Collective Intelligence Against Alzheimer's Disease

Alzheimer's disease is the leading cause of senile dementia and is extremely difficult to detect in its early stages. Existing diagnostic methods are often expensive and not always accurate, while remote hospitals do not always have the necessary specialists and equipment. BCFTL (Blockchain-enabled Multi-modal Federated Transfer Learning) – a blockchain-based multimodal federated transfer learning framework* – may be the solution.

Modern artificial intelligence can analyze vast amounts of medical information – clinical records, scan results, and other data – to identify subtle patterns that indicate the development of Alzheimer's disease. This new, unparalleled platform fully realizes this potential. The team behind the project included scientists from the University of Science and Technology of China, Hefei University of Technology, Shenyang Aerospace University (China), Korea University (South Korea), the University of Artificial Intelligence (UAE), and Togliatti State University.

"Let's say several hospitals want to teach artificial intelligence (AI) to recognize Alzheimer's disease. Each hospital trains its own AI model using its own patient data (MRI scans, tests). The data itself is not shared anywhere and remains within the hospital. This guarantees complete patient confidentiality," explains Alexey Shvetsov, one of the project's authors and project manager at the Regional Engineering Project Office of Togliatti State University. "The hospitals then send the 'accumulated knowledge' of their models (the AI's 'inferences', so to speak) to a central server. There, this knowledge is combined with data from other hospitals, creating a single, smarter and more accurate overall model."

The resulting model is fed back to each hospital, making the local AI even smarter. All transactions are recorded using blockchain technology, ensuring security and transparency, making it impossible to falsify results.

"Essentially, we've created not just a diagnostic tool, but a secure ecosystem for collaboration between medical institutions," comments Alexey Shvetsov. "Hospitals, especially in small towns, can pool their efforts to train a powerful AI model without directly sharing patient data. This is a breakthrough approach for telemedicine and remote diagnostics."

The platform's high efficiency has already been confirmed in experiments. The accuracy of Alzheimer's disease diagnosis was 97%. The system demonstrates high performance, processing up to 10 model updates per minute. The main practical application of this development is providing modern diagnostics to remote hospitals around the world. Now, with the BCFTL platform, they can accurately analyze their patient data, leveraging the collective experience of models trained at other institutions, and obtain reliable results for early treatment.

An article describing the research by an international team of scientists was published in the world's leading scientific journal IEEE Internet of Things Journal.

*A framework is a ready-made set of tools that helps a developer quickly create