Try : Insurtech, Application Development










Dev Ops(2)

Enterprise Solution(22)




Augmented Reality(17)

Customer Journey(12)


User Experience(34)

AI in Insurance(31)


Product Innovation(37)





Telehealth Care(1)


Artificial Intelligence(109)



Cognitive Computing(7)

Computer Vision(8)

Data Science(14)


Intelligent Automation(26)

Machine Learning(46)

Natural Language Processing(13)

How can Artificial Intelligence settle Insurance Claims in five minutes?

Originally published on medium.com

If you’ve ever been in the position of having to file an insurance claim, you would agree that it isn’t the most pleasant experience that you’ve likely ever encountered.

In fact, according to J.D. Power’s 2018 Insurance Customer Satisfaction Studymanaging time expectations is the key driver of satisfaction — meaning, a prompt claim settlement is still the best advertisable punch line for insurance firms. Time-to-settle satisfaction ratings were found to be 1.9 points lower even when the time frame was relatively short and insurers still missed customer timing expectations.

So what should an established insurance company do, to be at par with the customer’s desires of modern service standards? The question becomes even more pertinent when the insurance sector is still lagging behind consumer internet giants like Amazon, Uber who are creating newer levels of customer expectation. Lemonade, MetroMile and others are already taking significant market share away from traditional insurance carriers by facilitating experiences that were previously unheard of in the insurance trade.

Today, Lemonade contends that with AI, it has settled a claim in just 3 seconds! While a new era of claims settlement benchmarks are being set with AI, the industry is shifting their attitude towards embracing the real potential of intelligent technologies that can shave-off valuable time and money from the firm’s bottom-line.

How AI integrates across the Insurance Claims Life Cycle

For this entire process to materialize — from the customer filling out the claim information online, to receiving the amount in a bank account within a short amount of time, and have the entire process be completely automated without any interference, bias, or the whims of human prejudice.

How does this come about? How does a system understand large volumes of information that requires subjective, human-like interpretation?

The answer lies within the cognitive abilities of AI systems.

For some insurers the thought that readily comes to mind is — Surely, it must be quite difficult to achieve this in real-world scenarios. Well, the answer is — NO, it isn’t!

Indeed, there are numerous examples of real-world cases that have already been implemented or are presently in use. To understand how these systems work, we need to break down the entire process into multiple steps, and see how each step is using AI and then passing over the control to the next step for further processing.

How It Works
For the AI-enabled health insurance claims cycle, there are a few distinct steps in the entire process.

Analysis and abstraction

The following information is first extracted from medical documents (diagnosis reports, admission & discharge summaries etc.)

  1. Cause, manifestation, location, severity, encounter, and type of injury or disease — along with & related ICD Codes for injury or disease in textual format.
  2. CPT Codes — procedures or service performed on a patient, are also extracted.

There are in essence two different systems. The first one (described above) processes the information that is presented to it, while the other looks from the angle of genuineness of the information. The latter is the fraud detection system (Fraud, Abuse & Wastage Analyzer) that goes into critical examination of claim documents from the fraud, abuse and wastage perspective.

Fraud, Abuse & Wastage Analyzer

Insurance companies audit about 10% of their total claims. Out of which around 4–5% are found to be illegitimate. But the problem is that the results of these audit findings are available much after the claim has been settled, following which recovering back the money already paid for unsustainable claims is not that easy.

This means that companies are losing big sums on fraudulent claims. But is there a way by which insurers can sniff out fraud in real time while the claim is under processing?

With Cognitive AI technologies available today, this is achievable. All you need is a system that analyses hundreds and thousands of combinations of symptoms, diagnoses and comes up with possible suggested treatments. The suggestions are based on the learnings from past instances of cases that has been exposed to the AI system.

The suggested treatments’ tentative cost — based on the location, hospital, etc., is compared with the actual cost of the treatment. If the difference suggests an anomaly, then the case is flagged for review.

Automated processing of medical invoices

Now if your Fraud Analyzer finds no problem with a claim, how can you expedite its processing? Processing requires gathering information from all medical invoices, categorizing them into benefit buckets, and then finalizing the amount allowed under each head. Advanced systems can automate this entire process, ruling out manual intervention in most of these cases.

Recent AI systems have the capability of extracting line items from a scanned medical invoice image. This is achieved through a multistep process, outlined below.

  1. Localizing text on the medical invoice. This gives the bounding boxes around all texts.
  2. Running all localized boxes against a Scene Text Decoder trained using a LSTM and a Sequence Neural network.
  3. Applying Levenshtein Distance Correction for better accuracy.
  4. Mapping each line item against an insurer specific category.

Each line item is iterated over and looked up against the policy limits to get its upper limit. Each line item amount is aggregated to finally get the final settlement amount.

If the final settlement amount is within the limits set for straight through processing and no flags are raised by the Fraud, Abuse & Wastage Analyzer, then the claim is sent to billing for processing.

Moving Ahead With AI Enabled Claims
Today, AI transforms the insurance claims cycle with greater accuracy, speed and productivity, at a fraction of the cost (in the long run) — while delivering enhanced decision making capabilities and a superior experience in customer service. While, in the past, these innovations were overlooked and undervalued for the impact they produced — the insurers of today need to identify the proper use cases that match their organization’s needs and the significant value they can deliver to the customers of tomorrow. The cardinal rule is to — start small through feasible pilots, that will first bring lost dividends back into the organization.


Knowledge thats worth delivered in your inbox

Implementing a Clean Architecture with Nest.JS

4 minutes read

This article is for enthusiasts who strive to write clean, scalable, and more importantly refactorable code. It will give an idea about how Nest.JS can help us write clean code and what underlying architecture it uses.

Implementing a clean architecture with Nest.JS will require us to first comprehend what this framework is and how it works.

What is Nest.JS?

Nest or Nest.JS is a framework for building efficient, scalable Node.js applications (server-side) built with TypeScript. It uses Express or Fastify and allows a level of abstraction to enable developers to use an ample amount of modules (third-party) within their code.

Let’s dig deeper into what is this clean architecture all about. 

Well, you all might have used or at least heard of MVC architecture. MVC stands for Model, View, Controller. The idea behind this is to separate our project structure into 3 different sections.

1. Model: It will contain the Object file which maps with Relation/Documents in the DB.

2. Controller: It is the request handler and is responsible for the business logic implementation and all the data manipulation.

3. View: This part will contain files that are concerned with the displaying of the data, either HTML files or some templating engine files.

To create a model, we need some kind of ORM/ODM tool/module/library to build it with. For instance, if you directly use the module, let’s say ‘sequelize’, and then use the same to implement login in your controller and make your core business logic dependent upon the ‘sequelize’. Now, down the line, let’s say after 10 years, there is a better tool in the market that you want to use, but as soon as you replace sequelize with it, you will have to change lots of lines of code to prevent it from breaking. Also, you’ll have to test all the features once again to check if it’s deployed successfully or not which may waste valuable time and resource as well. To overcome this challenge, we can use the last principle of SOLID which is the Dependency Inversion Principle, and a technique called dependency injection to avoid such a mess.

Still confused? Let me explain in detail.

So, what Dependency Inversion Principle says in simple words is, you create your core business logic and then build dependency around it. In other words, free your core logic and business rules from any kind of dependency and modify the outer layers in such a way that they are dependent on your core logic instead of your logic dependent on this. That’s what clean architecture is. It takes out the dependency from your core business logic and builds the system around it in such a way that they seem to be dependent on it rather than it being dependent on them.

Let’s try to understand this with the below diagram.

Source: Clean Architecture Cone 

You can see that we have divided our architecture into 4 layers:

1. Entities: At its core, entities are the models(Enterprise rules) that define your enterprise rules and tell what the application is about. This layer will hardly change over time and is usually abstract and not accessible directly. For eg., every application has a ‘user’. What all fields the user should store, their types, and relations with other entities will comprise an Entity.

2. Use cases: It tells us how can we implement the enterprise rules. Let’s take the example of the user again. Now we know what data to be operated upon, the use case tells us how to operate upon this data, like the user will have a password that needs to be encrypted, the user needs to be created, and the password can be changed at any given point of time, etc.

3. Controllers/Gateways: These are channels that help us to implement the use cases using external tools and libraries using dependency injection.

4. External Tools: All the tools and libraries we use to build our logic will come under this layer eg. ORM, Emailer, Encryption, etc.

The tools we use will be depending upon how we channel them to use cases and in turn, use cases will depend upon the entities which is the core of our business. This way we have inverted the dependency from outwards to inwards. That’s what the Dependency Inversion Principal of SOLID implies.

Okay, by now, you got the gist of Nest.JS and understood how clean architecture works. Now the question arises, how these two are related?  

Let’s try to understand what are the 3 building blocks of Nest.JS and what each of them does.

  1. Modules: Nest.JS is structured in such a way that we can treat each feature as a module. For eg., anything which is linked with the User such as models, controllers, DTOs, interfaces, etc., can be separated as a module. A module has a controller and a bunch of providers which are injectible functionalities like services, orm, emailer, etc.
  1. Controllers: Controllers in Nest.JS are interfaces between the network and your logic. They are used to handle requests and return responses to the client side of the application (for example, call to the API).
  1. Providers (Services): Providers are injectable services/functionalities which we can inject into controllers and other providers to provide flexibility and extra functionality. They abstract any form of complexity and logic.

To summarize,

  • We have controllers that act as interfaces (3rd layer of clean architecture)
  • We have providers which can be injected to provide functionality (4th layer of clean architecture: DB, Devices, etc.)
  • We can also create services and repositories to define our use case (2nd Layer)
  • We can define our entities using DB providers (1st Layer)


Nest.JS is a powerful Node.JS framework and the most well-known typescript available today. Now that you’ve got the lowdown on this framework, you must be wondering if we can use it to build a project structure with a clean architecture. Well, the answer is -Yes! Absolutely. How? I’ll explain in the next series of this article. 

Till then, Stay tuned!

About the Author:

Junaid Bhat is currently working as a Tech Lead in Mantra Labs. He is a tech enthusiast striving to become a better engineer every day by following industry standards and aligned towards a more structured approach to problem-solving. 

Read our latest blog: Golang-Beego Framework and its Applications


Knowledge thats worth delivered in your inbox

Loading More Posts ...
Go Top