HomeCompaniesMecha Health

Mecha Health

Foundation models to automate x-ray analysis for radiologists

Mecha Health builds foundation models to automate x-ray analysis for radiologists. We take medical images and process them using proprietary models to produce accurate draft medical reports. Our first model was built in less than two months, and beat Microsoft, Google, and OpenAI on clinical accuracy metrics. On top of that, it’s two orders of magnitude smaller and trained with a quarter of the data. We are partnering with the largest privately owned radiology practice in the US and a multinational tele-radiology company to provide them with their own foundation model, enabling their radiologists to go from reading 1 scan per hour to 1 scan every 5 minutes. By charging on a per scan basis, x-ray report generation represents a 40B+ market opportunity.
Active Founders
Ahmed Abdulaal
Ahmed Abdulaal
Founder
Hugo Fry
Hugo Fry
Founder
Ayodeji Ijishakin
Ayodeji Ijishakin
Founder
Nina Montaña Brown
Nina Montaña Brown
Founder
Mecha Health
Founded:2024
Batch:W25
Team Size:4
Status:
Active
Location:San Francisco
Group Partner:Michael Seibel
Company Launches
Mecha Health 🩻 Trustworthy medical image reporting using AI
See original launch post

TLDR;
Mecha Health helps radiologists save time and effort by producing draft reports of medical images using AI.

The Problem: Too Many Scans Not Enough Doctors.
Due to a shortage of experts, US radiologists have to read 100 - 250+ studies per day, and this means that 55% have reported high levels of burnout. Additionally, patients sometimes have to wait days to receive medical reports for their scans due to backlogs. At times, this can result in preventable patient harm.

Our Solution: Accurate & Interpretable Medical Image Analysis.
We improve the reporting process by producing draft reports with AI and have invented new science to do this both accurately and safely. Our system can trace every finding to its visual source in the image and evidence each finding with examples from the training dataset. This allows for transparent reporting that doctors can trust.

Our Background: Frontier Scientific Expertise.
We are leading researchers in machine learning and medical imaging having published in tier-one AI venues (NeurIPS, ICLR, ICML). Nina, Ahmed & Deji crossed paths through University College London’s Medical Imaging PhD program. Hugo met the team after he published AI research that was cited by Anthropic. Ahmed, a trained medical doctor from Imperial College London, witnessed firsthand how reporting delays harm patient outcomes—driving Mecha Health’s mission to transform radiology.

Our Ask: Intros to Pioneering Medical Professionals and Healthcare Executives.
Please reach out to the team at ahmed@mecha-health.ai if you know any tech-forward clinicians, radiologists, radiology practices, or healthcare executives who could benefit from our technology. You can also check us out at https://mecha-health.ai/.

Watch our full product video here
https://youtu.be/s5uJS7S8EF4