Piramidal: Revolutionizing Brain Analysis with AI for Improved Neurological Diagnoses

Exclusive: How Piramidal is using AI to decode the human brain

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More The human brain is ultimately one of the last frontiers -- a paradoxical black box that we can't even begin to understand ourselves. But what if, just as paradoxically, AI could interpret the complexities of the brain to help identify and diagnose some of our most serious diseases? That's exactly what Y Combinator-backed startup Piramidal has set out to do. The company is building a first-of-its-kind foundation model that can detect and understand complex "brain language" or brainwaves. It can be fine-tuned to a range of electroencephalography (EEG) use cases, and has implications in other areas of medicine, as well as in pharmacology and even consumer products. The startup is also announcing today a $6 million fundraise from Y Combinator, Adverb Ventures, Lionheart Ventures and angels including founders of Intercom, Plangrid and Guilded. "We're training an AI model on brainwave data the same way ChatGPT is trained on text," Kris Pahuja, Piramidal co-founder, told VentureBeat. "It is the largest model ever trained on EEG data." EEG data too much for one person to interpret Today, when patients with brain-related conditions seek medical treatment, their EEG brain waves are mapped, then inspected by neurologists. But this can be highly time-consuming and error-prone, with a margin of error up to 30%, according to Pahuja. Compounding this is the fact that there is an "extreme shortage" of neurologists -- particularly those who can interpret EEGs -- in the U.S. Pahuja pointed out that patients' brain waves are recorded for several days or weeks when they are in the intensive care unit (ICU) -- and no human could possibly go through all that. Instead, physicians take random samples and perform quick pattern recognition, but this can miss out on a lot of diagnosis. EEG data is also incredibly complex, difficult to interpret and has significant signal variability. Pahuja pointed out that when someone is looking at an MRI image, for instance, they are looking at an image in one distinct period of time. But an EEG, by contrast, is "very difficult to read, it changes thousands of times a second across 10 to 20 channels," said Pahuja. He noted that even specialized doctors can miss many details, and some may only be trained in certain areas such as epilepsy or brain injury, so they don't know all the markers to look for. Another challenge lies in scarce labels/annotations for EEG recordings, which can inhibit the training of more large-scale, generalized models, he noted. Further, narrow models aimed at specific tasks can't be repurposed for new use cases. "We want to train our model to be at the level of an expert neurologist, but also not miss anything while an EEG is going on," said Pahuja. Trained on every EEG use case Advancements in time-series models trained on diverse, unlabeled data to evolve to a variety of tasks is allowing Piramidal -- named for pyramidal neurons found in areas of the brain -- to overcome these significant challenges, according to the startup. The company is first fine-tuning its model for the neuro ICU; that product will be able to ingest EEG data and interpret in near-real time, providing outputs to medical staff on occurrence and diagnosis of disorders such as seizures, traumatic brain bleeding, inflammations and other brain dysfunctions. "It is truly an assistant to the doctor," said Pahuja, noting that the model can ideally help provide quicker and more accurate diagnoses that can save doctors' time and get patients the care they need much more quickly (which can also help reduce overall healthcare costs). "Brainwaves are central to neurology diagnosis," Piramidal co-founder and CEO Dimitris Sakellariou, who holds a PhD in neuroscience, told VentureBeat. By automating analysis and enhancing understanding through large models, personalized treatment can be revolutionized and diseases can be predicted earlier in their progression, he noted. And, as wireless EEG sensors become more mainstream, models like Piramidal's can enable the creation of personalized agents that "continuously measure and monitor brain health." "These agents will offer real-time insights into how patients respond to new treatments and how their conditions may evolve," said Sakellariou. The company's model has seen every EEG use case from both proprietary and open-source datasets, said Pahuja. It can tackle certain biomarkers that exist on certain disorders right away (such as seizures, brain bleeding or low blood flow) and has the ability to find other biomarkers that don't yet exist (such as for diseases such as Parkinson's or Alzheimers. Piramidal is currently piloting in two hospitals in England, at King's College and Saint Thomas. "No one else is building an EEG model like ours," said Sakellariou. He pointed out that it requires significant time and money to ensure "generalisability and reliability" from the start. "AI has the potential to transform healthcare, especially neurological diagnostics," said Sakellariou. "Piramidal aims to be at the forefront of this transformation." Inspired by psychedelic and sleep research The revolutionary model was initially inspired by Sakellariou's experiences in various EEG studies, ranging from psychedelics to sleep research -- both as a subject and an observer. In these studies, he explained, a technician attaches electrodes to the scalp and the system records brainwaves. "Surprisingly, the process of capturing brain activity through scalp and hair is straightforward -- you simply attach some wires to your head, and you can monitor what's happening in your cortex," said Sakellariou. However, researchers and clinicians then have to visually analyze these "wavy lines," which could represent hours, days or even weeks of brainwave data, to extract useful information for the subject or patient. He explained that this process is error-prone and subject to misinterpretation for a couple of reasons. Firstly, acquiring necessary training to interpret brainwaves is "highly empirical"; secondly, the extensive duration of the recordings does not allow for "meticulous inspection," especially since brain changes reflected in EEG data can occur in milliseconds. Beyond the ICU But for Piramidal, the ICU is just the start, according to its founders: Their model has significant potential beyond that niche area of medicine. For instance, Pahuja noted, it could be implemented into general neurology, epilepsy units, longer-term monitoring situations and in neuropsychiatry (which uses EEGs to study mental health disorders and cognitive decline). Further down the line, it could be used in every physician clinic to help with different types of patient screenings. It could also be "huge for pharmacy," providing real-time efficacy, said Pahuja, as well as in consumer products that rely on EEG data (such as Ray Ban Meta or the multitude of health monitoring devices on the market). "As technology evolves, you can get through the noise," he said. In the near future, it's possible that humans will have the opportunity for "quantified introspection" through everyday devices such as earphones equipped with neural sensors, Sakellariou pointed out. For example, we could measure how stress levels decrease after reducing screen time, train ourselves to enhance meditation by monitoring relaxation levels in a closed loop, or boost memory during periods of "intense learning" through targeted auditory stimuli during specific sleep stages. "All of this will be possible via personalized agents powered by large-scale models like ours," said Sakellariou. Pahuja said he has always been fascinated by the brain, describing "neurotech as the next frontier." As he put it: "The most complex thing we have is our brain, but that is completely not understood at the moment. Can we find a way to decode the brain?"

Piramidal raises $6M to advance AI brainwave analysis and improve diagnoses of neurological conditions - SiliconANGLE

Piramidal raises $6M to advance AI brainwave analysis and improve diagnoses of neurological conditions Piramidal Inc. stepped into the limelight today, announcing that it has filled its war chest with $6 million in seed funding to tackle the intricacies of brainwave analysis using a specially developed foundational artificial intelligence model. Today's round was led by Y Combinator, with the participation of several other venture capitalists, including Adverb Ventures, Lionheart Ventures, as well as angel investors such as the founders of Intercom Inc., PlanGrid Inc. and Guilded Inc. The startup is developing what it terms a "barrier-breaking AI model" that's designed to help neurologists better assess brainwave data. It hopes that its AI model will speed up and improve the accuracy of brain injury diagnoses and reduce patient waiting times. Piramidal says it has used cutting-edge machine learning techniques to develop a proprietary AI model that can analyze the results of electroencephalography or EEG tests, which are used by doctors to measure electrical activity in the brain. EEG tests are performed in order to assess the extent of brain injuries and diagnose brain-related diseases. The tests involve mapping the patient's brainwaves, after which a neurologist will manually inspect the data to try and determine what's wrong. But although EEG is often the best method for diagnosing brain problems, it's a time-consuming and error-prone process, with studies suggesting that neurologists still misinterpret the data in 30% of cases. Piramidal co-founder and Chief Executive Officer Dimitris Sakellariou told SiliconANGLE that EEG scans are notoriously difficult to understand because they reveal such a vast number of normal and abnormal patterns of brain activity. "There's a lot of variability of these patterns across individuals," he added. A second challenge, Sakellariou mentioned, is that the EEG scans themselves can often take days to perform. "These things make EEG analysis time-consuming and error-prone, and they require highly specialized medical professionals to interpret them and conduct diagnosis," he said. Piramidal, which is named after the "pyramidal neurons" that play a crucial role in higher cognitive functions such as learning, memory and decision-making, wants to improve the accuracy and reliability of EEG tests by using AI to process and analyze the data more rapidly, so it can diagnose patient's conditions faster and more accurately. Its foundational model is initially focused on epilepsy diagnoses, and clinical tests show it has good potential to reduce error rates. While large language models such as ChatGPT are trained on text, Piramidal's AI model is trained specifically on human brainwaves, and this knowledge enables it to understand and detect various facets of brain activity. Kris Pahuja, co-founder and chief product officer, added that the medical science industry previously found it very difficult to build robust computational methods of analyzing EEG due to the variability found in recordings across different patients and devices. But with the widespread availability of generative AI and increased computational resources now available through the cloud, it has become possible to crack the EEG code. "We can now develop systems capable of analyzing vast volumes of data and identifying associations across thousands of patients," he said. "This is a task that was previously unimaginable for smaller machine learning models or humans." The startup plans to go beyond epilepsy and diagnose every kind of brain condition, and other use cases might include remote monitoring of brainwave abnormalities, real-time brain health tracking, and drug discovery for neurological conditions. Holger Mueller of Constellation Research Inc. said generative AI technology is much better suited for interpreting EEG scans because it has the ability to crunch data at greater scales and learn patterns much more rapidly. "The real value though, is that generative AI models like Piramidal's have the ability to look back at vast amounts of longitudinal data and identify suspicious signs in older EEGs that didn't previously raise any flags," Mueller said. "Humans will never have the capacity and willingness to study all of this data, but AI software can, and it will potentially save lives by doing it." The funding is important for Piramidal, as budgetary constraints are one of the main challenges that prevent AI from being used more extensively in healthcare. A recent article in Forbes underscores this, noting that the high costs involved in creating AI models for specific uses in healthcare means that many such initiatives never get off the ground. Pahuja said the funding will ensure the company has the money it needs to continue training its model and bring its first product to market.