Ethereum can be used for cancer research. Here’s how it works

Key points to remember

  • A medical team argued in a paper this year that blockchains were useful for cancer researchers to share information with each other for their AI systems.
  • According to the team, blockchains make it possible to simultaneously share the parameters of the AI ​​model among all collaborators without the help of a centralized coordinator.
  • The team specifically mentioned the use of smart contracts on Ethereum for this purpose.

Share this article

Ethereum smart contracts allowed three different teams of researchers to update their AI models simultaneously without going through a centralized authority. AI models themselves are used to predict the emergence of cancer cells in the body.

Decentralized data exchange

The Ethereum blockchain is used in the global fight against cancer.

A research article published in Nature Medicine in April, titled Swarm learning for decentralized artificial intelligence in cancer histopathology and written by 27 different contributors, noted in one of its footnotes, the team started using the Ethereum network for their cancer experiments.

According to the article, artificial intelligence (AI) can help predict the emergence of cancer cells in patients by extracting information about cell shape and size that is not visible to the human eye. The large datasets needed to operate such AI systems, however, face “practical, ethical and legal hurdles” from a data collection perspective, particularly if the data is shared between countries.

One way to solve this problem is to use federated learning (FL), which does not require researchers to share their data, only their locally trained AI model weights (or parameters). The problem is that such systems rely on a centralized coordinator who essentially combines all the weights of the model together and who then has complete control over the research project and its commercial exploitation.

Instead, the team pointed to the growing use of swarm learning (SL), a system that leverages blockchain technology to avoid ceding power to a centralized entity. In other words, SL allows teams to share the weights of their AI models while keeping all contributors at the same level, which facilitates collaboration between more parties and which, in turn, fuels AI models with more data, making them stronger.

The research team specifically states that they used smart contracts on Ethereum to have three separate computers synchronize their AI model weights at designated times. Indeed, the three partners had updated the AI ​​models simultaneously without requiring the assistance of a coordinator who would manually merge the model parameters. “In this configuration,” the document explains, “the blockchain maintains global state information about the model.” The research paper found that AI systems born from the configuration outperformed locally trained AI models and performed on par with other models trained with merged datasets (and that the technique was more efficient in data terms). As a healthcare professional AriGoldNFT Explain when they highlighted the article on Twitter, “a hospital in New York can communicate with a hospital in Los Angeles via nodes”.

This is important news for crypto in general and smart contract platforms in particular. So far, blockchains have proven to be extremely useful in the field of finance, but critics and enthusiasts have denounced the lack of adoption of the technology in other sectors. Vitalik Buterin, creator of Ethereum declared in August, this crypto was expected to “turn into something useful” within the next ten years. It would be hard to find a more worthy use case than for the medical field.

Disclaimer: At the time of writing this article, the author of this article owned BTC, ETH, and several other crypto assets.

Share this article

About Arla Lacy

Check Also

ALERIAN ENERGY INFRASTRUCTURE ETF REPORTS FOURTH QUARTER DISTRIBUTION OF $0.29618

DENVER, November 9, 2022 /PRNewswire/ — The Alerian Energy Infrastructure ETF (NYSE Arca: IN FR) …