Blockchain and Deep Learning: A duo to Enhance Healthcare System?

By Nitin Kumar, Punit Agarwal, and Sukant Khurana

Ever wondered what happens when you combine Blockchain and Deep Learning?

Despite significant advancement in technology in different fields, health management and administrative systems leave a lot of room for improvement. At present, in most of the healthcare organization, the health record of a patient is stored manually which makes it harder to maintain such huge amount of data.

Why is it so hard to maintain this healthcare data accurately? First of all, these information changes all the time, doctors are constantly moving in and out of networks, they are constantly accepting new insurance coverage, they’re changing office locations and changing their affiliations with clinics and hospitals and the patient is diagnosed at various health organizations. So the information changes a lot. So unless that doctor is very good about contacting their networks every time one of those data fields changes which are going to fall out of sync very quickly. This process, of updating records manually, is not feasible as the records can be updated at each doctor’s as well as patient’s end. And this process results in violating patient’s privacy.

Now how can blockchain solve this ecosystem?

Blockchain Technology basically a transactional ledger, which records transactions shared by multiple parties. Blockchain promises to provide safe and interoperable sharing of real-time data between vendors, payers, and patients in the healthcare industry. The use of blockchain in healthcare is anticipated to reinvent the ecosystem in limitless methods to benefit the affected person and developments in redress results safety and costs. In impact, blockchain technological know-how has the plausible to seriously change healthcare shipping, placing the patient at the center of the healthcare ecosystems and the functionality to expand the security, privacy, and seamless interchange of healthcare data.

Blockchain offers synchronization which used to be the primary flaw in manual updating processes. Every time any modifications or update is made, it is created in shape of a block and once it gets consensus from the network, it will automatically update all the participants involved in the network.

Now how this all is achieved? The blockchain is a decentralized and distributed digital ledger that records transactions across many computers so that the record cannot be altered retroactively besides the altercation of all subsequent blocks. The Blockchain technology acts as a crucial way to streamline the sharing of medical documents in an invulnerable way to guard sufferers non-public records or privacy from hackers, insiders, and outsiders, and give patients more control over their information.

Blockchain in Healthcare reduces cost by eliminating manual processes like multiple isolated ledgers, administrative processes and it provides increased speed of transactions and settlement through immediate distribution with increased security.

Blockchain in Healthcare reduces fraud by means of sharing a common, unchangeable ledge throughout the network, and reduces the risk of single points of failure and attack through distributed network nodes.

The shift closer to electronic fitness information (EHR) has executed little to enhance the splintered nature of healthcare. Starting from birth, patients accumulate data from clinical encounters, wearable devices, etc…and each data upload adds a new block to their electronic health record. Records of the sorts of data collected (vaccination histories, pathology reports etc) are stored on the parent’s EHR. Each patient owns his or her own electronic health record and decides who can access their data.

Image: Bulletin | Blockchain: A primer for surgeons

Similarly, each institution can identify electronic health data and decide how to use institutional data. Data collected via non-public fitness and wellness, diagnostics, therapeutics, processes, smart gadgets, genetic testing, and other sources could all be securely integrated into a patient’s unique EHR, accessible to both patients and healthcare institutions. The EHR could be patient-controlled data and institutional-level data, every encrypted access keys for chosen sharing and get entry to levels. Every interaction is time-stamped and imutably added to the chain, adding to its intrinsic security.

Image: Bulletin | Blockchain: A primer for surgeons

Blockchain in Claims Adjudication and Patient Billing Management

The current existing patient billing management system is mainly manipulated by service providers — a high fraction of healthcare costs are resulting from immoderate billing or billing for non-carried out services. Blockchain systems would help eliminate the need for intermediaries — through automation of the majority of the declared arbitration and fee processing work. It can even reduce the time taken for a claim to be accepted from days to minutes, thereby making the process convenient.

Blockchain in Drug Supply Chain Integrity

Another complexity that the existing healthcare system is facing is of drug supply. According to Forbes, “Blockchain-based supply chain systems could ensure a chain-of-custody log, with the ability to track each step of the supply chain at the individual drug/product level.”

Moreover, extra add-on functionalities such as non-public keys and smart contracts ought to assist to construct the proof of ownership between exclusive parties.

“In the recent articles covering efforts in the investigation of the world counterfeit drug menace — it led to the seizure of counterfeit drugs valued at $74 million (Aboody & Lev, 2000), and on a large scale, an estimated annual loss of $200 million for pharmaceutical companies due to counterfeit drugs (Danzon, 1998).”

“The World Health Organization (WHO, 2010) estimates worldwide sales of counterfeit medicines to $75 billion in 2010, a 90% rise in five years”

“According to Statista (2016), the size of the blockchain technology market worldwide from 2017 to 2021 will be expected to grow to 2.3 billion U.S. dollars by 2021 from 339.5 million U.S. dollars in 2017. These estimated forecasts are based on an annual constant growth rate of 61.5%.”

How could Machine Learning or Artificial Intelligence help in Healthcare?

Faster medical treatment saves lives. Machine Learning or Artificial Intelligence (AI) can help in saving lives by scouring a multitude of patient’s data and evaluating them to one patient’s health records to detect signs and symptoms 10 to 12 hours earlier than a doctor ought to. In many pressing medical problems, the answer to knowing whom to treat, when to treat, and to treat with, might already be in patient’s data. Machine learning applied to electronic health records (EHRs) can generate actionable insights, from enhancing patient hazard score structure to predicting the onset of disease, to aerodynamic hospital operations.

“Brain Informatics using deep learning makes use of mental health condition of soldiers to analyze the changes in the brain activities during the rise and fall of workload on a soldier and then the usage of cognitive strategies expand the performance of the soldiers.”

Electronic health records (EHRs) hold the clinical background of patients and could be analyzed to perceive the person chance of developing cardiovascular diseases. Recurrent neural networks (RNNs), which are commonly suitable for sequence evaluation, are one of the most promising tools for text or time-series analysis. And one of the most effective applications of RNNs in healthcare is digital scientific report analysis. Recently, RNNs had been used to predict heart failure of sufferers based on clinical activities in their records.

Image: Oncotarget | Converging Blockchain and artificial intelligence technology

Machine Learning or AI can be used to analyze data, and loop it back in real time to physicians to support them in making the proper decision in medical. The patient’s treatment data which includes symptoms, disease, medicines provided can be stored and further analyzed and used to train machine so that next time a physician sees a patient and enters symptoms, data, and test results, there’s machine learning behind the scenes looking at everything about the patient, and prompting the medical doctor with beneficial information for making a prognosis ordering a test, or suggesting a preventive screening.

So what happens when you combine Blockchain and Machine Learning?

The blockchain is a decentralized peer-to-peer ledger that records and shares transactions, providing security and interoperability for healthcare carriers and their patients. The massive amount of data like each patient visit, diagnosis, prescribed treatment, outcome and other key data are stored in EHRs. To handle this massive data some data manipulation technique is required, nowhere the AI or Machine Learning comes into the picture. AI can be used to analyze and manipulate this data and train himself, learn from the patterns in the data.

When Machine Learning and Blockchain converge, the patients can be benefitted from AI’s ability to accelerate the analysis of the enormous amount of data. By using ML and AI to govern the chain, there’s also an opportunity to significantly enhance security.

“Project Shivom works as an ecosystem that provides an open web-marketplace for other companies to add their apps and services, alongside genomic data analytics and personalized medicine. All this is based on the Blockchain-enabled platform”

Apps built on a blockchain can make data organized, secured and easily accessible, while artificial intelligence makes it viable to draw out intelligent and valuable insights from giant amounts of data that no human could ever analyze.


Blockchain and AI — these two technologies go really well together but no one’s really put them together yet. So both technically speaking and morally speaking creating what is called decentralized applications is a really good idea and it’s what we call as developers web 3.0, if you’re looking for something to disrupt you take blockchain take AI you combine it together and you create apps that have never before been possible.


1. Bitcoin. All-time transactions. Accessed October 30, 2017.

2. Inglis J. Docs now taking payment by Bitcoin: Lower transaction costs, increased privacy protections lead some practices to accept controversial e-currency. Accessed August 4, 2017.

3. Oncotarget. 2018 | Converging blockchain and next-generation artificial intelligence technologies to decentralize and accelerate biomedical research and healthcare.[]=22345&path[]=70701

4. Nakamoto S. Bitcoin: A peer-to-peer electronic cash system. Available at: Accessed August 4, 2017.

5. Bulletin. December 6, 2017 Blockchain technology in healthcare: A primer for surgeons.

6. McFarlane C. Patientory: A health care peer-to-peer EMR storage network v1.0. Available at: Accessed August 4, 2017.

7. Earnest MA, Ross SE, Wittevrongel L, Moore LA, Lin CT. Use of a patient-accessible electronic medical record in a practice for congestive heart failure: patient and physician experiences. J Am Med Inform Assoc. 2004; 11:410–17.

8. Peter Nichol. Researchgate Publication 306012906. Micro-Identities Improve Healthcare Interoperability with Blockchain Deterministic Methods for Connecting Patient Data to Uniform Patient Identifiers.

9. State of Blockchain and Artificial Intelligence in Fintech

10. IBM’s New Watson Centre Merges Blockchain with AI

— — — — — — — — — — —

— — -

Dr. Sukant Khurana runs an academic research lab and several tech companies. He is also a known artist, author, and speaker. You can learn more about Sukant at or and if you wish to work on blockchain, biomedical research, neuroscience, sustainable development, artificial intelligence or data science projects for public good, you can contact him at or by reaching out to him on linkedin

Here are two small documentaries on Sukant and a TEDx video on his citizen science effort.

This story is published in The Startup, Medium’s largest entrepreneurship publication followed by 318,583+ people.

Subscribe to receive our top stories here.