Combining AI and Blockchain to Push Frontiers in Healthcare

David Campbell | March 16, 2018 | 6 Min Read

AI and blockchain are two technology trends that have each individually demonstrated their potential to impact the healthcare industry, but what about their impact when used in combination? In his second piece on the use of blockchain in healthcare, Senior Developer at Macadamian, David Campbell, illustrates how these technologies could possibly be used together to benefit population health and change our daily lives.

AI and blockchain are two technology trends that have each individually demonstrated their potential to impact the healthcare industry, but what about their impact when used in combination? In his second piece on the use of blockchain in healthcare, Senior Developer at Macadamian, David Campbell, illustrates how these technologies could possibly be used together to benefit population health and change our daily lives.

The Potential of AI in Healthcare

Artificial Intelligence (AI) will revolutionize healthcare. Its potential is massive and it is our responsibility to harness its power to maximize its benefits. Think about how useful it would be if you could get an alert on your phone every time you entered a region where you were at a greater risk of catching the flu. Or if a doctor could compile a list of conditions that you were susceptible to based on your medical records cross-referenced with general medical trends. AI can make this happen.

How can we turn this vision into a reality? What barriers are preventing us from using AI to its full potential in the healthcare industry? For AI to be successful in any field, a large amount of data must be collected and analyzed. In healthcare, data collection, transportation, and storage present some complex privacy, integrity, and availability challenges that must be addressed before AI can play a full role.

You Might Also Like: Artificial Intelligence and the Future of Patient-Centered Care.

Finding data sources is another major hurdle, but with the advent of consumer Internet of Things (IoT) devices, raw data is increasingly available. AI algorithms can use anonymized data from these devices to show general population health trends, but the challenge is mining the huge amounts of raw data for useful information with a finite amount of computing power. Granular computing promises to mitigate large data issues, which can be achieved through a combination of IoT edge computing and traditional server/cloud processing. I will expand on this in future articles.

Enter Blockchain

Another source of medical data is a healthcare blockchain. As I mentioned in my introductory article on blockchain in healthcare, blockchains are becoming more prevalent in the medical domain because they store transactions in a network of distributed servers, which offers a high degree of availability. This adds protection against network outages and hardware failure. Also, the format of the transactions is stored in such a way that makes it almost impossible to tamper with the data. Data integrity and accountability are paramount to any healthcare solution.

While the quantity of data does not approach the amount of raw data that can be collected by medical devices, the data received by a medical blockchain is richer. Specifically, the data collected from smart contract transactions can have immense value if we broaden the scope of a smart contract.

In cryptocurrency, a smart contract is a piece of code that enforces rules concerning value passed between two or more agents. An agent, in the cryptocurrency context, is an account or a virtual wallet; in the medical space, the agent and value construct can be expanded. If we start changing the meaning of agent and value, the name “smart contract” becomes too limited to describe these interactions. A term like “relationship rules” would be more apt.

In the pharmaceutical field, we can think of a drug as the equivalent of “value” in cryptocurrency. A pharmaceutical blockchain can be used to track and control the distribution of drugs between “agents” such as pharmaceutical manufacturing, distribution nodes, pharmacies, and patients. This sort of control is very important for tracking dangerous drugs such as opioids. The example of using drugs as value and agents as owners mirrors cryptocurrency, but we can redefine value as “relationship” and agent as something more abstract. An example of this is if a doctor schedules surgery for a patient, the agents involved with the smart contract would be the patient, the doctor, and the medical procedure.

You Might Also Like: Exploring Blockchain Technology in Healthcare.

Converging AI and Blockchain to Revolutionize Healthcare

Using a blockchain solution in an Electronic Health Record (EHR) system allows for the creation of transactions between entities such as patients and medical conditions. In this case, we can think of a diagnosis of a condition as a transaction between a patient and a known condition. Not only can we store this information as a distributed immutable transaction in a patient record, but also to record the relationship. By updating a patient record using transactions between entities, a graph database can be constructed.

A graph database is a way of storing unstructured data and the relationships amongst the data. For example, if a physician prescribed a drug to a patient, the patient, the doctor, and the drug would be stored along with the relationships amongst the pieces of data. The relationship between the doctor and the patient would be regular doctor/patient or it could be specialist/patient. The relationship between the drug and the doctor would be prescriber. In a graph database, the actual data is stored as something called a “node” and the relationship between the nodes are called “edges”.

If smart contracts can describe relationships between participants of the contract, they can be used to build a graph database. The graph database can show latent variables, which is information hidden within the data. One example of a machine learning algorithm that uses graph database to extract and use latent variables is a Bayesian network. A Bayesian network is a graph database built on relationships of cause and effect.

The strength of a Bayesian network is its ability to determine probabilities. When applied to general population health data, it can help make powerful predictions and correlations between seemingly unrelated pieces of information. Given patient “x”, what is the probability of having condition “y”?

For example, smoking has an elevated probability of causing lung cancer. AI can mine data surrounding this relationship from a general graph database using various algorithms. The resulting Bayesian network can be used as a model to predict diagnosis based on the medical history of a patient. I will cover this in more detail in future articles.

The medical graph database has power on its own. By examining the relationships, we can discover some interesting connections. The most common factor between entities (nodes) can be determined simply by finding the largest number of common connections (edges). If a population is suffering from condition “x” and the largest shared connection is prescription to drug “y”, it would be reasonable to investigate whether drug “y” has a side effect that causes or contributes to condition “x”.

This article only scratches the surface of how AI and blockchain can work together to revolutionize healthcare, so stay tuned for more. The obstacles are real, but the potential to transform our daily lives is huge.

Get Email Updates

Get updates and be the first to know when we publish new blog posts, whitepapers, guides, webinars and more!

Suggested Stories

Health Information System Integration

In this webinar, we discuss interoperability in healthcare and answer attendee questions on Health Information System integration. Download the webinar Now.

Read More

How to Design and Develop the Right Healthcare Software Solution

This guide shares our knowledge and insights from years of designing and developing software for the healthcare space. Focusing on your user, choosing the right technology, and the regulatory environment you face will play a critical role in the success of your application.

Read More

Accelerate Time To Market Using Rapid Prototyping

In this webinar, you will learn how to leverage rapid prototyping to accelerate your products time to market in one week, agile sprints.

Read More