Challenge Overview
Welcome to the “Improve Accuracy for Pseudovet Aging Algorithm Challenge” .
Overview
PseudoVet is an automated patient data fabrication engine which provides a set of active synthetic patients and clinical data that can be used for healthcare software development. Development against real patient data unnecessarily exposes patient health information (PHI) and personally identifiable information (PII) and cannot be used by developers outside of the VA network. However, fully functional, realistic data sets can be used safely in development, testing, training and other non-production environments in compliance with the Health Information Technology for Economic and Clinical Health Act (HITECH Act) and other regulations. Development against current fabricated data is not useful because the data sets are outdated, which requires development teams to spend time developing data sets to use in lieu of writing code or require licenses and cannot be shared.
Challenge Requirements
We’ve run multiple challenges for this project so far to build an algorithm for generating aging and morbidity data. We first launched a challenge to build an algorithm for generating patient data. This was followed up with another challenge to convert the algorithm to use an updated dataset that includes morbidity data.
We then ran a challenge to build APIs on top of this algorithm. The problem we are facing is that the algorithm is essentially a randomiser so the APIs always return random information.
We’ve provided the following architectural artifacts for this challenge.
-
TCUML
-
Swagger
-
Algorithm & API code (available in our repo)
In this challenge, we want to fix the algorithm as well as the associated APIs so that it returns correct data.
- For any provided input configuration, the generated output data must be correct. A few examples
-
Algo and APIs must generate correct number of patients as specified in configuration
-
Patients generated MUST match the configuration input. For example, if we put in 100% males, NO female patients should be generated.
-
War Era information generated must be correct as per configuration
-
Morbidity information generated must be correct as per configuration
The existing algorithm uses the following data format (CCDA template) - you MUST validate your output using the validator tool mentioned in the algo README
Coding Standard
Follow python coding best practices : PEP 8 for the main text, and PEP 257 for docstring conventions
Documentation
Your solution must be well documented.
Final Submission Guidelines
Final Submission Guidelines
-
Algorithm & API code with instructions on how to run the algorithm, input data and receive results
-
Updated Postman collection if required
-
Demo video of how to configure and run your algo/ APIs