCL study published in Brain.

"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. If so, capable of modelling the human in its full complexity may uncover treatment effects that would otherwise be missed," said the study's lead author, Dr Parashkev Nachev (UCL Institute of Neurology).

To test the concept, the research team looked at large-scale data from patients with stroke, extracting the complex anatomical pattern of brain damage caused by the stroke in each patient, creating in the process the largest collection of anatomically registered images of stroke ever assembled. As an index of the impact of stroke, they used gaze direction, objectively measured from the eyes as seen on head CT scans upon hospital admission, and from MRI scans typically done 1-3 days later.

They then simulated a large-scale meta-analysis of a set of hypothetical drugs, to see if treatment effects of different magnitudes that would have been missed by conventional statistical analysis could be identified with machine learning. For example, given a drug treatment that shrinks a by 70%, they tested for a significant effect using conventional (low-dimensional) statistical tests as well as by using high-dimensional machine learning methods.

The machine learning technique took into account the presence or absence of damage across the entire brain, treating the stroke as a complex "fingerprint", described by a multitude of variables.

"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. 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).

The advantage of the machine learning approach was particularly strong when looking at interventions that reduce the volume of the lesion itself. With conventional low-dimensional models, the intervention would need to shrink the lesion by 78.4% of its volume for the effect to be detected in a trial more often than not, while the high-dimensional model would more than likely detect an effect when the lesion was shrunk by only 55%.

"Conventional statistical models will miss an effect even if the drug typically reduces the size of the lesion by half, or more, simply because the complexity of the brain's functional anatomy—when left unaccounted for—introduces so much individual variability in measured clinical outcomes. Yet saving 50% of the affected brain area is meaningful even if it doesn't have a clear impact on behaviour. There's no such thing as redundant brain," said Dr Nachev.

The researchers say their 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 formalising very complex decisions. 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 1000s of variables can still be rigorous and mathematically sound. We can now capture the complex relationship between anatomy and outcome with high precision," said Dr Nachev.

"We hope that researchers and clinicians begin using our methods the next time they need to run a clinical trial," said co-author Professor Geraint Rees (Dean, UCL Faculty of Life Sciences).

Explore further: Drinking coffee may be associated with reduced risk of heart failure and stroke

More information: Brain (2017). DOI: 10.1093/brain/awx288

Related Stories

Drinking coffee may be associated with reduced risk of heart failure and stroke

November 14, 2017
Drinking coffee may be associated with a decreased risk of developing heart failure or having stroke, according to preliminary research presented at the American Heart Association's Scientific Sessions 2017, a premier global ...

Conclusions on brain-machine interfaces for communication and rehabilitation

October 5, 2016
In the journal Nature Reviews Neurology, the researcher Ander Ramos of Tecnalia, with Niel Birbaumer, lecturer at the University of Tübingen, have expounded how brain-machine interfaces (BMI) use brain activity to control ...

High-resolution brain imaging could improve detection of concussions

December 1, 2016
High-resolution brain scans analyzed by machine learning algorithms could determine whether a patient has a concussion, according to a new study published in PLOS Computational Biology.

A portable tiny brain scanner for studying brain disorders in infants

October 12, 2017
(Medical Xpress)—A team of researchers affiliated with several institutions in France has developed a new type of brain scanner that is small enough for use on infants. In their paper published in the journal Science Translational ...

Machine learning identifies breast lesions likely to become cancer

October 17, 2017
A machine learning tool can help identify which high-risk breast lesions are likely to become cancerous, according to a new study appearing online in the journal Radiology. Researchers said the technology has the potential ...

Physicists extend quantum machine learning to infinite dimensions

March 6, 2017
Physicists have developed a quantum machine learning algorithm that can handle infinite dimensions—that is, it works with continuous variables (which have an infinite number of possible values on a closed interval) instead ...

Recommended for you

Parents' brain activity 'echoes' their infant's brain activity when they play together

December 13, 2018
When infants are playing with objects, their early attempts to pay attention to things are accompanied by bursts of high-frequency activity in their brain. But what happens when parents play together with them? New research, ...

Researchers discover abundant source for neuronal cells

December 13, 2018
USC researchers seeking a way to study genetic activity associated with psychiatric disorders have discovered an abundant source of human cells—the nose.

In the developing brain, scientists find roots of neuropsychiatric diseases

December 13, 2018
The most comprehensive genomic analysis of the human brain ever undertaken has revealed new insights into the changes it undergoes through development, how it varies among individuals, and the roots of neuropsychiatric illnesses ...

Researchers find the cause of and cure for brain injury associated with gut condition

December 13, 2018
Using a mouse model of necrotizing enterocolitis (NEC)—a potentially fatal condition that causes a premature infant's gut to suddenly die—researchers at Johns Hopkins say they have uncovered the molecular causes of the ...

How the brain tells you to scratch that itch

December 13, 2018
It's a maddening cycle that has affected us all: it starts with an itch that triggers scratching, but scratching only makes the itchiness worse. Now, researchers have revealed the brain mechanism driving this uncontrollable ...

Study confirms role of brain's support cells in Huntington's, points to new therapies

December 13, 2018
New research gives scientists a clearer picture of what is happening in the brains of people with Huntington's disease and lays out a potential path for treatment. The study, which appears today in the journal Cell Stem Cell, ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.