Machine Learning News and Research

RSS

UCSF collaborates with Intel to deploy and validate deep learning analytics to improve healthcare

UC San Francisco's Center for Digital Health Innovation today announced a collaboration with Intel Corporation to deploy and validate a deep learning analytics platform designed to improve care by helping clinicians make better treatment decisions, predict patient outcomes, and respond more nimbly in acute situations.

19 Jan 2017

New computational tool can predict personal cancer driver genes to optimize treatment

Columbia University Medical Center researchers have created a computational tool that can rapidly predict which genes are implicated in an individual's cancer and recommend treatments.

22 Dec 2016

Generative AAE can be radically new way to discover drugs on demand

Scientists at the Pharmaceutical Artificial Intelligence group of Insilico Medicine, Inc, today announced the publication of a seminal paper demonstrating the application of generative adversarial autoencoders (AAEs) to generating new molecular fingerprints on demand.

22 Dec 2016

Johns Hopkins scientists create bioinformatics tool to evaluate cancer driver gene prediction methods

In their search for new ways to treat cancer, many scientists are using a high-tech process called genome sequencing to hunt for genetic mutations that encourage tumor cells to thrive.

17 Dec 2016

Leti researchers show memristive devices can emulate short- and long-term synaptic plasticity

Leti researchers have demonstrated that memristive devices are excellent candidates to emulate synaptic plasticity, the capability of synapses to enhance or diminish their connectivity between neurons, which is widely believed to be the cellular basis for learning and memory.

8 Dec 2016

Novel machine learning approach could help predict dementia risk in cognitively healthy older people

A machine learning method analyzing large amounts of health information has potential in assessing the risk of cognitively healthy older people for later dementia, according to research published in the Journal of Alzheimer’s Disease. The new risk assessment tool also presents the individual risk profile in a quickly interpretable visual form.

8 Dec 2016

Gut microbes may play important role in exacerbated post-dieting weight gain

Following a successful diet, many people are dismayed to find their weight rebounding - an all-too-common phenomenon termed "recurrent" or "yo-yo" obesity.

5 Dec 2016

Symptom trends may help predict recovery of patients suffering from post-concussion syndrome

Researchers at the Krembil Neuroscience Centre's Canadian Concussion Centre have identified symptom trends that may not only help predict how soon patients suffering from post-concussion syndrome (PCS) will recover, but also provide insight on how to treat those who experience persistent concussion symptoms.

30 Nov 2016

Philips unveils series of intelligent, comprehensive connected radiology solutions at RSNA 2016

Royal Philips today unveiled a series of intelligent and comprehensive connected radiology solutions at the 2016 Radiological Society of North America Annual Meeting, beginning November 27 through December 1 at McCormick Place in Chicago.

29 Nov 2016

Research shows how machine-learning models can interpret echocardiographic images and enable HCM diagnosis

Computer algorithms can automatically interpret echocardiographic images and distinguish between pathological hypertrophic cardiomyopathy and physiological changes in athletes' hearts, according to research from the Icahn School of Medicine at Mount Sinai, published online yesterday in the Journal of the American College of Cardiology.

24 Nov 2016

Crowdsourcing new prediction tool for better prognosis of metastatic castration-resistant prostate cancer

Knowing the likely course of cancer can influence treatment decisions. Now a new prediction model published today in Lancet Oncology offers a more accurate prognosis for a patient's metastatic castration-resistant prostate cancer.

16 Nov 2016

Experts' ability to predict suicidal thoughts and behaviors has not improved, review reveals

Experts' ability to predict if someone will attempt to take his or her own life is no better than chance and has not significantly improved over the last 50 years, according to a comprehensive review of suicide research published by the American Psychological Association.

15 Nov 2016

Fraunhofer researchers use new deep learning approach to facilitate tumor measurement

Physicians have long used visual judgment of medical images to determine the course of cancer treatment.

14 Nov 2016

NCATS funds collaboration initiative aimed at repurposing antimalarial to combat Ebola virus

The National Center for Advancing Translational Sciences recently awarded $596,533.00 to Collaborations Pharmaceuticals, Inc. to initiate a partnership with Texas Biomedical Research Institute aimed at repurposing an antimalarial for use against the Ebola virus.

10 Nov 2016

Researchers apply deep learning to modernize cancer surveillance

Despite steady progress in detection and treatment in recent decades, cancer remains the second leading cause of death in the United States, cutting short the lives of approximately 500,000 people each year.

10 Nov 2016

Machine learning accurately identifies suicidal behavior using person's spoken or written words

Using a person's spoken or written words, new computer tools can identify with great accuracy whether that person is suicidal, mentally ill but not suicidal, or neither.

7 Nov 2016

Scientists find way to produce realistic sensations of touch in human amputees

Scientists at the University of Chicago and Case Western Reserve University have found a way to produce realistic sensations of touch in two human amputees by directly stimulating the nervous system.

27 Oct 2016

Salk researchers develop new computer program to measure blepharosplasm severity

If two clinicians observe the same patient with blepharospasm -- uncontrollable muscle contractions around the eye -- they'll often come away with two different conclusions on the severity of the patient's symptoms.

24 Oct 2016

Cancer cell's shape may offer clues for precise prognosis

Doctors can sometimes use a cancer cell's genetics to predict how it will act - how dangerous it is and thus what treatments should be used against it.

20 Oct 2016

USAID funds partnership effort to locate and assess Zika cold spots in Guatemala

The Arnhold Institute for Global Health at the Icahn School of Medicine at Mount Sinai, software company Dimagi, and Guatemalan NGO TulaSalud announced today that their partnership to locate and assess vulnerable areas in Guatemala to determine their level of risk for a Zika epidemic is being funded by the U.S. Agency for International Development.

18 Oct 2016