The Client
Our client, UKHealth, is one of the largest healthcare service providers in the UK. UKHealth manages thousands of hospitals and care units providing healthcare to the people of the UK. Apart from multispeciality hospitals, diagnostic clinics and pharmacies are also managed by UKHealth. They make healthcare services more efficient and accessible.
Disclaimer - The name UKHealth is a placeholder as there is an NDA signed between both parties.
Challenges
Our client faced significant inefficiencies and inaccuracies in manual data processing.
- Doctors generated massive volumes of discharges, referrals, and follow-up letters for patients daily.
- Data teams had to manually assess and classify these letters into specific categories: Discharge, Follow-ups, and Referrals.
- Managing the workload required a large team to update the central Hospital Information Management System (HIMS).
Solution
We developed a machine-learning solution to automate the extraction and classification of patient data, reducing manual intervention and improving efficiency.
- Step 1: Text Extraction via OCR (Optical Character Recognition)
- Scanned physical letters into digital files.
- Used OCR to extract and structure text for machine learning analysis.
- Step 2: Phrase Identification via NLP (Natural Language Processing)
- Designed an NLP model to understand the extracted text.
- Classified letters into Discharge, Follow-ups, and Referrals based on context-specific phrases.
- Integrated the machine learning model with UKHealth’s central HIMS for automated updates and easy data management.
- Improved model accuracy with supervised training, raising the confidence score from 80% to 85% in 6 months.