Select Page

Case Study

60% decrease in time required for synthesis of clinical guidelines

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.

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

Our 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

Tools & Technologies

Python, Scikit learn, RabbitMQ, Pytorch, Sci, SpaCy, Tesseract OCR, OpenCV

Key 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
Case Study KeyPoints

Services

Digital Product Engineering

Cloud Services

Data & Analytics

AI and Automation
Cybersecurity
Modern Managed Services

Build Operate Transfer

Talent Solutions

Industries

Communications & Media

Government Solutions

Healthcare, Life Sciences,
and Insurance

Banking & Financial Services

Energy, Oil & Gas and Utilities

Hi-Tech

Retail & CPG
Manufacturing & Automotive

Travel & Transportation and Hospitality

Partnerships

AWS

Automation Anywhere

Databricks

Google

IBM

Microsoft

Pega

Salesforce

SAP
ServiceNow

Snowflake

Uipath

Innovation @ Work

Blogs and Insights

Research and Whitepapers

Case Studies

Podcasts

Webinars & Tech Talks
US Employment Reports

Company

About Us

Leadership Team

Strategic Partnerships

Office Locations

Newsroom

Events

ESG

The Innova Foundation

Careers

Explore Open Positions

Life @ Innova Solutions

Candidate Resource Library

Let's Connect