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 today 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, machine learning capable of modelling the human brain 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 brain lesion 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).
Learn more: Improving clinical trials with machine learning
The Latest on: Machine learning clinical trials
H1 Announces Continued Growth and Expansion of Healthcare Machine Learning Analytics Platforms
on July 11, 2018 at 1:28 am
“Our long-term mission is to develop and launch new healthcare technology platforms that utilize machine learning and artificial ... letting you dive deep into the worlds of basic research, drug devel... […]
Machine learning predicts 1-year mortality using EHR data
on July 10, 2018 at 4:36 am
University of Minnesota researchers have developed a machine learning algorithm using electronic health ... sees the model as a potential clinical decision support tool for improving end-of-life plann... […]
NIH to host workshop on using artificial intelligence and machine learning to advance biomedical research
on July 2, 2018 at 1:12 pm
Harnessing Artificial Intelligence and Machine Learning to Advance Biomedical Research. The workshop will feature leading experts from Amazon and IBM, and scientists from the NIH Clinical Center, Mass... […]
Disruptive Innovations in Clinical Trials Event (DPharm) Announces Dates and Keynotes for 2018
on July 1, 2018 at 5:01 am
DPharm 2018 is divided into the following sections: keynotes, strategic level talks, pharma innovation reporting, new and advanced technologies, patient data access and ownership, digital biomarkers, ... […]
Researchers use machine learning algorithm to detect low blood pressure during surgery
on June 28, 2018 at 2:12 pm
The potential applications of machine learning in healthcare are limitless ... the real-time value of such algorithms in a broader set of clinical conditions and patients, our research opens the door ... […]
Esperite : NV (ESP) LAUNCHS NEW AGAATA Dx, DIAGNOSTIC SYSTEM WITH MACHINE LEARNING CAPABILITIES FOR GENETIC CLINICAL LABORATORIES.
on June 6, 2018 at 1:27 pm
Machine learning is a subset of artificial intelligence ... panel of genetic tests after a simple training session on the method in our research centre in Geneva. With AGAATA clinical laboratories can ... […]
GV invests in medical machine learning startup Owkin
on May 23, 2018 at 10:55 am
Owkin, a medical research machine learning startup ... “Owkin has assembled a talented team of experts in applied machine learning with clinical data experience,” noted GV general partner Adam Ghobara... […]
Reverie Labs uses new machine learning algorithms to fix drug development bottlenecks
on March 16, 2018 at 6:16 am
... can take years of research and cost millions of dollars before they are even ready for clinical trials. Several biotech startups are using machine learning to revolutionize the process and get dru... […]
American Heart Association and Duke partner to accelerate machine learning and AI
on March 14, 2018 at 3:22 am
The American Heart Association and the Duke Clinical Research Institute on Monday unveiled a partnership to try out machine-learning techniques to find new ways to analyze data and drive scientific di... […]
Improving clinical trials with machine learning
on November 14, 2017 at 4:00 pm
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 sta... […]
via Google News and Bing News