Computational Model Underlines Need for Personalised Approach to Sepsis
Sepsis occurs when the body’s normal immune response to injury and infection goes awry, causing systemic inflammation that kills up to half of sufferers. So far, researchers have struggled to find drugs that effectively combat sepsis, so patients are mainly treated with antibiotics to fight the underlying condition.
In a new study published in PLOS Computational Biology, Chase Cockrell and Gary An of the University of Chicago employed a computational model of the human immune system to explore the challenges of attacking the molecular processes underlying sepsis. The model, developed previously to investigate systemic inflammation, simulates how immune system cells and signaling molecules behave during sepsis, as well as the effects of disrupting these processes.
The model suggested successful treatment would require drugs targeting multiple immune system processes: disrupting a single signaling process would not be sufficient. This may explain why previous attempts that employed such a strategy have not been effective. The model also indicated that a “one-size-fits-all” multi-target approach would still be inadequate, demonstrating the need for treatment to adapt, perhaps using a machine-learning algorithm, to a patient’s individual response.
Cockrell believes that his findings may be “a reality check” for those working on sepsis treatments. “It will hopefully help focus research into those areas that will actually provide a path towards effective therapy, such as high-resolution diagnostics and sampling, and realizing that there is no ‘one-size-fits-all’ answer.”
Algorithm Speeds Up Medical Image Analysis 1000 TimesNews
Medical image registration is a common technique that involves overlaying two images, such as magnetic resonance imaging (MRI) scans, to compare and analyze anatomical differences in great detail. Researchers have described a machine-learning algorithm that can register brain scans and other 3-D images more than 1,000 times more quickly using novel learning techniques.
Mechanism Controlling Multiple Sclerosis Risk IdentifiedNews
Researchers at Karolinska Institutet have now discovered a new mechanism of a major risk gene for multiple sclerosis (MS) that triggers disease through so-called epigenetic regulation. They also found a protective genetic variant that reduces the risk for MS through the same mechanism.
Antarctic Worm and Machine Learning Help Identify Cerebral Palsy EarlierNews
A research team has released a study in the peer-reviewed journal BMC Bioinformatics showing that DNA methylation patterns in circulating blood cells can be used to help identify spastic cerebral palsy (CP) patients. The technique which makes use of machine learning, data science and even analysis of Antarctic worms, raises hopes for earlier targeted CP therapies.