- Supermedic.ai
- Posts
- Breakthrough: AI scientist conducts research autonomously 🚀
Breakthrough: AI scientist conducts research autonomously 🚀
ALSO: Say ‘aah’ to AI: tongue analysis detects diseases with 96% accuracy, AI-powered brain implant restores speech for ALS patient, 3D-printed blood vessels bring artificial organs closer to reality
Welcome AI & Healthcare enthusiasts!
Meet the world's first AI scientist, unveiled by Sakana AI. This autonomous system can conduct entire research projects from start to finish—no human intervention required.
But that's not all. From AI diagnosing diseases by looking at your tongue to 3D-printed blood vessels bringing us closer to artificial organs, this week is packed with breakthroughs in the intersection of AI and Healthcare.
Let’s dive into it!
Victor
TODAY’S MENU
Say 'Aah' to AI: Tongue Analysis Detects Diseases with 96% Accuracy
This AI Scientist Can Conduct End-to-End Scientific Research Autonomously
AI-Powered Brain Implant Restores Speech for ALS Patient
3D-Printed Blood Vessels Bring Artificial Organs Closer to Reality
Everything Else You Should Know this Week
Read time: under 5 minutes
AI DIAGNOSIS
Researchers from the University of South Australia and Iraq’s Middle Technical University have developed an AI system capable of diagnosing diseases by analyzing images of a patient’s tongue—a method inspired by traditional Chinese medicine.
How It Works
The AI was trained on over 5,000 tongue images, learning to recognize colors associated with various health conditions.
Researchers then tested the model with 60 real patient photos from teaching hospitals, fine-tuning its accuracy.
Finally, they used a USB webcam to scan volunteers' tongues, achieving 96.6% accuracy in identifying diseases such as diabetes, cancer, anemia or severe COVID-19.
"Typically, people with diabetes have a yellow tongue; cancer patients a purple tongue with a thick greasy coating; and acute stroke patients present with an unusually shaped red tongue" Ali Al-Naji, adjunct associate professor at UniSA.
Why It Matters: With its ability to offer a quick, non-invasive diagnosis, this technology might provide doctors with an instant second opinion and become a vital tool in medical facilities worldwide.
FROM OUR SPONSOR
Companies offer referral bonuses for new hires, but only to their employees - not you.
But what if you know the perfect candidate?
Enter Draftboard, a platform where companies make those bonuses public and claimable by anyone. Draftboard gives you a simple and seamless way to share job opportunities from the best companies in the world (SeatGeek, Via, Formlabs, Bilt, Triple Whale, OneSginal, etc.) with your network - and you get paid when they get hired.
How Draftboard Works:
Simple Sharing: Copy your unique referral link and send via text message, email, or social media - however you want.
Wide Range of Companies: Access job postings from top-tier companies across various industries - over 80 companies listing roles.
Real-time Tracking: Monitor the progress of your referrals in real-time as they move through the recruiting process.
Why You Should Join Draftboard: Earn extra income with no experience needed on an easy-to-use platform for sharing and tracking candidate referrals.
Sign up for free today and start earning referral bonuses of up to $10,000!
AI SCIENTIST
Illustration made with genAI (Midjourney)
Sakana AI, a Tokyo-based startup, has introduced "The AI Scientist," an AI system that can autonomously conduct scientific research, potentially revolutionizing the scientific process as we know it.
"We're envisioning a future where AI could autonomously manage entire research processes, from ideation to peer review”
Key Details
Like a scientist, Sakana AI generates fresh research ideas, writes code, runs experiments, writes papers, and performs its own peer review.
The AI Scientist has already produced papers with novel contributions in machine learning domains like language modeling and diffusion models.
Each paper only costs approximately $15 to produce, which could potentially democratize research capabilities.
Looking forward, Sakana AI imagine a future where we won't just manage AI researcher but also autonomous reviewers, area chairs, and entire conferences.
Why it matters: Initiatives like Sakana AI could dramatically accelerate scientific progress by allowing researchers to collaborate with AI agents and automate time-consuming tasks. We're entering a new era where academia could soon be powered by a tireless community of AI agents, working round-the-clock on any problem they're directed to.
NEUROSCIENCE
Credit: The New York Times
Casey Harrell, a 45-year-old living with ALS, had gradually lost the ability to speak due to the disease. Determined to reconnect with those around him, Casey volunteered for an experimental brain-computer interface (BCI) trial at UC Davis Health. The trial aimed to restore his ability to communicate by interpreting his brain signals into speech—a journey that recently culminated in a significant breakthrough.
How It Works
Microelectrode arrays were implanted in Casey’s brain, targeting speech-related areas.
The BCI system decoded Casey’s brain activity into words and sentences thanks to AI, displaying them on a screen and reading them aloud.
Initial training achieved 99.6% accuracy within 30 minutes with 50 words; subsequent sessions expanded the vocabulary to 125,000 words with 97.5% accuracy.
“The first time we tried the system, he cried with joy as the words he was trying to say correctly appeared on-screen. We all did.” Sergey Stavisky, Neuroscientist.
Why It Matters: While platforms like Neuralink have helped paralyzed patients navigate computer screens mentally, recreating someone's voice is considered more challenging due to numerous variables. This technology offers new hope for ALS patients and others with neurological conditions, allowing them to regain the ability to communicate effectively with their loved ones.
ARTIFICIAL ORGANS
Illustration made with genAI (Midjourney)
Scientists at Harvard's Wyss Institute have developed a revolutionary 3D printing method called "co-SWIFT" that creates functional blood vessels within living human cardiac tissue, bringing us one step closer to manufacturing implantable human organs.
Key Details
The new technique, co-SWIFT (Coaxial Sacrificial Writing In Functional Tissue), prints vessels with a distinct "shell" of smooth muscle cells and endothelial cells surrounding a hollow "core" for fluid flow.
These 3D-printed vessels closely mimic the structure of natural blood vessels and can be interconnected to form branching networks.
The team successfully printed a model of a patient's left coronary artery vasculature into cardiac tissue, demonstrating potential for personalized medicine.
After five days of perfusion, the cardiac tissue started beating synchronously and responded to common cardiac drugs, indicating healthy functionality.
Why It Matters: This breakthrough could revolutionize organ transplantation by enabling the creation of lab-grown, patient-specific organs with functional blood supply. It addresses one of the major challenges in tissue engineering - creating a vascular system that can support living human tissues and organs.
Must-Read AI Healthcare News This Week
Ambient Documentation: Kaiser Permanente integrates Abridge’s AI technology into 40 hospitals and 600 medical offices to automate clinical documentation, aiming to enhance operational efficiency across its network.
Business: Stryker announces definitive agreement to acquire Care.ai, a leading virtual care and ambient intelligence platform, set to impact 40,000 care sites.
Obstetrics: AI matches the accuracy of sonographers in estimating gestational age, demonstrating its potential as a reliable tool for prenatal care and reducing the need for manual ultrasound analysis.
Research: HHMI invests $500 million in AI-driven life sciences research, aiming to accelerate breakthroughs in understanding complex biological systems and improving human health.
Materials Science: University of Waterloo researchers develop a smart fabric that converts body heat and solar energy into electricity, enabling self-powered health monitoring and smart clothing applications.
Neurology: TUM researchers develop a protein drug that suppresses neuronal hyperactivity in Alzheimer’s, showing potential to halt disease progression based on promising results in mice.
Thanks for reading!
How would you rate today's newsletter?Your feedback helps me create better emails for you! |
Reply