Machine learning for healthcare: asthma management application

Innowise Group has built an ML-based asthma management application for a European company.

Customer

Industry

Healthcare

Region

Europe

Client since

2022

Our customer is a European company aiming to create a simple and affordable asthma management tool that’ll help both physicians and patients with asthma.

Detailed information about the client cannot be disclosed under the provisions of the NDA.

Challenge

Our customer has considered most asthma management tools to be complex in operating and unaffordable for regular patients with asthma. As a result, they have come up with the idea of a user-friendly mobile machine learning application containing necessary asthma management tools that can be used by anyone.The main project goal was to deliver an application that would help mobile users to manage their disease in an intuitive and informative way. Also, the application should contain enough information for physicians to adjust treatment and evaluate the patient’s progress. Our team was to develop the app’s functionality, design, and introduce the machine learning algorithms in healthcare.

Solution

Innowise Group’s team has developed from scratch the asthma management application and added machine learning algorithms integration for the client.

KEY FEATURES OF THE APP

The major purpose of the mobile application is to assist patients with asthma to manage their sickness. The application we have developed has extensive functionality, which makes it easy to manage the disease. The solution:

Tracks the patient’s condition;
Stores the information about the inhalations the patient takes;
Reminds the patient to take the inhalations according to the schedule;
Keeps track of emergency situations;
Evaluates the patient’s inhalation performance;
Provides information and guidelines about asthma management.

Users can use the application by logging into their personal accounts. When they launch the app, they see general information about their day, such as the risk of asthma symptoms based on evaluation of various triggers like weather, humidity, etc. Also, they see the list of planned inhalations and when some more or less severe symptom triggers may occur.

Through this dashboard, users can go to the Calendar section and see their monthly or weekly statistics about their condition including inhales they take, triggers they face, etc.

Also, users can let the exclusively taught machine learning algorithm listen to how they use inhalers. After the audio is processed by the algorithm, it evaluates the way the inhaler is used and gives a short summary to the user. According to this data, a patient can adjust the way the inhaler is used.

The user can go to the Education section and learn about asthma, inhalers, and other relevant topics. This section is useful for new users and those with the diagnosis made recently.

The last section is the user’s personal profile. Here a user can fill in the information about the primary and secondary inhalers, set up reminders, customize notifications, and more.

USER ROLES

There are 2 main user roles:

Users that have asthma;

App administrators.

Users are the patients with asthma. They interact with the application to make the process of maintaining asthma easier and more convenient through filling in relevant information about primary and emergency inhalers, setting up reminders, etc.Administrators are the client’s team members. They update the machine learning algorithm with relevant data and maintain the list of available inhalers so that patients could always find their medicine in the application.

Technologies & tools

Platforms

Android, iOS

Languages

Python, Dart

Frameworks

Flutter, Django

Database

PostgreSQL

Process

The client had a clear vision of the application. They have tailored the machine learning algorithm to suit the users’ needs. Our software engineers’ tasks were to develop the application with a user-friendly design and to implement the array of vital features like reminders, calendar, statistics, connect the machine learning algorithm itself, and more.

The entire project workflow was based on the Agile methodology with two-week sprints. At the end of each sprint, we provided a video demo of the completed tasks. We delivered release builds by the project deadline and then every sprint as the bugs/improvements requested by the client were fixed/done. We communicated with the client and the team via Slack.

Since our engineers were part of the international development team, it was essential tobe on the same page with IT professionals from all over the world and build up effectivecommunication. This had a positive effect on work efficiency and helped to cope withvarious challenges on the project such as mastering a large number of core moduleswritten several years ago.

Team

Flutter developers

Python developer

Project manager

DevOps engineer

QA engineer

Results

Our software engineers have created an application that helps people with asthma to control their symptoms with the help of their smartphones. The application possesses an intuitive user-friendly interface and an array of helpful features like a custom machine learning algorithm, reminders, a calendar with statistics, and more.

Project duration

March 2022 - May 2022

Related cases

Contact us!

Book a call or fill out the form below and we’ll get back to you once we’ve processed your request.

What happens next?

Having received and processed your request, we will get back to you shortly to detail your project needs and sign an NDA to ensure the confidentiality of information.

After examining requirements, our analysts and developers devise a project proposal with the scope of works, team size, time, and cost estimates.

We arrange a meeting with you to discuss the offer and come to an agreement.

We sign a contract and start working on your project as quickly as possible.

Machine learning for healthcare: asthma management application

Customer

Challenge