Subscribe to Our Newsletter

Success! Now Check Your Email

To complete Subscribe, click the confirmation link in your inbox. If it doesn't arrive within 3 minutes, check your spam folder.

Ok, Thanks

Piramidal raised $6M to build the world's first human brainwaves foundation model

Piramidal, a healthcare AI startup, is developing a groundbreaking foundation model for EEG data that will unlock a series of use cases in medical settings, from assisting in diagnosing neurological conditions to supporting the discovery of biomarkers for drug and treatment development.

Ellie Ramirez-Camara profile image
by Ellie Ramirez-Camara
Piramidal raised $6M to build the world's first human brainwaves foundation model
Credit: Piramidal

Cofounders Dimitris Sakellariou and Kris Pahuja founded the startup Piramidal, a member of Y Combinator's 2024 Winter cohort, to build the world's first foundation model trained on brainwave data extracted from Electroencephalography (EEG) scans to unlock diverse use cases, from neurology copilots to biomarker discovery assistants. The inspiration for Piramidal's foundation model came from cofounder Dimitris Sakellariou's experience during his PhD at London's St Thomas' EEG department. There, he discovered the landmarks of a problem that could be tackled using artificial intelligence: Sakellariou noticed that:

  1. It is standard for neurologists to manually review scan results to detect abnormal patterns over time with the expected error rates potentially leading to misdiagnoses.
  2. There are troves of untapped EEG data incoming to healthcare institutions as remote devices continue to be deployed. However, the available data substantially surpasses the trained healthcare professionals available to review it.
  3. EEG data is not being leveraged partly because there is a shortage of neurologists, leading to extended wait times for patients looking for a diagnosis.
  4. The issues above are compounded by the fact that no two institutions share the same workflows, since institutions may use equipment made by different manufacturers, have varied setups, and even place a different number of electrodes in differing places in the patients' heads.

Thus, even if it may seem plausible to build a unified solution to assist with something as simple as detecting variations and anomalies across EEG scans, multiple challenges must be solved before landing an adequate, scalable solution. Piramidal claims it has already worked out a foundation model capable of understanding signals incoming from any setup. Once the codebase is ready for production, Piramidal lined up four pilots which will start in Q1 2025. According to its Y Combinator profile, the company's first product is a copilot for epilepsy diagnosis.

Once the copilot is in place, Piramidal plans to fine-tune its model for further use cases, rather than simply profiting from a developer API that enables third parties to fine-tune Piramidal's foundation model to suit their needs. This effort will be substantially boosted by Piramidal's recent $6 million seed round co-led by Adverb Ventures and Lionheart Ventures, which also counted the support from Y Combinator and angel investors.

Ellie Ramirez-Camara profile image
by Ellie Ramirez-Camara
Updated

Data Phoenix Digest

Subscribe to the weekly digest with a summary of the top research papers, articles, news, and our community events, to keep track of trends and grow in the Data & AI world!

Success! Now Check Your Email

To complete Subscribe, click the confirmation link in your inbox. If it doesn’t arrive within 3 minutes, check your spam folder.

Ok, Thanks

Read More