Neuroscience Data Cloud

Digital Health

The healthcare industry is challenged to become more affordable, effective and accessible in an environment of rapid change and complexity. The successful healthcare enterprise of the future will be driven by data, have digital at its core, and have a flexible operating model.

Health organizations are implementing innovative digital health strategies. Whether the focus is cloud accessibility/integration, EHRs, machine learning, AI, cybersecurity or other technologies, leading organizations can fundamentally change the way healthcare is delivered and the health consumer experience.

  • Research
  • Brain biomarker data
  • Algorithm development
  • Algorithm validation
  • Data ingestion
  • Data pre-processing
  • Data normalization
  • Data management
  • Python backend
  • Pandas & Numpy
  • React.js
  • Data visualization


Data pipeline development

Our client brought 10 years of concussion data to us with a method of diagnosis. We were tasked with developing the algorithms and a technological system for collection of baseline data, automated processing, and dynamic diagnosis.

We developed a data pipeline strategy, research framework and technology roadmap.


Autoencoder Machine Learning

We developed an autoencoder to extract synthetic baselines for our brain data is a type of artificial neural network in machine learning used to learn efficient data codings, feature encoding in an unsupervised manner. The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for dimensionality reduction, by training the network to ignore signal “noise” and extract meaningful causal components.

Our autoencoder module analyzes the patterns of the biomarker data. It creates a synthetic baseline data expectation model and compares it to the concussed state. It analyzes each brain data file automatically and stores the synthesized baseline in the dataset. 


Brain Data Cloud

We developed a cloud-based software solution for the concussion project. We use Python and PostgreSQL on the backend for data warehousing, pre-processing and management. Python is the standard programming language for modern health applications and we leverage the Python libraries for data science including Pandas and Numpy. The front end is developed using React.js, a modern framework that makes it easy to expand to mobile and leverage javascripts.