It is impossible to pick up with your naked ear the unique sound of a Covid-19 cough. But MIT researchers are now detecting asymptomatic cases of Covid-19 using nothing but the sounds of them coughing.
We have seen researchers training algorithms to identify conditions like asthma and pneumonia using the sound of coughing.
A team at MIT was experimenting with detecting the signs of Alzheimer’s using phone recordings when they decided to try the same models on Covid-19.
The team which was based at the Auto-ID Laboratory in MIT, gathered at least 200,000 sample cough recordings. 2,500 of them were confirmed to have tested positive for the virus that causes Covid-19.
The coughs were crowd sourced from a website they set up allowing people to submit their own recordings of forced coughs.
4,000 of the samples were taken first to train the AI model. Another 1,000 were taken to test the model.
The researchers only had to slightly tweak the model they had created to make it work for Covid-19 instead of Alzheimer’s and they succeeded in detecting the patterns of vocal cord strength, lung and respiratory performance, sentiment, and muscular degradation. These were the four biomarkers that exhibited patterns unique to Covid-19.
After training and testing, the model was ready for a run. They fed it with new cough recordings and it successfully detected Covid-19 correctly 98.5% of the time. For people who had Covid-19 but were asymptomatic, the accuracy of the model went all the way up to 100%.
According to Professor Brian Subirana who is the director of the Laboratory, these findings show that when you have Covid-19, the way you produce sound will change, even when you are still asymptomatic.
The team is collaborating with multiple hospitals to gather more cough recordings. They hope to boost the model’s accuracy by working with a greater diversity of cough recordings.
The team is also working to put the model into an app that could allow people who may have asymptomatic Covid-19 to pre-screen themselves in a quick and non-invasive way.
Anyone who is coughing and thinks that they might have Covid-19 could pre-screen themselves before going in for a test.
Such a model could be used together with smart speakers and with other listening devices.
According to Subirana: “The effective implementation of this group diagnostic tool could diminish the spread of the pandemic is everyone uses it before going to a classroom, a factory, or a restaurant.
The Dawn of AI-Enhanced Rehabilitation: How AI-Powered Trousers are Revolutionizing Stroke Recovery
In the quaint town of Penarth, Vale of Glamorgan, a remarkable story of resilience and technological innovation is unfolding. Julie Lloyd, a 65-year-old stroke survivor, is relearning to walk, aided by a groundbreaking piece of technology: trousers powered by artificial intelligence (AI). This pioneering trial in the UK marks a significant leap in medical technology, offering new hope to stroke victims worldwide.
The Breakthrough in Stroke Rehabilitation
Julie’s journey is not just a personal triumph but a beacon of hope for millions affected by strokes. According to the World Health Organization, strokes are the second leading cause of death globally, and the leading cause of acquired disability among adults. The road to recovery is often long and arduous, with traditional rehabilitation methods providing varying degrees of success.
The AI-powered trousers represent a paradigm shift in rehabilitation technology. As Julie puts it, “I really feel this is the breakthrough for stroke victims that has been much and long awaited for.” This sentiment echoes the sentiments of many in the medical community who have long sought more effective ways to aid stroke recovery.
How the Technology Works
The AI trousers are a marvel of modern engineering and medical science. They function by using a series of sensors and motors that work in tandem with the wearer’s movements. This technology is not just about physical support; it’s about enhancing the body’s natural ability to relearn movements. The AI component analyses the wearer’s gait, providing real-time adjustments to improve walking patterns, much like a physical therapist would.
This approach is grounded in the concept of neuroplasticity, the brain’s ability to reorganize itself by forming new neural connections. By assisting in the correct movement patterns, the trousers help the brain to ‘relearn’ walking, potentially speeding up the recovery process.
The Impact on Stroke Rehabilitation
The implications of this technology are vast. For stroke survivors, the journey to recovery can be filled with frustration and despair. Traditional rehabilitation methods can be slow and, at times, ineffective. The AI trousers offer a more dynamic and responsive form of therapy that could revolutionize how we approach stroke rehabilitation.
In a study conducted by the American Stroke Association, it was found that early and individualized rehabilitation can significantly improve outcomes for stroke survivors. The AI trousers align perfectly with this philosophy, offering a tailored rehabilitation experience that adapts to the individual’s needs.
Challenges and Future Prospects
Despite the promise, the road ahead for AI in medical rehabilitation is not without challenges. Cost and accessibility are significant concerns. Cutting-edge technology often comes with a high price tag, potentially putting it out of reach for many who could benefit from it.
Moreover, there’s the challenge of integrating such technology into existing healthcare systems. As noted by experts in healthcare technology, the adoption of new medical technologies often faces hurdles in terms of regulatory approval, practitioner training, and patient acceptance.
However, the future looks bright. As AI and robotics continue to advance, we can expect these technologies to become more affordable and widespread. The potential for AI to aid in various aspects of healthcare, from diagnosis to treatment and rehabilitation, is enormous.
Julie Lloyd’s story is just the beginning. As we stand on the cusp of a new era in medical technology, the possibilities are endless. The AI-powered trousers are more than just a piece of technology; they are a symbol of hope and a testament to human ingenuity. For stroke survivors around the world, this could be the dawn of a new day in rehabilitation, one where technology and human resilience come together to create new possibilities.
AI-Powered Medical Database Aims to Revolutionize Doctor-Patient Interactions
Artificial Intelligence (AI) is making inroads into various sectors, and healthcare is no exception. According to a recent NPR article, Dr. Michael Mansour of Massachusetts General Hospital is among the early adopters testing an AI-enhanced version of UpToDate, a widely-used medical database. This experimental version employs generative AI to provide doctors with more targeted information, aiming to streamline the diagnostic process.
Wolters Kluwer Health, the company behind UpToDate, is working on making the database more conversational, allowing doctors to maintain the context of their queries. While the technology is still in beta and has some kinks to work out, the potential is enormous. AI could not only assist in making accurate diagnoses but also free up doctors’ time, allowing them to focus more on patient care. As Dr. Marc Succi of Mass General Brigham aptly puts it, “AI won’t replace doctors, but doctors who use AI will replace doctors who do not.”
A New way around Drug Resistant Tuberculosis
Researchers at Purdue University have created a powerful compound that specifically tackles Tuberculosis, a leading killer worldwide.
The scientists came up with a series of inhibitors that destroy TB by targeting a protein necessary for the survival of the TB molecule.
Tuberculosis destabilizes the immunity of patients with the help of Protein Tyrosine Phosphates B (mPTPB). Their findings were published in the Journal of Medicinal Chemistry.
“The death toll from TB is particularly high because of drug-resistant strains,” said Zhong-Yin Zhang, distinguished professor and head of Purdue’s Department of Medicinal Chemistry and Molecular Pharmacology and director of Purdue Institute for Drug Discovery. “These inhibitors are part of a promising new approach to developing TB therapeutic agents with novel targets and mechanisms of action to help save more lives.”
Right now, doctors rely on antibiotic preparations to treat Tuberculosis. The problem is that many patients don’t complete their dose of antibiotics and this non-adherence leads to the development of drug resistant tuberculosis.
“We developed a platform to target mPTPB for novel anti-TB agents that builds on technologies we pioneered to modulate abnormal protein tyrosine phosphatase activity for the treatment of diseases such as cancer, diabetes and autoimmune disorders,” Zhang elaborated.
According to Zhang, the inhibitors’ have unique properties that make them incredibly useful. They have a lighter molecular weight and superior metabolic stability. They give scientists an excellent opportunity to create better treatments for Tuberculosis.
The visionary scientists are already working to patent the exciting new technology. The hunt is on for partners who will work with Purdue to further the development of the new technology. This is together with the Purdue Research Foundation Office of Technology Commercialization.
Home3 years ago
Best Science Board Games
Medical3 years ago
Four-Week Memory Test that could predict the Risk of Alzheimer’s
Medical3 years ago
Patients could Start to Monitor their Vision Remotely from Home
Medical3 years ago
IVF gets Better with AI
Gadgets3 years ago
New to 3D Printing? Here are 7 Tips
Environment3 years ago
Farming Could be Transformed by Self-Watering Soil
Medical3 years ago
Scientists will Soon spot Diseases and find exoplanets with super Tiny photonic devices
Automation2 years ago
The Best Devices for a Smart home – and what to do with them