When we consider how far medicine has developed globally in the past century, it could be easy to become self-satisfied and assume that we have advanced our treatment methods and proficiencies as far as possible. However, a 2016 study exposed some quite shocking statistics regarding healthcare mistakes; namely, that 250,000 US citizens were killed every year from medical errors, such as misdiagnosis or incorrect dosage administration by healthcare professionals. This technically puts it at the third largest killer in the US, behind heart disease and cancer. Estimates of the economic costs of these mistakes reach up to $20.8 bln annually. With human error being one of the chief causes of medical mistakes, the healthcare industry is now able to turn to artificial intelligence (AI) for help.
A key player in advancing the use of AI in healthcare is Skychain, a project which aims to use Blockchain to train and use AI systems in medical care. Their white paper states that they aim to control 70 percent of the projected $200 bln medical AI market (estimated by IBM), through their ‘distributed open network’ system of artificial neural networks (ANNs), which can diagnose patients and prescribe the relevant treatments. They aim to “provide an opportunity to engineer, teach and host neural networks and provide paid access for independent specialists and organizations.” By using smart contracts, they hope to unite many individual parties (healthcare big data providers, independent AI developers, crypto miners and the consumers– doctors and patients) to create one effective solution.
Developers can submit ready-made ANN templates for doctors to choose from when diagnosing a patient. Once the networks have examined the data and returned the diagnosis information to the doctor, the developers and miners who provided the computing power will receive financial recompense.
Setting up these interdependent relationships will involve medical institution laboratories with large datasets, looking to set up and train their own neural networks (which can then also be used by others). They can offer these datasets for ANN training by developers. These developers can use a ‘SkyConstructor’ interface, and using a ready-made ANN template can edit it to meet the requirements of the institution once uploaded into Skychain. Once the ANN has completed the learning process, it can be published. Skychain uses the analogy of the wildly popular Uber taxi service: ANN developers are the drivers, doctors and patients the passengers, and the computer and servers of miners the cars.
The ICO will begin on Feb. 26 2018, with a total sale of 36 mln Skychain tokens (SCH) available, at one SCH = $1. They will be continuing their campaign by presenting at various conferences around the world, including Blockchain conferences in India and Russia. According to their roadmap, by June 2018 “the Skychain infrastructure is fully built, and early participants connect to it: healthcare data providers, medical AI developers, and hospitals.” They aim to be fully established by June 2019 and become “the leader in the medical AI market.”
The team behind Skychain boast an impressive display of experience. Founder Genendy Popov has over a decade of experience in programming and extensive education in computing, and Chief Technology Officer Ivan Svistunov has vast experience as a software architect within Blockchain.
Skychain claims their mission is to save 10 mln lives from error-related deaths within a decade. Ahead of the full launch, the Skychain team has created a model of the system, along with its source code. There is also a video demonstrating the system, for those who wish to learn more.
Skychain also ran a demo of their AI diagnostics system on Feb. 20th, comparing it to face-to-face doctors. Both attempted to diagnose melanoma, breast cancer and heart disease, and the team claims that there were instances of higher accuracy with the AI system. The team has provided a video of the demonstration. If the results can be verified this will be an enormously exciting step forward in healthcare diagnostics.