Classification and Analysis of Medical Data

Convenient storage and use of information obtained from medical analyzes of clients of the mobile telemedicine application involves a friendly process of downloading and digitizing paper medical tests. Automate download and organize sets of medical tests mobile platform user uses modern methods for the detection and classification of images for subsequent processing.

Input Data

  • A set of categories of medical tests
  • Base of medical analyzes image
  • Markup images by category

Output Data

  • Model classification of images by category

Main Results

The solution is integrated into the business process of the customer:

  • Reducing the burden on specialists by 60%
  • Increasing the speed of the document in the business process by 10%
  • Reducing the cost of lost documents by 5%

Built solutions for automating recognition:

  • Checks and receipts
  • Invoice
  • Purchase order
  • Contracts

Recognition quality:

Accuracy of the class “Complete blood count” 87 %
Accuracy class “ECG” 86 %
Accuracy of the class “Clinical analysis of blood” 83 %
Accuracy of the class “Blood test for HIV” 89 %
Accuracy class “Analysis for drugs” 85 %

Example of operation with recognition and classification of images