Selectdata (NLP)

SelectData interprets millions of patient stories with deep learned OCR and NLP

Read the full case study

INDUSTRY: Life Science

Introduction: Many Home Health businesses still depend on documents stored as images—from receipts, manifests, invoices, medical reports, and ID cards snapped with mobile phone cameras to contracts, waivers, leases, forms, and audit records digitized with scanners.

Challenge: The data is growing as the Home Health industry is expected to grow by 6.7% next year. Managers are overwhelmed dealing with an increased number of health recrods. Identifying the record’s complexity and reducing the noise within the clinical record becomes increasingly challenging.

Solution: “SelectData is the first to leverage the power of AI to transform home health coding and documentation to optimize clinical quality and financial outcomes. They enabled managers to identify assessments that are Hard, Medium and Easy by two metrics, degree of effort and perceived level of difficulty, and identify employees that possess the appropriate skill level to complete the work for an assessment. Partnering with JohnSnowLabs, SelectData applied:

  • Spark OCR – dealing with crumpled receipts photographed from an angle in a dimly lit room.
  • Spark NLP – extracting normalized values and entities from the natural language text.
  • Building predictors or recommendations that suggest the best next action—and in particular can deal with missing, wrong, or conflicting information generated by the previous steps.”

“Benefit (subtitle): SelectData increased overall production by 10% while ensuring the accuracy of the recommendation of 95%

10%Increase in overall production
95%Accuracy
Millions of patient records interpreted

““The good news is that state-of-the-art deep learning techniques can now approach human accuracy in these three tasks—and do so at scale.”

CIO SelectData