🤒 Your Phone Might Just Be Your New Doctor

In partnership with

Hi AI Futurists,

Today, we're unpacking Google Research's latest AI invention, Health Acoustic Representations (HeAR), and exploring how it can analyze coughs and breathing sounds to detect tuberculosis and estimate lung function.

Best,
Lex

Learn affiliate marketing for SaaS for $0

Recommended by 700+ SaaS professionals, Rewardful’s free affiliate marketing course aims to help you grow your MRR significantly.

Across 12 videos and 1 eBook, you’ll learn at your own pace how to build and grow a successful affiliate marketing program.

“I definitely recommend this course to any company who's rolling out a new program or wants to cover their bases on all best practices when it comes to creating a partner or affiliate program. It's a great starting point.”
- Tyler Gillespie, Head of Partnerships & SEO at beehiiv

Start Your Free Course Now

Highlight of the Day

Google’s AI Breakthrough in Lung Health Detection

Google Research's Health Acoustic Representations (HeAR) AI is revolutionizing health diagnostics by analyzing coughs and breathing sounds to detect issues like tuberculosis and estimate lung function. Trained using a staggering 300 million audio clips from YouTube, HeAR leverages the Transformer neural network to reconstruct hidden parts of audio spectrograms, enabling it to learn from real-world audio data.

In tests, HeAR outperformed existing models, achieving a 0.739 accuracy (AUROC) in detecting tuberculosis – a significant improvement over previous models. Beyond TB detection, HeAR also showed remarkable accuracy in estimating lung function parameters from smartphone recordings, potentially modernizing the screening of lung diseases like COPD.

While promising, HeAR remains a research tool and requires clinical validation before it can be used in diagnostics. Google is working to optimize HeAR for mobile devices, which could make this powerful AI more accessible globally. The future of health diagnostics might just lie in the sound of a cough.

Important Points:

• HeAR uses self-supervised learning to analyze health-related sounds.

• It outperformed previous models in TB detection (AUROC: 0.739) and lung function estimation.

• Requires further development for clinical use and mobile application.

What We Think About It:

HeAR is a brilliant example of how AI can give healthcare a much-needed upgrade, especially in places where medical resources are scarce. While it still needs to pass the real-world test (because who hasn’t had tech fail at the worst time?), the potential here is huge. Once perfected, this tech could make checking your lungs as easy as checking your notifications.

👉 Read more

Cool AI Tools

1. MolyPix.AI

   Create beautiful, easy-to-edit designs

   

2. AgentQL

   Painless data extraction and web automation

   

3. Fleak AI Workflows

   Build serverless APIs in minutes

   

Best of the Rest

• Procreate’s anti-AI pledge attracts praise from digital creatives

• Nvidia researchers create AI that predicts thunderstorms with kilometer-scale precision

• Stability AI names Hanno Basse as new Chief Technology Officer

• ElevenLabs’ text-to-speech app Reader is now available globally

And now, freshly picked AI art

That’s all for today, folks!

• If you’re enjoying the newsletter, share with a friend by sending them this link: 👉 https://www.futureblueprint.xyz/subscribe

• Looking for past newsletters? You can find them all here.

• Working on a cool A.I. project that you would like us to write about? Reply to this email with details, we’d love to hear from you!