How Chatbot Can Make an Efficient Patient Support System

 Healthcare is one of those industries that embrace cutting-edge technologies and makes the most of them. The reason for this is simple – new technologies that help save people’s lives and increase the quality of life. 

The adoption of machine learning and natural language processing algorithms throughout the healthcare industry has helped to streamline and vastly improve workflows of different medical procedures, and as a result, has made them more effective for their causes. 

Some of the most prominent examples of such streamlining and improvements are patient support systems. Let’s explain why. 

What’s wrong with patient support?

The word that best describes the state of patient support in the healthcare industry is “overwhelming”. Unlike other fields of the healthcare industry, where the root of the problem lies in the methodology, in the case of patient support it is the scope of the operation. In other words, too much demand and too little supply. 

Just like regular customer support everywhere else, the primary issues are:

  • Workflow efficiency. Because of limited resources, there is a tendency towards bottlenecks in the support pipeline. This prolongs the processing of the request and subsequently stretches out the reply time for a single request. As a result, the request processing pipeline is severely undercut. 
  • Workforce turnaround. Due to the high workload and punishing schedules, support operators often burn out and quit. 
  • Availability of the service. It is hard to maintain a fully-fledged 24/7 support service, beyond simple Q&A automation, with a limited workforce. 
  • Bringing onboard new employees takes time.
  • Operational costs. In addition to employee salaries, there are infrastructural maintenance costs. 

In one way or another, these issues are solved with process automation and adoption of Chatbot and Natural Language Processing. 

NLP Chatbot creates a win-win situation, both for healthcare service providers, and patients.

  • Companies are able to optimize the workflow;
  • Chatbot reduces the workload of the human operators while making the service available 24/7.
  • Patients get a much more engaging and efficient service.

Here’s how:

  • Conversational UI chatbots take over the majority of routine conversations, such as results notification and Q&A. Human operators are involved only in special cases;
  • Natural Language Processing provides a deeper dive into the intent and sentiment of the user’s requests; 
  • This information gives ground for process automation that increases the speed of delivery up to 40%;
  • The implementation of the conversational interface chatbot lowers the operational costs up to 30%. 

Our company was approached to develop such a solution and implement it into the existing system infrastructure. Let’s look at how The App Solutions developed a Chatbot solution for Healthcare patient support. 

How Chatbot can create a more efficient patient support system?

The client had a patient support system that handled a wide scope of patient requests such as: 

  • Providing various notifications – like test results, examination registering, etc;
  • Solving emerging issues – for example, retrieving lost passwords or explaining how to use different features of the service;
  • Gathering user feedback on the support service itself, and other services of the company. 

The entire operation was handled by trained human operators who worked under a strictly regulated set of guidelines. 

And while the workflow was fine-tuned, it wasn’t sufficient enough for the scope of the operation. With over a million active users, the patient support system resources were stretched too thin. 

In addition to this, there were concerns regarding the use of sensitive information and the possibility of compromising the integrity of the users’ accounts.

Because of this, it was decided to completely overhaul the patient support system with cutting edge technologies. 

Our task on the project can be described as follows: to develop a reliable solution that would: 

  • Streamline the workflow of the customer support operation;
  • Keep sensitive information safe.

The key requirements were to:

  • Implement a chatbot and enable 24/7 support;
  • Implement process automation for basic conversations and actions;
  • Increase the request resolution time;
  • Deploy the system on the cloud platform and make it more scalable for large scale data processing;
  • Keep the system fully compliant with the current privacy regulations.

Here’s how it went down:

Training a language model

Process automation and Chatbot interface require a pitch-perfect understanding of the request intent and subsequent trigger of the course of action. The former part is handled by the NLP language model. 

We have used a combination of Word2Vec and Doc2Vec to train the model and optimize the generative algorithm. 

Example of Doc2Vec mechanism

[Example of Doc2Vec mechanism]

Example of Word2Vec mechanism

[Example of Word2Vec mechanism]

Due to the specifics of the healthcare topic, the use of the open-source datasets is somewhat limited. They can be used to provide a groundwork for the model, but further training and optimization requires more peculiar data taken directly from the system.  

In order to train a language model on the best fitting dataset – we compiled it ourselves from patient support conversations. We used unsupervised machine learning algorithms to explore patient support data and then applied supervised machine learning algorithms to shape it into a training dataset.

Optimizing chatbot

The chatbot was the main system component. With a language model intact – our goal was to construct the interface around it. 

The model was developed with Python NLTK and Chatterbot library. After that, it was migrated to the web interface with Flask API.

We implemented a couple of machine learning algorithms to determine the intent of the request and connected it with relevant actions. For example, if the patient asks about doctor working hours – the bot accesses the doctor’s calendar and provides the relevant information. 

The main challenge at this stage was making the interface accessible. Since the level of technical literacy of the users may vary – we needed to make the whole thing as simple to use as possible. 

In order to do this, we applied extensive A/B testing of the functional elements. This allowed us to streamline the interface design and also optimize the conversation design.

Implementing process automation with machine learning

After developing a working language model and constructing a conversational UI chatbot around it, our next step was to prepare the process automation routines that would be activated from the chatbot interface. 

In order to do that, we broke the task into three categories:

  • Service support automation – the ones related to the services themselves (such as booking an examination or requesting test results).
  • Maintenance automation – related to system support and general information (for example, how to retrieve a lost password or to proceed with checkout)
  • Switch to human operator scenario – for complicated or emergency cases

We identified keywords and intentions for action triggers with TF-IDF. 

In order to broaden the scope of the model, we combined them with a wide selection of phrase variations so that the routine would be activated through casually formulated input queries. 

Cloud Deployment 

In order to secure consistent system performance, we deployed the entire project into the cloud platform. 

In this way, the patient support chatbot can maintain a high turnaround of information in the system, and a large volume of different operations, without slowing down or experiencing technical issues. 

Google Cloud Platform autoscaling features provided a solid backbone for every operation in the system and neutralized possible emergence of the scalability issues. 

Implementing Data Security solution 

Privacy and confidentiality are amongst the central concepts of healthcare services. In the case of patient support systems, this is one of the most important elements. Not only do you need to guarantee the security of data in general, but you also need to guarantee that the whole interaction between the service and the patient is absolutely confidential.

The whole data processing operation must be compliant with the Personal Information Protection and Electronic Documents Act (PIPEDA). 

In order to maintain PIPEDA compliance, we implemented the following solutions:

  • Provided a detailed description of how user personal data is used on the service;
  • Expanded a consent agreement for data processing upon registration;
  • Limited retention of data from deleted accounts to 30 days after termination.
  • Implemented Transport Layer Security (TLS) with a 256-bit Advanced Encryption Standard for data transit.

Tech Stack

  • Google Cloud Platform
  • NLTK for Python
  • Chatterbot library
  • Flask API
  • Word2Vec / Doc2Vec


The project reinvigorated the company’s patient support. 

  • The implementation of the chatbot interface cut operational costs in half. 
  • The NLP component increased the efficiency and availability of the service. As a result, the response time period was decreased by a third. 
  • The process automation allowed to streamline the service’s workflow and minimize the role of human operators in the handling of sensitive data. 

On the other hand, this project was a huge accomplishment for our team. We developed a complex solution that managed to bring the whole patient support system to a new level with a much higher efficiency rate. 

During the development of this project, we utilized more streamlined workflows that allowed us to make the whole turnaround much faster. Because of this, we managed to deploy an operating prototype of the system ahead of the planned date and dedicated more time to its testing and refinement. 

Have a project in mind?

Write to us

What is the best way to create a chatbot: Platform vs. Custom

Chatbot integration with a website or mobile app is a win-win strategy for both your business and your clients. Why? Firstly, thanks to various use cases, chatbots can increase revenue by up to 25%, lead generation to 9.5%, and improve engagement with clients by 35%. Secondly, your customers receive a better UX experience of finding and ordering goods or services, paying for them seamlessly, and more. Are you ready to integrate a Chabot into your business strategy? Great! But the question is, “Whether to build a custom-made Chabot or use a Chabot building platform”?

Let’s find out. 

Below, we have gathered the main chatbot types, their usages, and a comparison of custom vs. platform-build chatbots. After reading this article, you will know exactly what kind of chatbot you need. Depending on its type, you will know whether you need a custom chatbot or platform-build solution. 

Main types of chatbots

A chatbot is a computer app that mimics human behavior during a conversation with a real person. But, the degree of chatbot’s humanity depends on the complexity of the technologies behind the app. Now, let’s look at the Chabot types in more detail:

Type 1: Scripted/Quick Reply Bots

Scripted is the simplest type of chatbot. Such chatbots are powered with decision three hierarchy and communicate with people using predefined scripts via a set of questions or buttons. Such scripted chatbots are the slowest medium of getting the user to their desired value. 

Burberry scripted bot

[Burberry scripted chatbot] 

Type 2: AI Chatbots

AI chatbots are more complex than scripted chatbots and include two subdivisions: 

  • Chatbots with Natural Language Processing 
  • Content Enable Chatbots with Machine Learning 

Now, we will take a closer look at these types:

Natural Language Processing (NLP) chatbots can understand, analyze, and prioritize questions according to their complexity. NLP chatbots are programmed to recognize particular keywords. Then, such chatbots respond appropriately with a non-pre-scripted response. More advanced NLP can even understand your message intensity, i.e., whether you are asking a question or make a statement.

Booking chatbot

[ NLP chatbot]

Content Enable Chatbots. Powered by Machine Learning (ML) and Artificial Intelligence, Content Enable chatbots are the more advanced type. ML chatbots learn from conversations that happened in the past with a specific user and grow over time. Examples of such chatbots are Siri, Alexa, and AI versus, created and taught by our team, ISD GmbH, and Hoskhod agency. To learn more about this project, read the full case study.  

Now, let’s look at how you can use a chatbot for your business. 

Chatbot use cases

You can use live chats and chatbots for multiple business areas, including customer support, streamlined payment, shopping assistants, and even healthcare assistants. Many marketers agree that such chat options are here to stay as automation continues to make advances. Now, chatbots can cover the following usages: 

FAQ assistants

Chatbots, in most cases scripted, can perform as live FAQ and process over 80% of support queries. It means that the customer can ask them questions and receive an answer. But, to create such a chatbot, you need something more than integrating FAQ section materials into a chat interface. FAQ chatbots should also be able to ask follow-up questions and connect the user with a real person if needed. 

Such chatbots are used for both websites and mobile applications, and one example is the “Kate” chatbot, a mobile app digital assistant, developed by Geico insurance company. App users can ask Kate questions, via both voice and text, and receive answers about billing and basic policy.

Navigational botsshopping assistants

Navigations bots help website or mobile app users search for specific information such as blog articles, a particular website page or product, via a conversational interface. You can use the navigation chatbot to direct customers to the most relevant product. Firstly, the user tells a chatbot what product one is searching for. Next, the navigation bot shows the user all the products that match the user’s request and sends links to those items. To achieve this, the chatbot back-end is integrated with catalog and service-side API. Still, such chatbots are something more than navigation menus. Shopping assistants can even adopt changing messages and themes, send holiday greetings or information about an actual sale. 

Shopping assistants are widely used in the clothes and fashion industry. An example is the H&M bot on the KiK platform, which understands user style preferences, gives personalized style recommendations, and even builds an outfit. 

Healthcare assistants

Chatbots help clinics and hospitals save a considerable amount of money. In the healthcare industry, chatbots can perform as online receptionists, nurses, interns, or even assist with a patient progress report, assess drug interactions, and check post-op recovery. 

Besides, chatbots can make medical diagnoses faster, as MedWhat chatbot does. Thanks to the ML algorithm, MedWhat chatbot provides users with increasingly accurate answers on questions concerning medical diagnoses. Besides this, thanks to machine learning, the bot learns from each interaction with a patient. MedWhat bot expands existing medical data using a vast volume of medical research and peer-reviewed scientific papers. 

Recommendations and Booking agents

In industries like hospitality and traveling, chatbots can be used as personal traveler assistants or virtual concierges. In this way, customers receive 24/7 online support, which impacts customer loyalty and satisfaction. You can integrate such chatbots into a website, and even a Facebook Business page, like the SnapTravel agency has.

Using the SnapTravel Messenger bot, travelers can find the best accommodation that meets their preferences and budget. This bot is powered by Artificial Intelligence and works as an aggregator. You need to enter the dates and city you want to go to. Then, Snap bot analyzes offer from Expedia, Priceline, and other travel websites, to come up with the best deals. After selecting the best option, the user can book accommodation right through Messenger. 

Lead generation and retention bots

Chatbots might also be a part of a content marketing strategy and generate more leads from social media or websites. Besides this, a retention chatbot could activate your old leads by sending them sales alerts or relevant updates as TechCrunch Messenger chatbot does. It informs subscribers about stories on relevant topics. To achieve this, users need to subscribe to sections, authors, and topics on the TechCrunch website, and then the bot sends news articles, and other updates, right to the user via Messenger. 

Transactional bots

This type of chatbot is much different from other use cases on this list. The main goal of transactional chatbots is to simplify user experience and provide a convenient and quick channel for completing a particular action. Transactional chatbots allow users to place new orders and repeat purchases and even conduct an online payment. 

An example is Pizza Hut’s bot that helps users place orders for pizza and other meals via Twitter or Facebook. The bot also informs customers about recent promotions and answers FAQ questions.

Have you selected a perfect type and usage case for your chatbot? Great!

Now, let’s find out whether to build a bot with a builder or make a custom bot from scratch. 

READ ALSO: NLP Business Applications

Platform-based chatbots

Chatbot platforms allow you to make your own chatbot by yourself. While some chatbot-building platforms have a simple drag-and-drop menu, others require a degree of technical knowledge. Now, we’ll take a look at the most popular platforms for building chatbots, their capabilities, and price policies. 

Flow XO


Azure Bot Service





Where to use

·       Facebook Messenger

·       Slack

·       Twilio SMS

·       Telegram

·       Website

·       Facebook Messenger

·       WordPress

·       Shopify websites

·       Website

·       Mobile app

·       Cortana

·       Skype

·       Slack

·       Facebook Messenger


Main features

·       Simple questions answering

·       User answers validation

·       Switch between a chatbot and live chat

·       Accept payments

·       Build-in templates

·       Online chat

·       Payments

·       Call button

·       Switch between a chatbot and human agent

·       Support integrations via JSON API

·       Natural Language Understanding

·       Open-source SDK

·       Native integration of Azure Cognitive Services.

·       Any type of bots: from a Q&A bot to your own branded virtual assistant


·       Standard Plan – $19 per month


·       5 bots or active flows – $10 per month

·   25,000 interactions- $10 per month

·       Free – up to 1000 Subscribers

·       Pro – from $15 per month

·       Premium – from $199 per month

·       Free – 10,000 messages/month

·       Premium channels- $0.50 per 1,000 messages

So, what are the advantages of bot-building platforms?

  • Chatbot builders are handy for developing simple or even sophisticated chatbots for any business
  • You can integrate your chatbot to most popular messaging platforms, such as Messenger, Telegram, Skype
  • Some platforms allow integrating a chatbot right to your website or mobile app
  • You can connect your chatbot with third-party services such as payment gateway 
  • Chatbot-building platforms are cheap or even free 
  • By using a platform, you can set your business logic of chatbot behavior

At the same time, chatbot building platforms have some disadvantages:

  • You can only create a chatbot with simple logic. For more complex chatbots, you will need  help from developers 
  • Chatbot-builders’ tools may not always help you achieve your desired results.
  • If you are not a tech person, you will need more time and effort to make a chatbot. However, there is no guarantee that the chatbot will perform well.

Building a chatbot from scratch

If you want to create a sophisticated chatbot with your own API integrations, such as a shopping assistant, booking agent, or healthcare assistant, consider developing a chatbot from scratch. You can create a solution with custom logic and a set of features that ideally meet your business needs. Such chatbots work as a server-side application that implements chat features via its own API. To create your own custom chatbot, you need to hire a development team for chatbot development services. If your chatbot requires the integration of Natural Language Processing, the development team will use Opennlp or Nltk NLP tools. In this case, consider that NLP will perform as a separate service.  

Below, you can find our feature list of a custom chatbot MVP for a travel agency with estimation in hours. 


Functions required




Customization for agents

  • Logo
  • Agent Name


Connection to Data Server API


Switching between a chatbot and human agent

  • Switch between Human Agent and Chatbot
  • Return, Forward functions for user


Gathering of data from the user (Search for hotel, tour, full package flow)

  • Dates
  • Number of adults
  • Number of Infants
  • Meal
  • Hotel stars


Transferring Data to API and receiving results


Tour Proposals

  • Show search results


Show more variants


Admin Panel

Admin Login


Chatbot Management

  • Define questions and answers




From 240 hours

In our experience as a chatbot development company, developing a custom chatbot starts from $4000 and takes from 240 hours of coding

By developing a custom chatbot you will receive the following benefits: 

  • You can integrate complex and unique functionalities to your chatbot
  • Your development team will provide your bot with excellent user experience, as well as helping you to find the right technical solution for your business needs. 
  • The development team will conduct tests of your chatbot to ensure that it is bug-free.
  • After the bot release, the development team will provide you with technical maintenance and further bot improvement. 

However, there are also some drawbacks: 

  • Developing a custom chatbot takes more time and costs more than developing a bot via the building platform. 
  • To develop such a solution, developers will need to create service infrastructure and hosting, which also takes time. 

Now, let us compare developing a chatbot with a platform and a custom solution. 

Platform vs. Custom: Chatbot development comparison




Initial cost


While some bot development platforms are free of charge, others will charge a fee:

·   Monthly

·   Per user

·   Per transaction basis



The cost will depend on:

·   Experience of the developers

·   The number of developing hours

·   Bot usage case

·   The number of platforms required

·   The number of chatbot users

·   The number of third-party integration such as an online store or a CRM

·   API integration




You can simultaneously plan and build a chatbot using a flowchart-like or drag and drop interface

Here, you need to consider the integration of a chatbot with:  

·   NLP

·   Analytics

·   Payments

·   Subscriptions

·   Integrations

·   Platforms

All elements will work together, which increases both chatbot complexity.

Build Time


By using ready-made templates, you can integrate a simple chatbot in messenger in less than 30 seconds.

The chatbot building time depends on

·   Number of developers

·   Number and complexity of features

·   Number of integrations




You need to test the Chabot on your own. You can receive support on Chabot testing via a test/development chat within the platform.

The developing team will conduct the bench of the test to ensure that your bot operates correctly.




You can make changes and integrate new scenarios on your own without coding.

Only developers can make changes in the bot code.

Want to Learn More About The APP Solutions Approaches In Project Development?

Download Free Ebook

What to choose: platform-build or a custom chatbot?

There is no single answer since the solution will depend on the complexity of your chatbot, its’ usage case, number of integrations, and so on. 

Chatbot builders suite for developing:

  • FAQ bots
  • Transactional chatbots 
  • Navigation bots
  • Lead generation bots

Besides, you can use chatbot builders if you are in a hurry, have a tight budget, and need simple functionality. However, even platform build-solutions may be complex and apply MLP, AI, and machine learning. For such cases, you need to hire a development team to set up and teach the sophisticated chatbots for you. 

Custom chatbots are great in the following use cases:

  • Shopping assistants with AI and machine learning 
  • Healthcare assistants 
  • Medical diagnoses bot
  • Hospitality chatbots and personal concierge
  • A bot with catalog and service-side API integrations

In a nutshell

Chatbots vary in the level of their complexity, usage cases, and industries. Still, with such great diversity, you can find the option that will ideally meet your business needs. To achieve this, you need to answer the following questions: 

  • What is the purpose of the chatbot?
  • Where will you use it: in a messenger, website, or app?
  • How complex should it be?
  • How many features should it have?
  • Do you need to integrate it with third-party services, such as analytics or payment gateway?  

After answering these questions you will have a clear idea of whether to build your own custom chatbot or use a bot builder. 

Related articles: