Health care analytics

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Health care analytics is a product category used in the marketing of business software and consulting services. It makes extensive use of data, statistical and qualitative analysis, explanatory and predictive modeling.[1]


The United States (US) healthcare industry is undergoing three major, overlapping developments in the evolution of data management and information technology utilization: (1) Data collection, characterized by the adoption and meaningful use of electronic medical records; (2) Data sharing, characterized by the adoption of health information exchanges; and (3) Data analysis, characterized by the adoption of enterprise data warehouses and analytic tools.

In 2004, the Healthcare Information Management Systems Society (HIMSS) published the seven-stage EMR Adoption Model (EMRAM), creating a pivotal framework for measuring the industry’s advancement toward the use of computerized medical records. The EMRAM was also useful to vendors and led to the development of the federal Meaningful Use criteria. In addition, hospitals and physician organizations used the EMRAM as an internal guide for assessing their progressive utilization of an EMR. No such industry-wide framework for the adoption and utilization of health information exchanges (HIEs) exists, but, recently, several organizations have published frameworks for business models to address the poor track record of economic sustainability for HIEs.

The adoption of enterprise data warehouses, business intelligence and analytics in healthcare is estimated at approximately 10%, with substantial growth anticipated in the next decade (Frost & Sullivan 2012). A generally accepted framework for adoption and meaningful use of data warehouses and analytics in healthcare could be very beneficial, in ways similar to the HIMSS EMRAM. An eight-level framework proposed for that purpose, with the hope that comments and feedback for improvement will result in a nationally recognized standard. This framework was developed by a cross-industry group of healthcare industry veterans.[2]

These levels can be explained as follows:

Level 0: Fragmented Point Solutions:

  • Vendor-based and internally developed applications are used to address specific analytic needs as they arise.
  • The fragmented point solutions are neither co-located in a data warehouse nor otherwise architecturally integrated with one another.
  • Overlapping data content leads to multiple versions of analytic truth.
  • Reports are labor-intensive and inconsistent.
  • Data governance is non-existent.

Level 1: Integrated Enterprise Data Warehouse

  • At a minimum, the following data are co-located in a single data warehouse, locally or hosted: HIMSS EMR Stage 3 data, Revenue Cycle, Financial, Costing, Supply Chain, and Patient Experience.
  • Searchable metadata repository is available across the enterprise.
  • Data content includes insurance claims, if possible.
  • Data warehouse is updated within one month of source system changes.
  • Data governance is forming around the data quality of source systems.
  • The EDW reports organizationally to the CIO.

Level 2: Standardized Vocabulary & Patient Registries:

  • Master vocabulary and reference data identified and standardized across disparate source system content in the data warehouse.
  • Naming, definition, and data types are consistent with local standards.
  • Patient registries are defined solely on ICD billing data.
  • Data governance forms around the definition and evolution of patient registries and master data management.

Level 3: Automated Internal Reporting:

  • Analytic motive is focused on consistent, efficient production of reports supporting basic management and operation of the healthcare organization.
  • Key performance indicators are easily accessible from the executive level to the front-line manager.
  • Corporate and business unit data analysts meet regularly to collaborate and steer the EDW.
  • Data governance expands to raise the data literacy of the organization and develop a data acquisition strategy for Levels 4 and above.

Level 4: Automated External Reporting:

  • Analytic motive is focused on consistent, efficient production of reports required for regulatory and accreditation requirements (e.g. CMS, Joint Commission, tumor registry, communicable diseases); payer incentives (e.g. MU, PQRS, VBP, readmission reduction); and specialty society databases (e.g. STS, NRMI, Vermont-Oxford).
  • Adherence to industry-standard vocabularies is required.
  • Clinical text data content is available for simple key word searches.
  • Centralized data governance exists for review and approval of externally released data.

Level 5: Clinical Effectiveness & Accountable Care:

  • Analytic motive is focused on measuring clinical effectiveness that maximizes quality and minimizes waste and variability.
  • Data governance expands to support care management teams that are focused on improving the health of patient populations.
  • Permanent multidisciplinary teams are in-place that continuously monitor opportunities to improve quality, and reduce risk and cost, across acute care processes, chronic diseases, patient safety scenarios, and internal workflows.
  • Precision of registries is improved by including data from lab, pharmacy, medications, and clinical observations in the definition of the patient cohorts.
  • EDW content is organized into evidence-based, standardized data marts that combine clinical and cost data associated with patient registries.
  • Data content expands to include insurance claims (if not already included) and HIE data feeds.
  • On average, the EDW is updated within one week of source system changes.

Level 6: Per Case Payment & The Triple Aim:

  • The “accountable care organization” shares in the financial risk and reward that is tied to clinical outcomes.
  • At least 50% of acute care cases are managed under bundled payments.
  • Analytics are available at the point of care to support the Triple Aim of maximizing the quality of individual patient care, population management, and the economics of care.
  • Data content expands to include bedside devices, home monitoring data, external pharmacy data, and detailed activity based costing.
  • Data governance plays a major role in the accuracy of metrics supporting quality-based compensation plans for clinicians and executives.
  • On average, the EDW is updated within one day of source system changes.
  • The EDW reports organizationally to a C-level executive who is accountable for balancing cost of care and quality of care.

Level 7: Per Capita Payment & Predictive Analytics:

  • Analytic motive expands to address diagnosis-based, fixed-fee per capita reimbursement models.
  • Focus expands from management of cases to collaboration with clinician and payer partners to manage episodes of care, using predictive modeling, forecasting, and risk stratification to support outreach, triage, escalation and referrals.
  • Physicians, hospitals, employers, payers and members/patients collaborate to share risk and reward (e.g., financial reward to patients for healthy behavior).
  • Patients are flagged in registries who are unable or unwilling to participate in care protocols. Data content expands to include home monitoring data, long term care facility data, and protocol-specific patient reported outcomes.
  • On average, the EDW is updated within one hour or less of source system changes.

Level 8: Per Unit of Health Payment & Prescriptive Analytics:

  • Analytic motive expands to wellness management, physical and behavioral functional health, and mass customization of care.
  • Analytics expands to include NLP of text, prescriptive analytics, and interventional decision support.
  • Prescriptive analytics are available at the point of care to improve patient specific outcomes based upon population outcomes.
  • Data content expands to include 7x24 biometrics data, genomic data and familial data.
  • The EDW is updated within a few minutes of changes in the source systems.

Value of EMRs[edit]

The previously mentioned data collection phase, characterized by the urgent deployment of EMRs, will not, by itself, have a significant impact on the quality or cost of healthcare in the US. Numerous retrospective studies of EMR deployment have yet to reveal anything other than a very modest return on investment (ROI) (Goodman 2005; Hillestand et al. 2005), and those modest returns are very dependent on complex local factors of deployment. More recently, the US Secretary of Health and Human Services and Attorney General issued a national letter of warning (24 Sep 2012) to five healthcare industry associations, suggesting that electronic health records are actually increasing the cost of care in the US by enabling fraudulent billing and “up coding.”

However, the investment in EMRs, as a source of workflow transaction data, is fundamentally required to achieve the value that is accessible in data warehousing. The ROI from data warehousing is well-documented (Nucleus Research 2002). The ROI from the more than $50B invested in EMRs, let alone impactful health reform, will not be realized until the healthcare industry invests in enterprise data warehousing and commits culturally to the exploitation of data – that is, to become a data-driven culture, incented economically to support optimum health at the lowest cost.

Historically, healthcare delivery organizations in the US have focused on, at best, managing quality and cost separately. In truth, were it not for pressure from the federal government and private insurance companies, the US healthcare system would be even less inclined to measure, and less mature at measuring, quality of care. In addition, the predominant methodology in US healthcare enterprises is to measure cost of operations, not cost of production, the latter being a reflection of the costs required to achieve the production of a given outcome and the former being simply an indication of current run rates unrelated to product quality. In the future, CFOs and other C-level executives must manage both quality and cost and understand the interplay between the two.


"Predictive vs. Explanatory Modeling in IS Research", and patient health information to drive medical decision making.[vague] The breadth of digital data available through point-of-care encounters, medical claims, pharmacy claims, lab values, HRAs, genetic markers, and biometrics has resulted in an increase in the capabilities of traditional analytical tools. This data is combined with medical guidelines and patient profiles to reveal contraindicated care, gaps in care, and opportunities for cost savings. John-David Lovelock, Research VP at Gartner, called health care analytics 'the first step in improving the overall efficiency of hospitals.'[3]

Real-time health care analytics[edit]

Currently the most prevalent application for real-time health care analytics is within Clinical Decision Support (CDS) software. These programs analyze clinical information at the point of care and support health providers as they make prescriptive decisions. These real-time systems are “active knowledge systems, which use two or more items of patient data to generate case-specific advice.”[4]

Batch health care analytics[edit]

Batch health care analytics is a technical application in which retrospectively evaluates population data sets (i.e. records of patients in a large medical system, or claims data from an insured population). These evaluations can be used to supplement disease management or population health management efforts.

A benefit of batch health care analytics is its use of "predictive modeling across multiple clinical conditions.[5] This process can identify undiagnosed conditions for patients within an insurer's patient population, or suggest interventions to prevent conditions from developing.


  1. ^ Galit Schmueli and Otto Koppius
  2. ^ Healthcare Analytics Adoption Model -
  3. ^
  4. ^ "Decision support systems." 26 July 2005. 17 Feb. 2009
  5. ^ Howe, Rufus, and Christopher Spence. Population health management: Healthways' PopWorks. HCT Project 2004-07-17, volume 2, chapter 5, pages 291−297. Retrieved 2008-10-12.

External links[edit]