Corti, a generative AI company developing AI foundation models for healthcare, announced the launch of specialised Healthcare AI models designed and trained to improve healthcare delivery. These models come in response to a new report from Corti and YouGovm which reveals that that one-third of US healthcare professionals using AI are spending up to three extra hours each week correcting errors.
Corti states that the announcement comes at a pivotal moment for the adoption of healthcare AI. While 74 percent of healthcare professionals in Europe support the use of AI in practice, 52 percent say they wouldn’t feel confident using current AI solutions in their work.
“This crisis of confidence has contributed to what industry experts call ‘pilot paralysis’ – widespread AI trials that fail to advance beyond testing due to accuracy, cost, and integration challenges,” it added.
Corti’s Three Core AI Models
In response to these issues, Corti has introduced three specialised AI models designed to improve healthcare delivery. Built on nine years of peer-reviewed research and trained on healthcare data, Corti’s new foundation models aim to enhance accuracy, speed, and cost-efficiency. The models are tailored to meet the unique needs of healthcare professionals and comply with strict medical regulations.
“We could be entering a golden age of healthcare AI, with over 60 apps now focused on scribing alone,” said Lars Maaloe, co-founder and CTO of Corti. “It’s exciting progress, but many of these tools rely on general-purpose AI that isn’t built to integrate or adapt to the complexities of healthcare. At Corti, we’ve developed specialized infrastructure and APIs that empower these apps to go further – enabling them to deliver smarter, more reliable solutions that can adapt to clinicians’ needs.”
“Corti’s foundation models form the most powerful and adaptable AI infrastructure in healthcare – delivering faster, more concise, accurate, and cost-efficient performance than the leading Large Language Models on the market,” the company said.
Solo: A fast, audio-reasoning model for expert clerk and transcription tasks, handling complex medical terminology in over ten languages.
Ensemble: A model focused on exceptional documentation. It builds agents that turn consultations into action, transforming medical discussions into structured documentation that is 25 percent more concise and more accurate than general-purpose AI, according to the company.
Symphony: A real-time clinical support model, operating 35 times faster than GPT-4, offering evidence-based insights during patient consultations.
In addition to these core models, the company says customers can integrate up to 20 expert models that function like healthcare specialists – purpose-built to build agents that tackle tasks like medical coding, quality control, and summarisation.
Corti’s AI Innovation
“Just as we wouldn’t let a medical student perform surgery without proper training, we shouldn’t trust AI systems that haven’t been specifically trained and validated for healthcare,” said Frederik Brabant, MD and Chief Medical Strategy Officer at Corti. “When over half of healthcare professionals say they wouldn’t feel confident using current AI solutions in their work, we know we need specialized solutions that can build sector confidence and safely meet healthcare’s unique demands.”
Professor Serge Belongie, Director of the Danish Pioneer Centre for Artificial Intelligence, underscored the technical significance: “General-purpose AI has its limits in the intricate, high-stakes world of healthcare. Corti’s dedication to building specialized models redefines what’s possible. By grounding their technology in healthcare-specific training and rigorous validation, they’ve created systems that not only meet but exceed the critical demands of AI for this field. Their work is a testament to the power of domain-specific AI to advance patient care and set a new benchmark for responsible and effective innovation.”
Seattle Fire Department Assistant Chief Lombard, said, “As an early partner of Corti, we’ve witnessed how their specialised healthcare AI transforms emergency care. Their purpose-built technology has enabled us to increase appropriate nurse triage referrals significantly, reducing pressure on public safety while maintaining excellent patient care. This evolution in their AI infrastructure reaffirms our choice of a partner truly dedicated to healthcare.”
“By 2030, we’ll face a global shortage of 10 million healthcare professionals and yet our study shows that today, a quarter consider leaving their job every single week,” added Andreas Cleve, Corti’s co-founder and CEO. “We can’t afford AI solutions that create more complexities or increase risk. The stakes are simply too high when it comes to patient care. It’s time to return to the roots of AI in healthcare, aim higher, and set a new standard across the industry.”
Corti is a research and development company that specialises in AI foundation models for healthcare. Corti says its models integrate into any healthcare application through Corti’s SDKs and APIs, enabling vendors, providers, and payers to leverage safe, AI across extensive use cases in healthcare.
Previously, according to a Microsoft report, Microsoft and technology partner Corti, EMS, developed a virtual assistant that can listen in and flag a likely cardiac arrest using a database of some 1,400 recorded calls to the emergency number.
Some people read for free. A few choose to support. If you found TelecomTalk useful, you can help keep us running.
Support Telecomtalk
