We worked with a healthcare startup on a mission to offer healthcare professionals with an improved ability to remotely monitor at-home patients. Specifically, the target was to prevent patient falls — a billion dollar cost to the healthcare system. Reducing patient falls would reduce injury and the associated costs, and would improve overall patient experience in acute, home care, and long-term care environments.
To deliver on this mission, the customer applied state of the art IoT devices and cameras to track patient vitals. Bitstrapped was contracted to develop a more scalable architecture on GCP to migrate the customer over to. An event driven architecture with best practices for automation, Dev Ops, and use of serverless and highly scalable compute, enabled the customer to improve the performance of their camera ML models by shipping faster updates, ingesting more data, and automating more backend processes in real time.
To make this possible, Bitstrapped utilized Kubernetes Engine pipelines with design of preemptible GPU node pools to power ML training and automate pipeline orchestration for data intake and processing. Bitstrapped brang traditional infrastructure strategies to solve for the hard parts of operating machine learning at scale, automating away tedious, manual workflows, enabling the client to work smarter on their ML technologies.
Bitstrapped re-architected an event driven system on GCP that enabled greater degree of automation and high volume of data ingestion and processing events. The chosen architecture for pre-processing and data ingestion was serverless, powered by IoT core with enablement of automated deployment of models to the edge. As images were collected, the architecture would facilitate data augmentation and preprocessing of the images in order to speed up downstream training pipelines.
For the data science team, the new infrastructure on Google Kubernetes Engine and use of production KubeFlow, enabled automation of ML pipelines to pre-process, train, and deploy the models. This included flexible compute for their experimentation dynamic and GPU enablement as needed to accelerate training time.
Once the event-driven pipeline automation was in place, focus shifted to the performance of the camera solution. Implementing a semi-automated labelling solution would automatically detect failures and allow for humans in the loop as needed. This way, the team could be efficient in labelling images, while also improving the ability to do meta learning and make use of previously trained models to label new datasets. Label automation was achieved by integrating a custom instance of Label Studio into the architecture and MLOps process.
Event driven automation enabled:
DevOps and Orchestration enabled:
Kubernetes Engine adoption enabled:
Improved Security with:
Best Practices adopted:
IoT Core enabled:
Customer was equipped with productive grade, practically fully automated process, that freed back all the time previously spent manually executing steps to trigger events, label, and upload data. As a result, the same teams could focus on the accuracy of the models and new model development with a self sufficient cloud environment.