Today after the load, the dashboard shows discrepancies in the data counts without any drilled-down details. This not only takes up more time but adds up hidden costs
MCheck allows drill down of every data discrepancies hence accelerating corrective measure.
The tool identifies a targeted list of medical charts that should be reviewed, target codes for nurses/coders and automated solutions to search for in these charts
It can be combined with our home grown NLP based document extraction to provide a multi-pronged approach to test for data errors
Historical data from the source system and the target from a specific business area(s) are fed into MCheck to learn the inter system patterns. The test data is run through MCheck, resulting in automatic generation of inter-systems discrepancies
The few proactive data quality management solutions that do exist are generally rules-based. They can handle only those types of data quality errors that organizations are already aware of. It cannot find new or unknown scenarios of data errors
The tool identifies potential members with the highest probability of inaccurate/incomplete coding. In addition, it generates, with at least 90% confidence, a list of missing/inaccurate codes for each potential member.