Researchers use AI to predict Alzheimer’s disease 7 years before clinical diagnosis

85C853C6-D92F-4315-80BB-E77B8442BB44

IBM and Pfizer developed an AI that looks at speech patterns over time for markers of the crippling degenerative disease.

Alzheimer’s is a crippling degenerative disease, but the answer to early diagnosis might lie in speech.

I was afraid my grandmother wouldn’t remember who I was the last time I saw her in person. She looked small and frail in the wheelchair but I could still see the sparkle in her eyes. Our relationship was complicated, but when she said she remembered me, none of it mattered any more.

I sat by her wheelchair and tried to cram in a decade of memories and happenings. Every few moments, it was like she’d reset, and would ask what I’d been up to all these years. We’d go through everything again. We only had a few precious hours before she didn’t remember who I was anymore, no matter how many stories I told her.

Alzheimer’s is a degenerative brain disease that over 5 million Americans live with, and that number is only expected to grow, according to the Alzheimer’s Association. But IBM Research and Pfizer have developed a new AI model that uses quick speech tests to help predict the onset of the disease in healthy people, the companies said Thursday. The AI’s accuracy is about 70%, potentially giving people up to seven years’ notice before symptoms of cognitive decline.

The disease can seem like it sneaks in, beginning with symptoms that may be misinterpreted as typical age-related changes. These early warning flags are important to recognize, as they’re a sign of coming cognitive decline. The sooner clinicians can detect Alzheimer’s disease, the more that can be done to help a patient, even though there’s no cure to date.

Continue reading… “Researchers use AI to predict Alzheimer’s disease 7 years before clinical diagnosis”

0

Rapid disease pathogen identification a step closer following successful GeneCapture demonstration

FE331E34-70B3-4C72-A79B-9A7B4B0BA7DF

GeneCapture’s unique disposable cartridge design enables rapid multi-pathogen identification directly from samples.

 Soon it could only take an hour to find out what pathogen is making you ill, following the successful demonstration of the world’s first multi-pathogen identification using non-amplified RNA detection by GeneCapture, a company cofounded by researchers at The University of Alabama in Huntsville (UAH), a part of the University of Alabama System.

GeneCapture has licensed a molecular binding technology from UAH and the company’s CAPTURE PLATFORM is on track for commercialization within two years. The GeneCapture team has briefed the Food and Drug Administration (FDA) on its approach and has begun to prepare for the clinical testing required for FDA clearance. It is in discussions with industry leaders for various applications in health care rapid infection detection.

“We made history today—this is the first time an automated rapid pathogen identification has been reported directly from the RNA of the sample, with no modification or amplification of its genetic source, in about an hour,” says GeneCapture CEO and local entrepreneur Peggy Sammon. “We envision a future where finding out why you are sick can be solved almost anywhere, in an hour, and without being chained to a lab.”

Continue reading… “Rapid disease pathogen identification a step closer following successful GeneCapture demonstration”

0

Harnessing deep neural networks to predict future self-harm based on clinical notes

DE76288D-7B52-4377-A38B-77D55E2D4482

According to the American Foundation for Suicide Prevention, suicide is the 10th leading cause of death in the U.S., with over 1.4 million suicide attempts recorded in 2018. Although effective treatments are available for those at risk, clinicians do not have a reliable way of predicting which patients are likely to make a suicide attempt.

Researchers at the Medical University of South Carolina and University of South Florida report in JMIR Medical Informatics that they have taken important steps toward addressing the problem by creating an artificial intelligence algorithm that can automatically identify patients at high risk of intentional self-harm, based on the information in the clinical notes in the electronic health record.

The study was led by Jihad Obeid, M.D., co-director of the MUSC Biomedical Informatics Center, and Brian Bunnell, Ph.D., formerly at MUSC and currently an assistant professor in the Department of Psychiatry and Behavioral Neurosciences at the University of South Florida.

Continue reading… “Harnessing deep neural networks to predict future self-harm based on clinical notes”

0

Determining if tumor gene testing can select efficacious precision cancer treatment

F1431A17-558C-48C3-AC90-B819615E3349

NCI-MATCH is a precision medicine cancer trial that seeks to determine whether matching certain drugs or drug combinations in adults whose tumors have specific gene abnormalities will effectively treat their cancer, regardless of their cancer type. Such discoveries could be eligible to move on to larger, more definitive trials. The trial is led by the ECOG-ACRIN Cancer Research Group. Credit: ECOG-ACRIN Cancer Research Group

Five years ago, the ECOG-ACRIN Cancer Research Group (ECOG-ACRIN) and National Cancer Institute (NCI), part of the National Institutes of Health, jointly launched a very different kind of cancer study. NCI-Molecular Analysis for Therapy Choice (NCI-MATCH or EAY131), the largest precision medicine cancer trial to date, sought to match genetic abnormalities driving patients’ tumors with approved or experimental drugs targeting those defects. The type of cancer did not matter. Nearly 6000 cancer patients quickly joined the trial and contributed their tumor specimens for genomic testing. Now, the Journal of Clinical Oncology is publishing an in-depth look into the tumor gene make-up of these patients. It is the largest data set ever compiled on patients with tumors that have progressed on one or more standard treatments, or with rare cancers for which there is no standard treatment. The information contains significant discoveries that tell physicians and patients more about how to use genomic testing to select the best treatments.

Continue reading… “Determining if tumor gene testing can select efficacious precision cancer treatment”

0

Robot that can perform colonoscopies aims to make it less unpleasant

 

 C98B583C-6D55-4909-8B7E-135218196C73

 A robot that can perform colonoscopies may make the procedure simpler and less unpleasant.

Pietro Valdastri at the University of Leeds in the UK and his colleagues have developed a robotic arm that uses a machine learning algorithm to move a flexible probe along the colon.

The probe is a magnetic endoscope, a tube with a camera lens at the tip, that the robot controls via a magnet external to the body.

The system can either work autonomously or be controlled by a human operator using a joystick, which pushes the endoscope tip further along the colon. Valdastri likens the movement to the intuitive motion of playing a video game. The system also keeps track of the location and orientation of the endoscope inside the colon.

Continue reading… “Robot that can perform colonoscopies aims to make it less unpleasant”

0

Wearable sensors can be printed directly onto skin at room temperature

 BD79760C-6C7D-4374-AEFD-C59AAAB2348A

An example of the new wearable sensor developed at Penn State University

Flexible electronics have opened up some interesting possibilities when it comes to wearable sensors that can be applied to the skin, taking the form of tattoo-like films and sleeves that monitor various aspects of human health. Scientists at Penn State University have now developed one they say can be safely printed directly onto the skin, where it can track things like body temperature and blood oxygen levels, before being washed off once the job is done.

The new printable sensors build on earlier work by the same researchers, in which they developed flexible circuit boards for use in wearable sensors. But a key part of this process involved bonding some of the metallic components together at the kinds of temperatures not well tolerated by the human body, at around 572 °F (300 °C).

Continue reading… “Wearable sensors can be printed directly onto skin at room temperature”

0

Scientists claim to invent hydrogel that heals nerve damage

B1D39E93-FF59-4E3B-B8BE-F9803A382F3A

THEY SAY THE GEL CAN PROPAGATE NEURAL SIGNALS WHERE NERVES ARE INJURED.

A team of doctors and engineers have developed a new hydrogel that they say might be able to repair nerve damage more quickly and reliably than any other methods.

The hydrogel is essentially a porous and water-saturated material that can stretch, bend, and — most importantly — propagate neural signals. In animal trials, the team of Nanjing University researchers found that the hydrogel restored lost bodily function and helped the animals heal faster, according to research published Wednesday in the journal ACS NANO. Now, they’re hoping the gel will work in human medicine as well.

Continue reading… “Scientists claim to invent hydrogel that heals nerve damage”

0

AI tool could predict how drugs will react in the body

 

104172E3-AD63-4107-A9F0-1C67C731F903

“The safety of a drug does not depend only on the drug itself but also on the metabolites
that can be formed when the drug is processed in the body,” says Eleni Litsa

A new deep learning-based tool called Metabolic Translator may soon give researchers a better handle on how drugs in development will perform in the human body.

When you take a medication, you want to know precisely what it does. Pharmaceutical companies go through extensive testing to ensure that you do.

Metabolic Translator, a computational tool that predicts metabolites, the products of interactions between small molecules like drugs and enzymes could help improve the process.

The new tool takes advantage of deep-learning methods and the availability of massive reaction datasets to give developers a broad picture of what a drug will do. The method is unconstrained by rules that companies use to determine metabolic reactions, opening a path to new discoveries.

Continue reading… “AI tool could predict how drugs will react in the body”

0

UK ambulance services are testing a rescue jet suit

6D099C66-4E63-462C-B2C7-76154C7DF89B

Gravity Industries’ suit could quickly get a medic to a remote casualty site.

The “Iron Man” jet suit we first saw back in 2017 might be less crazy than we first thought. Inventor Richard Browning and his company Gravity Industries have demonstrated that it may be a viable option to quickly get medical help to victims in remote areas. Working with the UK’s Great North Air Ambulance Service (GNAAS), Browning flew to a simulated casualty on a remote mountainous site in just 90 seconds, a fraction of the time it would take to walk there.

The sooner a paramedic can get to a victim, the sooner they can stabilize them and call for a helicopter or other support. “We think this technology could enable our team to reach some patients much quicker than ever before,” said GNAAS director of operations Andy Mawson. “In many cases this would ease the patient’s suffering. In some cases, it would save their lives.”

Continue reading… “UK ambulance services are testing a rescue jet suit”

0

Neural network trained to control anesthetic doses, keep patients under during surgery

To define how the world should look, neural networks are making up their own rules

 Researchers demonstrate how deep learning could eventually replace traditional anesthetic practices.

Academics from the Massachusetts Institute of Technology (MIT) and Massachusetts General Hospital have demonstrated how neural networks can be trained to administer anesthetic during surgery.

Over the past decade, machine learning (ML), artificial intelligence (AI), and deep learning algorithms have been developed and applied to a range of sectors and applications, including in the medical field.

Continue reading… “Neural network trained to control anesthetic doses, keep patients under during surgery”

0

Breast milk could stop virus spreading, researchers claim

 274B52CD-A047-4AD7-80A1-87A0DDC9C666

Whey proteins in cow and goat milk also could inhibit the virus but is less effective than human breast milk.

 

Human breast milk could help to prevent or treat COVID-19, according to a new study by Chinese scientists, lending support to World Health Organisation guidelines that mothers should breastfeed their newborn babies even if they are infected with the coronavirus.

Continue reading… “Breast milk could stop virus spreading, researchers claim”

0

Experimental cancer treatment destroys cancer cells without using any drugs

AB0A30DC-8060-4F4D-BFBC-A261FCBBE416

One of the latest methods pioneered by scientists to treat cancer uses a Trojan horse sneak attack to prompt cancer cells to self-destruct – all without using any drugs.

Key to the technique is the use of a nanoparticle coated in a specific amino acid called L-phenylalanine, one of several such acids that cancer cells rely on to grow. L-phenylalanine isn’t made by the body, but absorbed from meat and dairy products.

In tests on mice, the nanoparticle – called Nano-pPAAM or Nanoscopic phenylalanine Porous Amino Acid Mimic – killed cancer cells specifically and effectively, posing as a friendly amino acid before causing the cells to destroy themselves.

The self-destruction mode is triggered as the nanoparticle puts production of certain chemicals known as reactive oxygen species (ROS) into overdrive. It’s enough to bring down the cancer cells while leaving neighbouring, healthy cells intact.

Continue reading… “Experimental cancer treatment destroys cancer cells without using any drugs”

0