Toggle light / dark theme

A deep learning-augmented smart mirror to enhance fitness training

In recent years, engineers and computer scientists have created a wide range of technological tools that can enhance fitness training experiences, including smart watches, fitness trackers, sweat-resistant earphones or headphones, smart home gym equipment and smartphone applications. New state-of-the-art computational models, particularly deep learning algorithms, have the potential to improve these tools further, so that they can better meet the needs of individual users.

Researchers at University of Brescia in Italy have recently developed a computer vision system for a smart mirror that could improve the effectiveness of fitness training both in home and gym environments. This system, introduced in a paper published by the International Society of Biomechanics in Sports, is based on a deep learning algorithm trained to recognize human gestures in video recordings.

“Our commercial partner ABHorizon invented the concept of a product that can guide and teach you during your personal fitness training,” Bernardo Lanza, one of the researchers who carried out the study, told TechXplore. “This device can show you the best way to train based on your specific needs. To develop this device further, they asked us to investigate the viability of an integrated vision system for exercise evaluation.”

Association of COVID-19 with New-Onset Alzheimer’s Disease

The study population comprised 6,245,282 older adults (age ≥65 years) who had medical encounters with healthcare organizations between 2/2/2020–5/30/2021 and had no prior diagnosis of Alzheimer’s disease. The population was divided into two cohorts: 1) COVID-19 cohort (n = 410,748)— contracted COVID-19 between 2/2/2020–5/30/2021; 2) non-COVID-19 cohort (n = 5,834,534)— had no documented COVID-19 but had medical encounters with healthcare organizations between 2/2/2020–5/30/2021. The status of Alzheimer’s disease and COVID-19 were based on the International Classification of Diseases (ICD-10) diagnosis codes and laboratory tests (details in the Supplementary Material).

We examined risks for new diagnosis of Alzheimer’s disease in COVID-19 and non-COVID-19 cohorts in all older adults, three age groups (65–74, 75–84, ≥85), and three racial/ethnic groups (Black, White, and Hispanic). Cohorts were propensity-score matched (1:1 using a nearest neighbor greedy matching) for demographics, adverse socioeconomical determinants of health including problems with education, occupational exposure, physical, social and psychosocial environment, and known risk factors for Alzheimer’s disease [13] (details in the Supplementary Material). Kaplan-Meier analysis was used to estimate the probability of new diagnosis of Alzheimer’s disease within 360 days after the COVID-19 diagnosis. Cox’s proportional hazards model was used to compare matched cohorts using hazard ratios and 95% confidence intervals. All statistical tests were conducted within the TriNetX Advanced Analytics Platform at significance set at p < 0.05 (2-sided).

Stanford scientists build first synthetic human microbiome from scratch

A team of researchers from Stanford University has constructed the first synthetic microbiome model, built entirely from scratch and encompassing more than 100 different bacterial species. It’s hoped the achievement will revolutionize gut microbiome research by offering scientists a consistent working model for future experiments.

Trillions of microbes live inside our guts. Perhaps one of the most significant discoveries in medical science over recent decades has been how deeply these microbes influence our general health. From affecting how well drugs we consume work, to modulating our immune systems, the gut microbiome plays a powerful role in all aspects of our health.

It’s also mind-bendingly complex. No two people share exactly the same gut microbiome composition. And while researchers frequently home in on ways particular bacteria influence metabolic mechanisms, it has been difficult to translate these findings into actual clinical therapies for humans.

Artificial pieces of brain use light to communicate with real neurons

Researchers have created a way for artificial neuronal networks to communicate with biological neuronal networks. The new system converts artificial electrical spiking signals to a visual pattern than is then used to entrain the real neurons via optogenetic stimulation of the network. This advance will be important for future neuroprosthetic devices that replace damages neurons with artificial neuronal circuitry.

A prosthesis is an artificial device that replaces an injured or missing part of the body. You can easily imagine a stereotypical pirate with a wooden leg or Luke Skywalker’s famous robotic hand. Less dramatically, think of old-school prosthetics like glasses and contact lenses that replace the natural lenses in our eyes. Now try to imagine a prosthesis that replaces part of a damaged brain. What could artificial brain matter be like? How would it even work?

Creating neuroprosthetic technology is the goal of an international team led by by the Ikerbasque Researcher Paolo Bonifazi from Biocruces Health Research Institute (Bilbao, Spain), and Timothée Levi from Institute of Industrial Science, The University of Tokyo and from IMS lab, University of Bordeaux. Although several types of artificial neurons have been developed, none have been truly practical for neuroprostheses. One of the biggest problems is that neurons in the brain communicate very precisely, but electrical output from the typical electrical neural network is unable to target specific neurons. To overcome this problem, the team converted the electrical signals to light. As Levi explains, “advances in optogenetic technology allowed us to precisely target neurons in a very small area of our biological neuronal network.”

Researchers construct complex synthetic microbiome

This can help engineer microbiome-based therapies in the future.

Researchers at Standford University have built from scratch the most complex and well-defined synthetic microbiome that will help us better understand the connections between the microbiome and human health, a university press release said.

The microbiome is a community of microorganisms that are found to cohabit in a given environment. The human gut has its own set of microorganisms that are markedly different from those on the skin.


The microbial community of over 100 bacterial species could help scientists learn more about the connections between the microbiome and human health.

Lassa Fever: Symptoms Of Ebola-like Virus As First UK Death Confirmed

Lassa fever is like ebola and there is an outbreak in Nigeria. It is transmissible through inhalation.


The death of a patient in the UK suffering from Lassa fever has heightened concern around the illness after a third case was reported.

The UK Health Security Agency (UKHSA) said it was contacting individuals who had been in close contact with the infected patients after the death was confirmed last week.

Commenting on the recent cases detected in the UK, which were linked to travel to west Africa, Dr Susan Hopkins, chief medical advisor at UKHSA, said: Cases of Lassa fever are rare in the UK and it does not spread easily between people.

Explained: New York City declares poliovirus a public emergency disaster

NPR’s Ayesha Rascoe speaks to Nsikan Akpan, health and science editor at WNYC/Gothamist, about the poliovirus emergecy disaster declaration in New York state.

AYESHA RASCOE, HOST:

New York Governor Kathy Hochul declared polio a state disaster emergency on Friday. The first polio case in nearly a decade was identified back in July. The virus can cause paralysis. Nsikan Akpan runs the health and science desk at WNYC/Gothamist. He joins us now. Welcome to the program.

Nigeria’s rising Yellow fever epidemic

Yellow fever epidemics are happening across Nigeria spreading state by state. The yellow fever is another haemorgic disease like ebola.


Over 160 million people, more than half of Nigeria’s current estimated population, are at risk of yellow fever in the country, reports by the World Health Organisation Africa Region have recently highlighted. Lately, the yellow fever virus has become of serious global health concern more because the wakes of its historic outbreaks are trailed by devastating outcomes.

The WHO says the virus is spreading rapidly across Africa, warning that the rising trend could cause an epidemic in Nigeria particularly, mainly because of its large population. Consequently, it issued an advisory for travellers to and out of Nigeria to consult their healthcare provider on precautionary measures required against the virus if need be.

The Yellow fever virus is endemic in tropical areas of Africa and Central and South America. The disease is a potentially fatal disease, as half of its patients in the toxic phase die within seven to 10 days.

Psilocybin therapy seems to help some people give up drinking alcohol

Psilocybin, the psychedelic compound in magic mushrooms, may help people with alcohol dependencies abstain from drinking. Nearly half of those who took the drug as part of a 12-week therapy programme no longer drank more than eight months later, according to results from the largest trial to date on psilocybin and addiction.

Michael Bogenschutz at NYU Langone Health in New York and his colleagues recruited 95 adults who were diagnosed with alcohol dependence. None of the participants had any major psychiatric conditions or had used psychedelics in the past year.

Everyone in the group went through a 12-week therapy programme. Most weeks, they had a roughly 1-hour long session with a therapist and a psychiatrist where they received cognitive behavioural therapy for alcohol use disorder.

Trust in AI-based preventive healthcare low among users

Artificial Intelligence (AI) can perform preventive healthcare activities such as health screening, routine check-up and vaccination with expert-level accuracy that can turn out to be cost-effective in the long run. Yet, a new research found that individuals show less trust in preventive care interventions suggested by AI than when the same interventions are prompted by human health experts.

The researchers at Nanyang Technological University (NTU) Singapore studied 15,000 users of a health mobile application and found that emphasising the involvement of a human health expert in an AI-suggested intervention could improve its acceptance and effectiveness.

These findings suggest that the human element remains important even as the healthcare sector increasingly adopts AI to screen, diagnose and treat patients more efficiently. The findings could also contribute to the design of more effective AI-prompted preventive care interventions, said the researchers.