Big data analytics


Learn more

It all starts with powerful BIG data

Our database of more than 200 million unique patients’ medical and pharmaceutical claims is more accurate, extensive, and timely than any other.

  • Unmatched comprehensiveness

    Data coverage for all settings of care and every 3-digit ZIP code in the U.S.

  • Current and historic data

    Monthly data refresh plus access to 12 years of longitudinal coverage

  • Conformed data

    Single data model from all contributors for data uniformity

  • Highest quality and integrity

    Four levels of certification, including an independent external actuarial review

  • Continuous enrollment

    Member/patient continuity allows for unique tracking across claims

Big data for healthcare

Effective healthcare services, research, economic studies, and product innovation rely on access to quality data to:

  • Demonstrate the effectiveness of a treatment path
  • Train a predictive model
  • Populate a product
  • Profile markets
  • Evaluate provider performance

“We wanted a data set that allowed us to capture a wide range of patient populations. BHI’s National Data Repository allowed us to architect a platform with unique classifiers that captured subtle clinical and geographic nuances. The BHI data set also gave us a comprehensive R&D playground to look at the different diseases we were addressing.”

Chase Spurlock, PhD, CEO of Decode


Best-in-class data, combined with machine learning, provides revolutionary insight into chronic disease management
Decode Health, a Nashville-based analytics company, developed a machine learning (ML) engine that uncovers specific patterns of chronic disease risk. Using claims data from Blue Health Intelligence® (BHI®) Decode was able use its ML to create comprehensive models that detect patients with undiagnosed or misdiagnosed disease and predict individuals who will likely experience the highest healthcare spend.
Read the story

Data Enhancement Tools

Using our advanced methodologies and award-winning predictive models, organizations can accelerate their comparisons of outcomes and utilization across multiple settings, identification of trends to help predict cost of care, and analysis of patterns to help forecast critical events.

Data Augmentation Solutions

Our data augmentation solutions combine data from multiple sources for a more complete health profile. These enriched datasets reveal options for customizing care delivery or providing new or enhanced services and products.

At BHI, there are no black boxes; our clients understand exactly how we use data to uncover insights and recommend actions.

Peer Reviewed Articles

External research powered by BHI Data and published in healthcare industry publications.

"Budget Impact of a Steroid-Eluting Sinus Implant Versus Sinus Surgery for Adult Chronic Sinusitis Patients with Nasal Polyps," Journal of Managed Care & Specialty Pharmacy, August 2019

A budget impact analysis was conducted from a U.S. commercial payer perspective over a 1-year time horizon with patients who received the implant or revision ESS. Primary outcomes of interest were annual total and per-member per-month (PMPM) direct health care costs. Costs were estimated using a decision analysis model, assuming 50% implant utilization as an alternative to revision ESS in eligible patients, with other levels (25%, 75%) also considered. The model utilized the results of a recently published analysis of 86,052 patients in the Blue Health Intelligence® database, results from published clinical trials evaluating the implant, a literature review, and published Medicare national payment amounts.

Read the article

"Lymphedema-associated comorbidities and treatment gap," Journal of Vascular Surgery: Venous and Lymphatic Disorders, September 2019

To determine the proportion of LE patients with various LE-associated comorbidities as well as the rate of associated treatment, deidentified Health Insurance Portability and Accountability Act-compliant commercial administrative claims from the Blue Health Intelligence® (BHI®) research database (165 million Blue Cross Blue Shield members) were queried. We analyzed a BHI study sample of 26,902 patients with LE who had been enrolled with continuous medical benefits for 12 months before and after the index date for the complete years 2012 through 2016.

Read the article

"The Influence of Physician Payments on the Method of Breast Reconstruction," Journal of the American Society of Plastic Surgeons, October 2018

Using the Blue Health Intelligence® database from 2009 to 2013, patients were identified who underwent tissue expander (i.e., implant) or free-flap breast reconstruction. The implant-to-flap ratio and physician payments were assessed using quadratic modeling. Matched bootstrapped samples from the early and late periods generated probability distributions, approximating the odds of surgeons switching reconstructive method.

Read the article

"Budget Impact of Increased Payer Adoption of the Flexitouch Advanced Pneumatic Compression Device in Lymphedema patients," Journal of Medical Economics, July 2018

Budget impact was calculated over 2 years for a hypothetical US payer with 10-million commercial members. Model inputs were derived from published sources and from a case-matched analysis of Blue Health Intelligence® (BHI®) claims data for the years 2012-2016.

Read the article

"Benefits of Advanced Pneumatic Compression Devices in Patients with Phlebolymphedema," Journal of Vascular Surgery, June 2018

This was a longitudinal matched case-control analysis of deidentified private insurance claims. The study used administrative claims data from Blue Health Intelligence® for the complete years 2012 through 2016. Patients were continuously enrolled for at least 18 months, diagnosed with phlebolymphedema, and received at least one claim for CONS either alone or in addition to pneumatic compression (SPCDs or APCDs).

Read the article

"Disease-related Expenditures in Chronic Rhinosinusitis Patients After Endoscopic Sinus Surgery," Journal of Medical Economics, April 2018

Adults (aged 18-64 years) undergoing ESS for CRS in 2012-2015 were identified within the Blue Health Intelligence® database and used to estimate revision rates. Patients with ±1 year of enrollment around the index ESS were used to estimate 1-year healthcare expenditures. Revision ESS rates were evaluated via Kaplan-Meier and Cox regression models. Disease-related healthcare and pharmacy expenditures were modeled with generalized linear regression to assess the impact of baseline patient characteristics.

Read the article

"Trends in Physician Payments for Breast Reconstruction," Plastic and Reconstructive Surgery, April 2018

The Blue Health Intelligence® database was queried from 2009 to 2013, identifying women with claims for breast reconstruction. Trends in the incidence of surgery and physician reimbursement were characterized by method and year using regression models.

Read the article

"Costs of Cervical Disc Replacement versus Anterior Cervical Discectomy and Fusion," Spine, April 2015

This was a retrospective, matched cohort analysis of a prospectively collected database of costs and outcomes for patients aged 18 to 60 years, who were continuously enrolled in a Blue Cross Plan contributing data to a claims database. Inclusion criteria were as follows: all patients who were treated surgically with either CDA or ACDF between January 2008 and December 2009, with single-level cervical pathology and claims reflecting at least 6 weeks of nonsurgical preoperative care without claims history of prior surgery.

Read the article