SensoDetect AB (publ) today announced a proprietary technological breakthrough that positions the company to capture a significant share of the global neuropsychiatric diagnostics market. By applying advanced artificial intelligence (AI) to its unique database of Brainstem Evoked Response Audiometry (BERA) tests, SensoDetect has achieved diagnostic accuracy for ADHD that is competitive with complex, costly methods like MRI and EEG, but with superior scalability and speed.

This AI-powered analysis validates the company's path to leadership in a market seeking objective, scalable diagnostic tools. Recent studies (Ref 1 and 2) highlight AI's potential to achieve 70-95% diagnostic accuracy in psychiatry, but these rely on expensive, time-consuming methods like MRI and EEG.

Commercial advantages

SensoDetect is the first company to successfully apply AI to an Auditory Brainstem Response (ABR) database, creating a decisive competitive moat. The Company's solution matches the accuracy of leading methods while offering critical commercial advantages:

• Speed & Workflow: A complete test in under 10 minutes, versus hours for alternatives.
• Cost-Efficiency: Requires no multimillion-dollar capital equipment.
• Patient Comfort: Non-intrusive and simple to administer.
• Scalability: Easily deployed in clinics worldwide.

"This isn't just an innovation; it's a fundamental competitive shift," said P-A Hedin, CEO of SensoDetect. "We are leveraging our vast, proprietary BERA database-an asset no competitor can replicate-to train AI models that deliver gold-standard accuracy with unprecedented practicality. This synergy directly translates into a faster commercial rollout, stronger IP protection, and a clear trajectory for market leadership."

Strategic Value and Next Steps

This advancement provides a dual benefit: it immediately enhances the value of SensoDetect's historical data and accelerates the ongoing validation of its core BERA technology. The company will now focus on integrating this AI software into its global commercial strategy, which is expected to significantly accelerate adoption rates and create new, high-value revenue streams through IP licensing.

References

1 Zaheer, A., & Akhtar, A. (2025). Artificial intelligence as a support to diagnose ADHD: An insight of unorthodox approaches: A scoping review. Child Neuropsychology.

2 Deepika, M., Sharma, S., & Arora, S. (2025). Redefining parameter-efficiency in ADHD diagnosis: A lightweight attention-driven Kolmogorov-Arnold network with reduced parameter complexity and a novel activation function. Psychiatry Research: Neuroimaging, 351, 112016.