Breaking News
October 20, 2018 - New approach to understanding cancers will accelerate development of better treatments
October 20, 2018 - LJI and UC San Diego awarded $ 4.5 million as part of NCI’s Cancer Moonshot initiative
October 20, 2018 - School-based HPV vaccination did not increase risky sexual behaviors among adolescent girls
October 20, 2018 - Eye discovery to pave way for more successful corneal transplants
October 20, 2018 - New analysis examines the importance of location in the opioid crisis
October 20, 2018 - Green filters increase reading speed for children with dyslexia
October 19, 2018 - Bariatric Sx Cuts Macrovascular Complications in Obesity, T2DM
October 19, 2018 - Better assessments for early age-related macular degeneration
October 19, 2018 - Visible and valued: Stanford Medicine’s first-ever LGBTQ+ Forum | News Center
October 19, 2018 - Understanding of metal-free enzymes used by bacteria could lead to new effective antibiotics
October 19, 2018 - Beckman Coulter Life Sciences announces new research-focused website
October 19, 2018 - Study finds link between refined soluble fibers, gut microbiota and liver cancer
October 19, 2018 - Social media reduces risk of depression among seniors with pain
October 19, 2018 - Newly developed synthetic DNA molecule may one day be used as ‘vaccine’ for prostate cancer
October 19, 2018 - Preoperative weight loss may not provide health benefits after surgery
October 19, 2018 - U.S. Birth Rates Continue to Drop as Age of New Moms Rises
October 19, 2018 - New technology can keep an eye on babies’ movements in the womb
October 19, 2018 - Juul e-cigarettes pose addiction risk for young users | News Center
October 19, 2018 - Gene sequencing reveals crucial molecular aspects of Trypanosoma brucei
October 19, 2018 - New DNA vaccine strategy protects mice against lethal challenge by multiple H3N2 viruses
October 19, 2018 - Study shows close link between cytokine interleukin-1ß and obesity-promoted colon cancer
October 19, 2018 - Muscle mass plays a critical role in health, shows research
October 19, 2018 - Study finds undiagnosed prediabetes in many infertile men
October 19, 2018 - The Current issue of “The view from here” is concerned with Nanotherapeutic strategies
October 19, 2018 - Delay in replacing the Pap smear with HPV screening is costing lives
October 19, 2018 - Physicians battle pediatric diseases of ear, nose, throat in Zimbabwe | News Center
October 19, 2018 - Researchers investigate why some cancers affect only young women
October 19, 2018 - Drugmakers funnel millions to lawmakers; a few dozen get $100,000-plus
October 19, 2018 - Unselfish people tend to have more children and receive higher salaries
October 19, 2018 - New findings reveal potential cellular players in tumor microenvironment
October 19, 2018 - Human brain cell transplant offers insights into neurological conditions
October 19, 2018 - Parental education associated with increased family health care spending
October 19, 2018 - New statistical method estimates long- and short-term risk of recurrence of breast cancer in US women
October 19, 2018 - Father’s exposure to nicotine may cause cognitive deficits in descendants
October 19, 2018 - Could we prevent Alzheimer’s disease by treating herpes?
October 19, 2018 - Nurse-led care can be more successful in managing gout
October 19, 2018 - Trump administration, pharma exchange verbal volleys on drug-price transparency
October 19, 2018 - Duke researchers find way to detect blood doping in athletes
October 19, 2018 - Many primary care doctors are still prescribing sedative drugs for older adults
October 19, 2018 - Finger length can predict sexuality in women say researchers
October 19, 2018 - Study finds differences in side-effects experienced by male and female OG cancer patients
October 19, 2018 - Dysfunction of single gene leads to miscarriages
October 19, 2018 - Few Seniors Who Self-Harm Referred for Mental Health Care
October 19, 2018 - Don’t sweat the sweet stuff
October 19, 2018 - URMC researchers discover new approach to deliver therapeutics to the brain
October 19, 2018 - Speech Pathology Australia raises awareness about Developmental Language Disorder
October 19, 2018 - Middlemen suppliers can increase drug prices and hospital bills, say Johns Hopkins researchers
October 19, 2018 - Survey finds high prevalence of HTLV-1 infection among teens and adults in Gabon
October 19, 2018 - Bliss funds research to find whether parental touch can help alleviate pain in premature infants
October 19, 2018 - Human neurons employ highly compartmentalized signaling, study shows
October 19, 2018 - Ultromics expands multiple clinical trials for coronary heart disease to the U.S.
October 19, 2018 - $11 million NIH grant for Clemson University helps launch new center for musculoskeletal research
October 19, 2018 - A new approach identified to control Zika virus, dengue fever
October 19, 2018 - Head Blows Without Concussion May Not Damage Brain, Study Claims
October 19, 2018 - US opioid use not declined, despite focus on abuse and awareness of risk
October 19, 2018 - Next-generation RNA sequencing technology sheds new light on human mitochondrial diseases
October 19, 2018 - UT Southwestern biochemist receives 2019 Breakthrough Prize in Life Sciences for innate immunity discovery
October 19, 2018 - The immune system also plays a key role in day-to-day function of healthy organs
October 19, 2018 - New tool may reveal how the brain structure impacts brain activity, human behavior
October 19, 2018 - Trump Administration announces ‘Winning on Reducing Food Waste’ initiative
October 19, 2018 - For-profit nursing home residents more likely to experience health issues caused by substandard care
October 19, 2018 - Incidence of stroke has risen steadily among marijuana users, show studies
October 19, 2018 - Conceptual framework proposed to examine role of exercise in multiple sclerosis
October 19, 2018 - Near infrared spectroscopy technique for accurate evaluation of chondral injuries
October 19, 2018 - Scientists receive $5.1 million grant to develop stem cell-based therapy for blinding retinal conditions
October 19, 2018 - Shorter physician encounters associated with antibiotic prescribing
October 19, 2018 - In the Spotlight: Enjoying research and exploring opportunities
October 19, 2018 - Physical activity lowers cardiovascular mortality risk in frail older adults
October 19, 2018 - New imaging tool helps visualize how sound-induced vibrations travel through the ear
October 19, 2018 - Key insights into the application, production of bioactive materials
October 19, 2018 - New urea sorbent could speed up the development of wearable artificial kidney
October 19, 2018 - Intensive care patients’ muscles less able to use fats for energy
October 19, 2018 - FDA Advisory Committee Recommends Approval of Dsuvia for the Treatment of Moderate-to-Severe Acute Pain
October 19, 2018 - 48,XXXY syndrome – Genetics Home Reference
October 19, 2018 - Physical exercise improves the elimination of toxic proteins from muscles
October 19, 2018 - How a new system improved wait times for Stanford kidney transplant patients
October 19, 2018 - Nutrition has bigger positive impact on bone mass and strength than exercise
October 19, 2018 - Study finds lack of progress in media representation of nurses over last 20 years
October 19, 2018 - Many people have trouble understanding differences between OCD and OCPD
October 19, 2018 - New family planning app found to be as effective as modern methods

Improving clinical trials with machine learning

image_pdfDownload PDFimage_print

 “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. We used well-established methods of machine learning, teaching the algorithm on subsets of data and then testing its performance on other subsets it had not seen,” 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).

The study was funded by Wellcome and the National Institute for Health Research University College London Hospitals Biomedical Research Centre.

Tagged with:

About author

Related Articles