Challenges
- Manual review of patient medical charts was becoming too time and labor-intensive and was prone to errors.
- The client needed to automate the manual coding process in order to have more consistent and accurate results.
Solutions
- The client needed to extract data from unstructured and nonstandard document formats including paper, fax and digital. We implemented optical character recognition technology for patient data extraction from the scanned medical charts which helped pull out relevant medical information.
- Integrated multiple data sources to automate the query process.
- Ran the extracted medical data through the NLP engine and captured the sentiment of a particular record.
Tools & Technologies
Python, Open NLP, LeadTools
Key benefits
- Improved productivity by 40%.
- Increased output rate using NLP as compared to the manual coding rate.
- Accuracy rates of 95-98% in identifying medical conditions.
- Reduced overall administration costs.
- Easy access to information leading to expedited care for those in need (patient & doctor).
