Challenge
- Culling of massive data set comprising of more than two million documents to determine the impacted data set
- Focused data mining to identify the final review population from the impacted data set
- Preparation of a deduped list in spreadsheet format containing individual names or entities along with the details of their impacted PII elements
- End-to-end cost containment from the initial identification of data through the completion of the final deduped list of impacted individuals and entities
- Fast turnaround time for completion of the project due to the strict regulatory requirement
Solution
- Elevate performed an extensive data mining process combining artificial intelligence and machine learning functionalities to identify PII and PHI and its built-in, data-driven regular expression searches with Elevate’s custom searches specifically crafted to each review’s requirements
- Application of features to dedupe and consolidate the raw entity list containing multiple line items identical information for an impacted individual or entity
- Adoption of comprehensive processes to merge all duplicate information for each individual or entity missed during AI review due to software restrictions
