Canada
Puerto Rico
USA
Belgium
France
UK
India
Client Background
The client is a US-based healthcare technology and services company.
We aim at building a tool for risk adjustment to improve the efficiency of the medical coding process using NLP, ML, and DL capabilities. It extracts clinical insights from unstructured text, improves risk score accuracy and operational efficiencies and thereby provides the best care to patients.
We aim at building a tool for risk adjustment to improve the efficiency of the medical coding process using NLP, ML, and DL capabilities. It extracts clinical insights from unstructured text, improves risk score accuracy and operational efficiencies and thereby provides the best care to patients.
Client Need
The manual review of patient medical charts is a tedious process and is prone to errors. Client needed to automate the manual coding process to have more consistent and accurate results. The solution need to include:
Extract data from unstructured and nonstandard document formats. This includes chart pages which are scanned charts, lab reports, patient chart history, etc.
Build a medical record review service to assist coders with PHI identification and patient and provider information extraction using OCR and NLP techniques
Solution
Developed an OCR module for training a custom tesseract model to extract text from patient’s medical charts
Built NLP Engine constituting Entity extraction module and ICD extraction modules
Entity extraction module – A pipeline to extract patient information like patient name, age, gender etc. and provider information provider name, title, facility, etc. Leveraging regular expressions and advanced deep learning approaches
ICD extraction module – A pipeline to extract ICD codes
Trained using a state-of-the-art multi-label classification model to extract ICD details and corresponding annotations
Implemented regex logic to extract AS-IS ICD codes apart from annotation based ICDs
Realized Benefits
90% increase in accuracy rate with 5000+ documents
60% decrease in time required for synthesis of clinical guidelines
Increased output rate using NLP (15-16 charts per day) compared to manual coding (10-11 charts per day)
Reduced overall administration costs
Tools & Technologies
Python
Scikit Learn
RabbitMQ
Pytorch
Sci
SpaCy
Tesseract OCR
OpenCV
Trending Success Stories
Transforming Provider Credentialing with a Trusted Data Foundation and Continuous Compliance
Optimizing Pharmacovigilance Operations to Strengthen Revenue and Regulatory Trust
Elevating Clinical Trial Performance with a Data-Driven Orchestration Platform
Scaling Agentic AI for Enterprise Telecom Operations
Ready to Innovate with Us?
Let’s Talk!
Connect with us on social media
Write to us at
[email protected]