More accurate, efficient, and personalized processes, from diagnostics to treatment.

Healthcare

Health organizations have accumulated vast data sets in the form of health records and images, population data, claims data and clinical trial data. AI technologies are well suited to analyze this data and uncover patterns and insights that humans could not find on their own.

With deep learning healthcare organizations can use algorithms to help them make better business and clinical decisions and improve the quality of the experiences they provide.
Learn More
BlueRectangle
Use Cases
How we can leverage ML in Heavy Industry
Medical images analysis & diagnosis
Automatic processing of medical records
Accelerating medical research & drug discovery
Assisted diagnosis & prescription
Patient and facilities data analytics and pattern detection
Auditing & fraud detection
Robot-assisted surgeries
Facial Ageing System
About the client
Change my face is a UK-based firm that develops face age technology for health, finance and skincare markets. It has catered to major clients both in the private and public sectors, such as Netflix, Lexus, HSBC, NHS, The University of Manchester and The Scottish Government, among others.
Challenge
Our client needed to generate images changing a person's age but preserving identity, similar to FakeApp. These applications are very useful when running health prevention campaigns to show visually the effects different lifestyles can have on a person.
Results
Based on the work of companies like NVIDIA, we implemented an ageing system for human facial photos. It is based on generative adversarial networks utilizing state of the art papers and techniques. Our system receives the photo of a person and alters the person’s age while preserving their unique visual identity.
We solved challenges such as developing the production deployment of a scalable solution, optimized for minimum processing time yet while minimizing cloud costs for our client.
13
%
Of increase on saving patterns
Impact
This technology was implemented in a financial app that allowed customers to see an image of their future selves based on their current saving habits. Combined with messages regarding the importance of savings, these images had a direct impact on saving patterns, influencing an increase of 13%.
Impact
According to market research firm IDC, most companies lose 20-30% in revenue every year due to bottlenecks and inefficiencies.
13
%
Of increase on saving patterns
Technologies
Python, Tensorflow, Pytorch, Docker, AWS.
Summarizing Medical Documents With NLP
About the client
Our client was a technology company dedicated to developing AI-based platforms for healthcare companies.
Challenge
They approached us looking to build a PoC platform to process medical papers and generate a summarized document as an output.
A few challenges were identified in order to achieve this, such as:
  • The availability of the datasets to train and evaluate machine learning models
  • The difficulty of building an objective metric to benchmark those model
  • The need for medical subject matter experts (SME) knowledge to extend the dataset and assess the preliminary results.
Results
Given the complexity of the problem and the current state of the art, we began with a product discovery phase to assess the platform’s viability. This was done to understand the potential results considering the current state of the art, producing an early-stage prototype of the product, compiling the product backlog, proposing an architecture design and defining dataset requirements.
We also proposed an architecture for an MVP that includes a machine learning pipeline that uses Natural Language Processing to extract key value messages from core value dossiers, an API and a frontend so that a human in the loop could improve any automatic processing being done.
70
%
Practitioner’s time
30
%
Healthcare costs
Impact
AI helps minimize time spent on routine, administrative tasks, which can take up to 70% of a practitioner’s time and 30% of ​​healthcare costs.
Impact
AI helps minimize time spent on routine, administrative tasks, which can take up to 70% of a practitioner’s time and 30% of ​​healthcare costs.
70
%
Practitioner’s time
30
%
Healthcare costs
Shape of the picture
Get in touch with one of our specialists.
Let's discover how we can help you
Training, developing and delivering machine learning models into production
Contact us
Shape of the picture