Machine Learning News and Research

RSS

AI techniques in medical imaging may lead to false positives and false negatives

Machine learning and AI are highly unstable in medical image reconstruction, and may lead to false positives and false negatives, a new study suggests.

12 May 2020

New tool could help physicians diagnose the cause of blood clots

A new tool using cutting-edge technology is able to distinguish different types of blood clots based on what caused them, according to a study published in eLife.

12 May 2020

Personalized therapeutic approach can improve bone healing process, prevent complications

When someone breaks a bone in their lower leg, the fracture can often be complex, making the healing process lengthy and involved. In these cases, it is usual for the fractured bone to be surgically stabilized using an orthopedic implant.

12 May 2020

UC Santa Barbara researcher receives NSF award to study the coordinated behavior of neural circuits

Everything we do comes down to a series of neural signals that translate into physical behaviors. We receive information through our senses, sensory neurons convert this information into electrical and chemical signals that are processed by other neurons in our brains and ultimately, motor neurons fire muscles that move our limbs.

12 May 2020

Single-cell RNA-seq addresses key question in islet cell biology and diabetes research

The pancreas is an abdominal organ that produces digestive enzymes as well as hormones that regulate blood sugar levels. This hormone-producing function is localized to the islets of Langerhans, which constitute clusters of different endocrine cell types.

12 May 2020

Smart health system to monitor people in COVID-19 quarantine

The global coronavirus pandemic has spread to 187 countries and territories, infecting more than 4.17 million people. Most countries, especially those with a skyrocketing caseload, grapple with a lack of hospital beds and facilities to cater to every patient infected with the virus. Now, a team of researchers may have the solution to this problem – a smart health system to monitor patients who are in home isolation.

12 May 2020

GCS centers support research to fight against global COVID-19 pandemic

In December 2019, the world learned of a new and deadly pathogen. News coming out of Wuhan, China confirmed public health experts' worst fears--a novel coronavirus appeared to have jumped from animals to humans.

11 May 2020

Reproduction number of COVID-19 and how it relates to public health measures

A new study published on the preprint server medRxiv in May 2020 reports the use of a dynamic SEIR model to identify variations in the reproductive number of SARS-CoV-2 over time, using machine learning techniques. This could help to model and predict the outcomes of various public health solutions.

10 May 2020

Internet search patterns important in tracing and predicting COVID-19 spread

A new study published on the preprint server medRxiv in May 2020 has identified a link between Internet search patterns and local disease progression for COVID-19. It recommends the use of search data to track and predict COVID-19 spread as a complementary method to established public health surveillance methods.

10 May 2020

World's largest CT scan database with COVID-19 features collected in Russia

Earlier, scientists of the Diagnostics and Telemedicine Center already reported that they had collected the first database of CT studies of patients with laboratory-confirmed infection. It had about 50 CT scans of 20 patients.

8 May 2020

New tool may offer a novel approach to prevent multiple chronic diseases

A study just released by Columbia University Mailman School of Public Health is reporting a blood-DNA-methylation measure that is sensitive to variation in the pace of biological aging among individuals born the same year.

6 May 2020

Artificial intelligence may help diagnose diseases that affect the heart

Artificial intelligence (AI) may be an aid to interpreting ECG results, helping healthcare staff to diagnose diseases that affect the heart.

5 May 2020

Quantum machine learning may lead to possible treatments for COVID-19

Quantum machine learning, an emerging field that combines machine learning and quantum physics, is the focus of research to discover possible treatments for COVID-19, according to Penn State researchers led by Swaroop Ghosh, the Joseph R. and Janice M. Monkowski Career Development Assistant Professor of Electrical Engineering and Computer Science and Engineering.

5 May 2020

AI tool automatically diagnoses atrial fibrillation and other ECG abnormalities

Artificial intelligence may be an aid to interpreting ECG results, helping healthcare staff to diagnose diseases that affect the heart.

4 May 2020

Researchers develop AI algorithm to accurately predict risk for and diagnose Alzheimer's

Researchers have developed a computer algorithm based on Artificial Intelligence that can accurately predict the risk for and diagnose Alzheimer's disease using a combination of brain magnetic resonance imaging, testing to measure cognitive impairment, along with data on age and gender.

4 May 2020

Improving Automated NMR Integration Through Deep Learning

In this interview, Data Scientist Federico Paruzzo discusses how Bruker has used deep learning to develop the new command, and how it compares to other approaches available.

From Bruker BioSpin Division 30 Apr 2020

New web-based imaging platform reveals processes in cancer and COVID-19

Medical images for a wide range of diseases, including COVID-19, can now be more easily viewed, compared, and analyzed using a breakthrough web-based imaging platform developed by Massachusetts General Hospital (MGH) and collaborating researchers.

30 Apr 2020

Study with twins shows COVID-19 symptoms have genetic contribution

A new study published on the preprint server medRxiv from King's College, London, suggests that an individual's genetic makeup may contribute to how much a person is likely to be affected by COVID-19, or whether they are likely to be infected at all.

29 Apr 2020

Studies show how sex-determining genes affect courtship and aggression behaviors

Fruit flies, like many animals, engage in a variety of courtship and fighting behaviors. Now, Salk scientists have uncovered the molecular mechanisms by which two sex-determining genes affect fruit fly behavior.

28 Apr 2020

AI system could predict a youth's risk for committing acts of school violence

By leveraging the basics of artificial intelligence technology now used to predict risk for suicide or other mental health issues, researchers developed an AI system that analyzes linguistic patterns to predict a youth's risk for committing acts of school violence.

28 Apr 2020