Machine learning algorithm to predict mortality in heart failure patients

Researchers from the University of California San Diego developed a machine-learning model by training a boosted decision tree algorithm on de-identified electronic health records data of 5,822 hospitalized or ambulatory patients with heart failure from the University of California San Diego.

This machine learning model is based on eight readily available variables. These include, diastolic blood pressure, creatinine, blood urea nitrogen, haemoglobin, white blood cell count, platelets, albumin, and red blood cell distribution width. This model was able to predict life expectancy in 88% of the patients.

This study is published in the European Journal of Heart Failure.

The tool was additionally tested using data from the University of California, San Francisco, and a database derived from 11 European medical centers.

With the advance of machine learning and artificial intelligence tools, large amounts of health data thanks to electronic health records, and computing power, we able to work on creating more and more accurate risk prediction tools. These tools will be commonplace in clinical practice to help with data-based decisions.

Bacteriophage treatment for alcohol related liver disease

Researchers from King’s College London and the University of California San Diego School of Medicine conducted an animal study in mice and shown promise of bacteriophage therapy in treating alcohol-related liver disease.

This research is published in journal Nature.

The team discovered that patients with severe alcoholic hepatitis had high numbers of a destructive gut bacterium Enterococcus faecalis, which produced a toxin called cytolysin. This toxin is shown to injure liver cells. Enterococcus faecalis is normally found in low numbers in the healthy human gut.

To investigate the potential for phage therapy, the researchers isolated four different phages that specifically target cytolysin-producing Enterococcus faecalis. When they treated the mice with these, the bacteria were eradicated, and alcohol-induced liver disease was abolished. Control phages that target other bacteria or non-cytolytic E. faecalis had no effect.

With the rise of multidrug-resistant infections, people are looking at alternatives to antibiotics. Bacteriophages are viruses that kill bacteria. These bacteriophages are naturally occurring and offer a promising alternative to antibiotics. However, much research is needed to establish their safety and efficacy in clinical practice. The current study show promise of using phage therapy to alter the gut microbiome in cases with alcoholic liver disease.

Calculator to predict five year risk for chronic kidney disease

A new risk calculator tool to predict the risk of chronic kidney disease is developed by Chronic Kidney Disease Prognosis Consortium, a large global collaboration led by researchers at the Johns Hopkins Bloomberg School of Public Health. It utilizes a mix of variables to predict accurately whether someone is likely to develop chronic kidney disease within five years.

The risk calculator published in the Journal of the American Medical Association (JAMA), is based on an analysis of clinical data from more than five million people around the world. The calculator is based on risk prediction model that utilizes age, sex, race/ethnicity, eGFR, history of cardiovascular disease, ever smoker, hypertension, body mass index, and albuminuria concentration. For participants with diabetes, the models also included diabetes medications, hemoglobin A1c, and the interaction between those two.

This calculator is available online at www.ckdpcrisk.corg

Risk prediction tools can help identify high-risk patients that can be followed with interventions that can slow or stop disease progression. In the case of kidney disease, progression can be delayed or stopped with treatments that address kidney-harming disorders such as hypertension and diabetes, and by limiting the use of kidney-stressing substances such as certain antibiotics, NSAID painkillers, and imaging contrast agents.

Smartphone app shown to improve medication intake compliance in heart patients

According to a research study presented at the 45th Argentine Congress of Cardiology heart patients using a smartphone app reminder are more likely to take their medication than those who receive written instructions,

This study tested the impact of a smartphone application on medication compliance. A total of 90 heart attack patients admitted to hospital were randomly allocated to the app or detailed written information (standard care). Adherence to medical treatment was measured at 90 days using the Morisky Medical Adherence Scale (MMAS-8). For those assigned to the smartphone group, the prescribed medication schedule was uploaded to the digital application, and an alarm would ring each time a pill should be taken. After taking the pills, patients confirmed it in the application. Doctors could check daily adherence using a professional digital platform linked to the patient’s smartphone.

The average age of patients in the study was 63 years and 75% were men. At 90 days, significantly more patients in the digital application group were correctly taking their pills (65%) compared to those who received standard care (21%; p<0.001). A secondary objective of the study was to examine how many patients in each group were hospitalized for another heart attack or had an unplanned visit to the doctor or emergency department. No differences between groups were found.

Overall this study shown increasing use of digital tools to monitor the treatment delivery. However this study does not prove that taking medications on time and digital monitoring would improve patient outcomes. Further research is needed in that respect.

New findings of cortical activity during delta wave sleep sheds further light into memory formation

Scientists at the Center for Interdisciplinary Research in Biology have shown that delta waves emitted while we sleep are not generalized periods of silence during which the cortex rests, as has been described for decades in the scientific literature. Instead, they isolate assemblies of neurons that play an essential role in long-term memory formation. These results were published in journal Science.

While we sleep, the hippocampus reactivates itself spontaneously by generating activity similar to that while we are awake. It sends information to the cortex, which reacts in turn. This exchange is often followed by a period of silence called a ‘delta wave’ then by a rhythmic activity called a ‘sleep spindle’. This is when the cortical circuits reorganize to form stable memories.

However, the role of delta waves in the formation of new memories is still a puzzle: why does a period of silence interrupt the sequence of information exchanges between the hippocampus and the cortex, and the functional reorganization of the cortex?

The authors here looked more closely at what happens during delta waves themselves. They discovered, surprisingly, that the cortex is not entirely silent but that a few neurons remain active and form assemblies, i.e. small, coactive sets that code information. This unexpected observation suggests that the small number of neurons that activate when all the others stay quiet can carry out important calculations while protected from possible disturbances.

And the discoveries from this work go even further! Spontaneous reactivations of the hippocampus determine which cortical neurons remain active during the delta waves and reveal transmission of information between the two cerebral structures. In addition, the assemblies activated during the delta waves are formed of neurons that have participated in learning a spatial memory task during the day. Together these elements suggest that these processes are involved in memory consolidation.

To demonstrate it, in rats the scientists caused artificial delta waves to isolate either neurons associated with reactivations in the hippocampus or random neurons. Result: when the right neurons were isolated, the rats managed to stabilize their memories and succeed at the spatial test the next day.

Anti aging drugs focus – Rapamycin

New opinion article by Dr. Mikhail V. Blagosklonny about anti aging drug published in the journal Aging.

Drug in focus is rapamycin, which functions by inhibiting mTOR pathway. Similar drugs include everolimus. Normally when over-activated by nutrients and insulin, mTOR acts via S6K to inhibit insulin signaling, thereby causing insulin resistance.

The evidence in preclinical and animal suggests that rapamycin is a universal anti-aging drug that is, it extends lifespan in all tested models from yeast to mammals, suppresses cell senescence and delays the onset of age-related diseases, which are manifestations of aging

Author lists advantages of rapamycin which include immunomodulator and anti inflammatory effects in addition to anti aging effects. Also it is know that rapamycin reduces viral replication. Some of the notable side effects include stomatitis and mucositis, non-infectious interstitial pneumonitis and nuetrophil inhibition which can lead to severe bacterial infections.

In addition to rapamycin/everolimus, other conventional drugs with anti-aging effect include metformin, aspirin, ACE inhibitors, angiotensin receptor blockers and PDE5 inhibitors such as Sildenafil and Tadalafil, can prevent or treat more than one age-related disease. In addition to above drugs calorie restriction and intermittent fasting has been shown to extend both the lifespan and healthspan in diverse species.

Genetic-based epilepsy risk scores to promote precision medicine

Researchers led by Cleveland Clinic have developed new genetic-based epilepsy risk scores which could help provide more personalized epilepsy diagnosis and treatment. This research is published in the journal Brain.

Researchers combined all known common genetic variants identified from several large genome wide association study cohorts, which included more than 12,000 people with epilepsy and 24,000 healthy controls, to calculate the polygenic risk scores in more than 8,000 people with epilepsy and 622,000 population controls.

By combining the effect sizes of thousands of common genetic variants, these scores can be used to determine an individual’s risk for epilepsy. Researchers showed that these scores can accurately distinguish on a cohort level between healthy patients and those with epilepsy, as well as between patients with generalized and focal epilepsies.

Machine learning to predict the clinical utility of biomedical research

A machine learning model to predict which scientific advances are likely to eventually translate to the clinic has been developed by Ian Hutchins and colleagues in the Office of Portfolio Analysis (OPA), a team led by George Santangelo at the National Institutes of Health (NIH).

This work published in the journal PLOS Biology aims to decrease the interval between scientific discovery and clinical application. The model determines the likelihood that a research article will be cited by a future clinical trial or guideline, an early indicator of translational progress.

Researchers have quantified these predictions as a novel metric called “Approximate Potential to Translate” (APT). Approximate Potential to Translate values can be used by researchers and decision-makers to focus attention on areas of science that have strong signatures of translational potential. Although numbers alone should never be a substitute for evaluation by human experts, the Approximate Potential to Translate metric has the potential to accelerate biomedical progress as one component of data-driven decision-making.

The model that computes Approximate Potential to Translate values makes predictions based upon the content of research articles and citations. A long-standing barrier to research and development of metrics like Approximate Potential to Translate is that such citation data has remained hidden behind proprietary, restrictive, and often costly licensing agreements. To disrupt this impediment to the scientific community, to increase transparency, and to facilitate reproducibility, OPA has aggregated citation data from publicly available resources to create an open citation collection (NIH-OCC).

The open citation collection comprises over 420 million citation links at present and will be updated monthly. For publications since 2010, the open citation collection is already more comprehensive than leading proprietary sources of citation data. Citation data from the open citation collection are used to calculate both Approximate Potential to Translate values and Relative Citation Ratios (RCRs). The latter, a measure of scientific influence at the article level, normalized for the field of study and time since publication.

Approximate Potential to Translate values and the open citation collection are publicly available as components of the iCite webtool. This tool will continue as the primary source of Relative Citation Ratios data.

New microfluidic system using artificial membrane keep brain tissue viable for a longer duration

Researchers at the RIKEN Center for Biosystems Dynamics Research in Japan have developed a new system for keeping tissue viable for long-term study once transferred from an animal to a culture medium. The new system uses a microfluidic device made of polydimethylsiloxane (PDMS) with a porous membrane that can keep tissue from both drying out and from drowning in fluid. This study was published in the journal Analytical Sciences.

The team tested the device using tissue from the mouse suprachiasmatic nucleus, a complex part of the brain that governs circadian rhythms. By measuring the level of bioluminescence coming from the brain tissue, they were able to see that tissue kept alive by their system stayed active and functional for over 25 days with nice circadian activity. In contrast, neural activity in tissue kept in a conventional culture decreased by 6% after only 10 hours.

This new method will be useful in observing development and testing how tissues respond to drugs. Experiments with tissues are much more complex and provide important information such as cell to cell interaction, unlike seeded cells where such observation is difficult.

Researchers develop self sterilizing bacterial air filter using graphene

Rice University researchers have developed self-sterilizing bacterial air filters using graphene. Workings of this novel air filter are published in the American Chemical Society journal ACS Nano.

This devise captures bacteria, fungi, spores, prions, endotoxins and other biological contaminants carried by droplets, aerosols and particulate matter. The filter then prevents the microbes and other contaminants from proliferating by periodically heating up to 350 degrees Celsius (662 degrees Fahrenheit), enough to obliterate pathogens and their toxic byproducts.

The filter utilizes laser-induced graphene. ¬†This is a conductive foam of pure, atomically thin carbon sheets synthesized through heating the surface of a common polyimide sheet with an industrial laser cutter. The process discovered by Tour’s lab in 2014 has led to a range of applications for electronics, triboelectric nanogenerators, electrocatalysis, water filtration and even art.

The lab tested LIG filters with a commercial vacuum filtration system, pulling air through at a rate of 10 liters per minute for 90 hours, and found that Joule heating successfully sanitized the filters of all pathogens and byproducts. Incubating used filters for an additional 130 hours revealed no subsequent bacterial growth on the heated units, unlike control LIG filters that had not been heated.

This filter provides use case scenarios especially in hospitals, schools, and passenger aircraft. Although similar air filtration systems are available currently, self sterilization of filter holds promise as it can reduce number of filters used and their replacement frequency there by providing a cost reduction. However further research is required before this product is fully implemented.

MNO