Distinguishing different subtypes of sepsis by machine learning sets the stage for individualized treatment, researchers say

Four clinical sepsis phenotypes were identified that correlated with host-response patterns and clinical outcomes, researchers reported here. The four novel sepsis phenotypes — alpha (α), beta (β), gamma (γ), and delta (δ) — with different demographics, laboratory values, and patterns of organ dysfunction were derived, validated, and shown to correlate with biomarkers and mortality, according

Read More


AI can predict patient response to popular Crohn’s treatment

A predictive machine learning model was able to identify how effectively patients with Crohn’s disease would respond to long-term usage of ustekinumab, according to a new study in JAMA Network Open. Researchers from the University of Michigan trained the model using demographic and laboratory data obtained in previous clinical trials. The data described 401 patients with active Crohn’s

Read More


Scientists developed a light-activated bio-glue that can seal a heart wound in seconds

A new ‘biological glue’ developed by Chinese researchers could one day stop hearts and arteries from uncontrollable bleeding. Placed on an open wound and activated through UV light, this life-saving sealant rapidly morphs into a non-toxic hydrogel, capable of withstanding both slippery surfaces and the pulsing of heart tissue. The adhesive sealant hasn’t been tested

Read More


Liquid biopsy could identify cancer patients at risk of metastatic disease, offering an opportunity to tailor treatment

Researchers at The Royal Marsden say ctDNA, a form of liquid biopsy, may be an accurate technique to monitor treatment response in patients with locally advanced rectal cancer, allowing treatment to be adapted or changed earlier to try to prevent the development of metastatic disease.  Results from the study, led by researchers at The Royal

Read More