AI-powered HealthCare platform

machine learning
ux/ui design
An AI-powered anamnesis platform that provides efficient health tools to help doctors make the right diagnosis

Doctors verify each diagnosis, improving the machine learning engine

Enhancing the quality of each patient's face time with their doctor


Our main task was to deliver a machine learning-based app, designed to improve and shorten the appointment time with a doctor, thanks to a preliminary analysis of symptoms provided by the patient.

What we did
  • UX/UI Design
  • Front-end Development
  • Back-end Development
  • Machine Learning
  • Engine Development
  • Chatbot

Patients answer smart questions and boost diagnosis accuracy

An interactive human body avatar for patients to show their symptoms.
Machine learning diagnosis support for doctors.
Built for easy integration with appointment scheduling systems.
What we did

Worskhops with clients

F9FC52DF-CBF2-4F1F-8CFC-C7074A587CAF Created with sketchtool.
  • Focus group research
  • Analysis
  • Marketing segmentation
  • Competition Research
  • Personas
  • User Scenarios
3968FD3C-DDD2-4D3C-9016-FCD2C36266CF Created with sketchtool.
  • User Story Mapping
  • Site Map
  • User Flows
  • Stakeholder Workshop
  • Information Architecture
4C27786F-A0A1-4535-8E95-99CD295F66FB Created with sketchtool.
  • Sketching
  • Wireframing
  • UI Style Guide
  • Graphic Design
  • Testing

Project kick-off

Our team analysed relevant focus group studies as well as marketing segmentation data. We put the clients hypotheses through our verification process, and created a sitemap with user flows pointing out the strenghts, weaknesses and opportunities.

Then we hosted a workshop with the stakeholders and summed up the business, techonology and qualitative data we were basing our recommendations on. During this workshop, we created personas, user scenarios and user stories, which led us to identifying the scope of the MVP.

User Stories

Scenarios from the workshop were divided into short stories that were shared with the whole team and used for progress tracking and backlog creation.

Sketching & Prototyping

We kicked off our design sprint with ‘crazy 8's’ to generate initial ideas. Once these had become sketches everyone was clear on, the process moved on to wireframes and then visual design.

UI Design

We started by developing a style-guide, so that the developers had a consistant and flexible framework that remained in-line with the brand.


  • Front-end Development
  • Back-end Development
  • Machine Learning Engine


  • Typescript
  • flexboxgrid-sass
  • momentjs
  • ng2-img-cropper
  • ng-2select
  • rxjs
  • svg.js


Bingli back-end architecture makes use of Microservises. The project also utilises Amazon ECS, providing robust infrastructure for the machine learning engine.

Interface for back-end/
front-end connection
Engine API
Handles machine
learning module
Admin Panel
Data analysis and
CRUD operations
Celery Worker
App for CRUD tasks
  • Codeship
  • Codeclimate
  • Bitbucket
  • PyCharm
  • Apiary mock server
  • Amazon Web Services
  • Docker
  • Aiohttp
  • Flask
  • SQLAlchemy
  • Marshmallow
  • Itsdangerous
Data management
  • Postgres
  • Elasticsearch
  • Mandrill
  • Sentry
Written in Python

Machine Learning Engine

During the patient's interview, questions are adjusted in reponse to previous information and answers provided.

The bayesian network within the machine learning engine, factors in the prevelance of diseases alongside the symptoms provided.

This computation of both probablity and the symptoms allows the system to generate a highly reasoned suggested diagnosis for each patient.