MSA's powerful, HIPAA-compliant Data@Factory merges patient records...

Without the risk of compromising patient confidentiality

The Power of Data@Factory

Go beyond de-identification – link records to create a complete view of the therapeutic experience

MSA’s patented, industry-agnostic Data@Factory technology addresses the rapidly growing need for HIPAA-compliant solutions that provide integrated, anonymous data for sophisticated patient-centric analytics.

Data@Factory transforms raw disparate data from across the healthcare spectrum – including but not limited to pharmacy, medical, and hospital claim data –  into connected information.

Adhering to each customer’s specific business rules, de-identified data is processed through the Data@Factory for robust patient matching. The Patient Matching process assigns an anonymous Patient ID – that’s as strong as using PHI but without the risk – and creates and maintains an anonymous Patient Master table to enable the longitudinal alignment of the disparate data from multiple data sources.

Leading healthcare companies and academic and research organizations rely on Data@Factory-generated anonymous patient-level databases (APLDs) for deep, actionable insights.

We do the heavy-lifting – as much or as little as you need.

Data provider management, including file monitoring and data quality issue resolution

Automated data management and validation reporting, interventions, and alert notifications

Data normalization and standardization of patient matching and other data elements across all data sources

Complex multi-dimensional data alignment and management across multiple data sources

Stay Safe and Secure

Committed to safeguarding the integrity of PHI, MSA’s HIPAA-compliant, HITRUST CSF-certified environment ensures that patient privacy is protected.

The Gold Standard

The 10-step process of data processing inside the Data@Factory is the gold standard and brings together a wide array of de-identified data sets into a single uniform, normalized and integrated data set, thus removing the traditional barriers of accessing disparate data originating from multiple sources.

1.  Map/Load

Align disparate formats into a common schema

2.  Clean

Create field consistency – trim, remove special characters, date formats

3.  Standardization

Standardize fields across sources – gender, race, state, units of measure, etc.

4.  De-Duplicate

Remove duplicate data within or across sources

5.  Verify Quality

Configurable alerts at the File, Field, and Content levels; quarantine data as required

6.  Process Exceptions

Remedy or remove quarantined data

7.  Match

Align dimension members across sources and time

8.  Master Data Management

Introduce new key dimension elements and consolidate obsolete element variation

9.  Command/Control

Automates processing and raises operational alert

10. Metrics/Statistics

Date and time stamps, error metrics, and matching metrics