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
- Owkin Raises $25M to Enhance Medical Research Machine Learning and Collaborationon May 29, 2020 at 8:42 am
Owkin is fueling collaborative medical research using machine learning while being compliant with privacy laws. Thomas Clozel discusses the unique benefits of Owkin.
- How AI and machine learning are helping to fight COVID-19on May 28, 2020 at 7:55 am
This article is brought to you thanks to the collaboration of The European Sting with the World Economic Forum. Author: Emma Charlton, Senior Writer, Formative Content Organizations have been ...
- Testing System Leverages Machine Learning to Predict Sepsis Outcomeson May 27, 2020 at 10:03 am
A new testing approach uses machine learning to accurately identify which patients with sepsis will recover quickly, recover later, or die from the condition.
- Researchers use machine learning to predict heart damage in COVID-19 patientson May 27, 2020 at 9:32 am
Yearlong project will collect heart data from COVID-19 patients to create a model that predicts risk of adverse cardiac events such as heart attacks or heart failure ...
- Insitro Adds $143M to Fuel Machine Learning-Driven Drug Developmenton May 26, 2020 at 9:07 pm
A stem cell biologist, a gene editing expert, and a data engineer walk into a room...and that’s just a few of the people Daphne Koller has recruited in ...
- Machine Learning Helps Detect Heart Damage in COVID-19 Patientson May 26, 2020 at 10:35 am
Researchers are using a machine learning algorithm to identify COVID-19 patients at high risk of developing heart damage.
- Machine learning: Rapid diagnosis of patients with COVID-19 using an AI modelon May 19, 2020 at 5:00 pm
images and clinical history can quickly and accurately identify patients with COVID-19, according to a paper published in Nature Medicine. This system achieved an AUC (a metric of machine-learning ...
- Machine learning: Model identifies three biomarkers associated with COVID-19 mortalityon May 14, 2020 at 5:00 pm
Machine learning tools selected three biomarkers — lactic dehydrogenase ... in advance of their outcomes with more than 90% accuracy. Fast, accurate and early clinical assessment of patients’ COVID-19 ...
- Keeping It Real: Challenges And Benefits Of Integrating AI And Machine Learning Into Pharma R&Don May 7, 2020 at 5:00 pm
Clinical trial research Machine learning also has many potential applications for improving clinical trials. When applied to data sets, such as social media data, genetic information or electronic ...
- Exactech and KenSci Publish Research on the Impact of Artificial Intelligence to Predict Clinical Outcomes after Shoulder Arthroplastyon May 7, 2020 at 9:13 am
We are excited to publish this research and its clinical findings that demonstrate the utility of machine learning methods to anticipate patients’ results after shoulder arthroplasty." ...
via Google News and Bing News