The convergence of AI and Blockchain in Healthcare

Blockchain combined with Artificial Intelligence (AI) has the potential to revolutionize the field of healthcare in the next few years. Let’s look at each of these concepts first.

What is Artificial Intelligence (AI)?

Artificial Intelligence (AI) was originally introduced as a term to emulate the human brain and try to solve problems in the world using machines but with a holistic human approach. There have been several advancements in technology to satisfy our strong desire to augment the human brain. Big data brings the capacity to store large amounts of data and AI does a great job of processing and translating the data in an intelligent manner into consumable tools. A truly artificially intelligent system is one that learns on its own, one that’s capable of processing huge amounts of data and create associations and intelligently mimic actual human behavior.

The increased use of artificial intelligence and machine learning is disrupting the areas of medical research and treatment. These advanced technologies provide researchers access to tons of data via clinical studies and journals on several genetic disorders. This could potentially shorten the amount of time it takes to develop cures by analyzing of a lot of comprehensive data very quickly. AI can be used to generate insights which can assist in the discovery and clinical development of pharmaceutical medicine.

What are some use cases for AI in Healthcare?

Do you remember when we started using robotics in manufacturing? Well, in a similar fashion, AI is making its mark in healthcare by automating a few daily, repetitive tasks. Let’s look at the example of detecting cancer. We can leverage the power of deep learning, write algorithms and develop  models that can be trained to distinguish between sets of pixels in an image that represents cancer versus sets that don’t. At this point, AI technology can go through millions of medical images (X-Rays, MRIs, CT scans, etc.) in a single day to detect patterns and anomalies that normal humans just cannot do.

Additionally, these algorithms are constantly learning and evolving and getting better at making these associations with each new data set that gets ingested into the data stores. Pathology and radiology might see tangible benefits soon as technology companies will bring these deep learning algorithms to healthcare providers. In fact, some companies are already doing this. FDA recently approved an AI-powered medical imaging platform that helps doctors analyze and diagnose anomalies in the heart. This is the first time ever that the FDA has approved a machine learning application for use in clinical environments.

Now, let’s look at the practicality of using AI as opposed to normal human beings. We know that humans get distracted easily but computers don’t get bored or distracted. That, combined with immense compute and processing power, AI is exponentially better than us at analyzing data.

Let’s look at the example of IBM’s Watson. Watson could analyze genomic data from both tumor cells and healthy cells and was ultimately able to recommend actionable insights in a mere 10 minutes. The same data would have taken a human roughly 160 hours to analyze. Apart from diagnoses, AI is also being used in the pharmaceutical industry to help with extremely time-consuming monotonous work of discovering new drugs, and a lot of companies are jumping on the bandwagon.

Gartner recently predicted that by 2025, 50 percent of the population will rely on AI-powered virtual personal health assistants for their routine primary care needs. These virtual assistants (like Siri) would be out main interaction engines for out health devices and the machine learning algorithms would be working round the clock to analyze our biometric data. These assistants would tell us about current state of health, acting as a sort of medical informer and alert us when it’s time to see a physician.

With the amount of data generated and available to mankind today combined with the various advancements in technology, healthcare is transitioning from reacting to preventing and disrupting the way care is delivered. Artificial intelligence is and will be saving our lives for years to come.

Now, let’s see what Blockchain is all about.

So, what is Blockchain?

How do you make a transaction currently? By using trusted middleman like a bank, right? The difference with blockchain is that it allows consumers and suppliers to connect directly, eliminating the need for a third party. By using cryptography to keep the exchanges secure, blockchain provides a decentralized database or a “digital ledger” of transactions that everyone on the network can see. This network is basically nothing but a chain of computers that will each have to approve an exchange before it can be deemed to be verified and recorded.

Blockchain can best be described as a digital database, which, unlike a traditional database, is characterized by three main features: decentralization, immutability and transparency.

Decentralization

As a major deviation from centralized structures, a distributed ledger technology like blockchain exists in the form of a network: essentially a copy of the blockchain is located on each participating computer. This makes the data integrity extremely strong and resistant to hacking. For example, in the traditional financial world, the bank is the central authority that everyone must trust, in the world of blockchain, the bank can be eliminated. All cryptocurrencies (e.g. Bitcoin) function according to this principle. All transactions take place completely autonomously through the users and their end devices.

Immutability

Data can only be added to the blockchain, but it cannot be changed or deleted. All data remains in its original state. This makes every transaction visible to every user. You can change the access rights but that’s about it.

Transparency

All the users involved in a blockchain can view the data at any time without restriction by having the right privileges. This way transparency is established without any additional layer of software or authentication.

Now, let’s look at some of the applications of Blockchain in the Life Sciences field

The element of transparency appears to be highly misconstrued in the healthcare sector. However, transparency in this context does not mean that the patient is semi-transparent and unauthorized persons can view his data. In fact, it’s exactly the opposite. Blockchain has the potential to bring the healthcare sector much closer towards patient centralization.

The management of medical data in the form of digital patient records based on blockchain technology can make the patients have complete control of their own data. We know that there are public blockchains, such as those used to trade cryptocurrencies. But, there are also private blockchains that only permit access to those who have permission to access them. The possibility of storing data in external databases also exists with pointers (references) in the blockchain.

You can potentially store x-rays and CT scan images and medication histories in external databases with pointers in the blockchain. So, essentially, data is available on the computer systems in place at the relevant healthcare provider. An index will point to this data in the blockchain and manages the corresponding access rights. The patient can then decide who can access his data, and can access it at any time. This simplifies the cooperation between the different specialists treating the patients, and the storage and administration of their personal data.

Additionally, sensor and medical device data can be added to the blockchain and evaluated. Imagine the potential of an individual early warning system that can be created for the patient keeping him informed of his health status. In medical research, blockchain technology is also useful for managing the results of studies. The reliability of research results can be tracked objectively because it is transparent and secure from tampering. The question of who made the initial discovery can also be addressed in this manner, since all the data and transactions are transparent and immutable.

I strongly believe that blockchain can radically improve data sharing, data security, interoperability, patient engagement, health information exchange (HIE) and R&D. For example, in population health management, providers can use blockchain to progress in clinical research patient safety event reporting, adverse event identification, public health reporting and precision medicine.

So, how Blockchain and AI can work together for a better healthcare?

Technology is democratizing data and enabling real-time analytics for actionable insights. We can combine Blockchain and AI to analyze data sets that cannot be analyzed together due to regulations or data privacy concerns. Insights that were unaffordable due to a manual curation process will be made accessible by biotech companies, treatment centers and even patients.

We can use blockchain to keep the data decentralized. Imagine a world where patients don’t worry about sharing their behavioral data? Additionally, let’s say they are able to share their deeply personal medical data with pharmaceutical companies. This can be possible with blockchain since the data won’t reside with pharmaceutical companies but in immutable blocks. If they take part in a trial and the drug gets approval, patients can partake in the benefits instantly through smart contracts. Blockchain and AI could enable a structural shift where all parties share data in a decentralized fashion, wherein the system could still collectively use the data to make smart decisions. This could overthrow the legacy hurdles of healthcare i.e. data lying in different places, strong regulations restricting the sharing and analysis of that data, and weak incentives for sharing research and training data.

The future of healthcare is very bright. We can combine technologies like AI, Cognitive computing, machine learning and blockchain to look at much larger and diverse data sets. As with any emergent technology, blockchain’s use for healthcare data is a work in progress, but they have predicted that within five years, healthcare blockchain will be the new norm for the sector.