Clinical Data Analytics Definition

Clinical Data Analytics Definition

Analytics is used to describe the collection, analysis, and information-based changes in an organization’s policies. The clinical data analytics definition takes this concept and applies it to the electronic health record (EHR). With this, clinical data analytics extrapolate information from Medicare billing codes and other structured and unstructured data to enact population health management.

Population health management is how a healthcare organization manages the treatment and prognosis of conditions within a service area. This may include private information, such as data on sexually transmitted infections and diseases, personal information, diagnoses, and treatment pathways. However, this information cannot be shared with the public in raw form.

The information must be scrutinized for patterns and trends, which identify ways of influencing positive outcomes for an organization’s service area. Ultimately, the use of this data allows healthcare organizations to improve processes across all departments, which may include the following:

  • Billing Centers
  • Physicians’ Offices
  • Emergency Departments
  • Outpatient and Inpatient Surgical Centers
  • Individual Hospital-Units

As a result, the organization can achieve a higher score on quality-based measurements, which result in higher reimbursements from supervisory agencies, such as CMS and Joint Commission.

The realm of healthcare is changing drastically, especially considering news regulations and quality-based payments from Medicare. However, the basic functions of healthcare providers have remained the same. In order to meet the demands of the Centers for Medicaid and Medicare Services (CMS), healthcare organizations must find a way to identify, monitor, analyze, and alter practices to minimize patient readmissions. As explained by Melanie Evans Medicare penalizes hospitals who discharge a patient and readmit the same patient within 30 days. Furthermore, due to this penalty and quality-based payments, healthcare organizations have found themselves searching for more effective ways of reducing such readmissions, and clinical data analytics finds these solutions.

Accountable Care Organizations and Clinical Data Analytics

In accountable care organizations (ACOs), a single provider will be responsible for the sharing of data across multiple users throughout the ACO, asserts the American Academy of Family Physicians. This sharing of data must fall under meaningful use guidelines, i.e. it must benefit the organization and service area’s population. Since some participants within a given ACO may work with paper health records and an EHR, the collection of such data can be challenging.

Clinical data analytics models, such as the Healthcare Analytics Adoption Model, addresses this concern by allowing individual practices to upload information to a given server or repository. The repository can then be accessed by authorized data analysts, who will make recommendations on changes to the organization’s policies, practices, and healthcare services. Ultimately, this leads to greater sharing of data between parts of an ACO, which reduces readmissions and healthcare costs.

Why Not Just Use These Standardized Insurance Reports for Analysis?

Insurance reports are indeed very useful for certain types of analysis, so they are often used. The problem is that they don’t capture all of the nuances needed for other types. For example, there’s an insurance code for recording that a patient is nicotine dependent, but it includes so many possible permutations that it isn’t very useful for anything but high-level analysis. Is the nicotine-dependent person trying to quit smoking, a tobacco chewer with no interest in quitting, or someone who has quit and is now suffering withdrawals? It doesn’t matter to the coding system; the can all be recorded as code 305.1.

Clinical Data Analytics Impact Health Care


Consider the scenario of a poor outcome for a given patient. The patient went to Dr. X’s office for significant pain and inflammation after surgery. If the physician is able to access and review the patient’s information from the hospital stay, he or she can determine the best course of action. If similar events are occurring or have occurred previously with correlating factors, such as the same procedure was performed, the physician can begin to identify why the complications have arisen. In this hypothetical scenario, the procedure was found to have used a specific lot number of surgical implants. Therefore, future readmissions of patients who have yet to be operated on can be reduced by identifying and removing the affected implants from use. Therefore, future patients will not undergo the same procedure with a malfunctioning implant. This scenario can be applied to any process or treatment practice in a healthcare organization.

Ultimately, clinical data analytics help some healthcare organization trace problems to their causes. These problems may not always involve a manufacturing defect, poor standard-of-care, or billing problem; however, the clinical data analytics definition encompasses a means of ensuring population health for a healthcare organization’s service area. By reducing complications, readmissions, errors, and inefficiencies, a healthcare organization can reduce their costs and increase their reimbursements as part of quality-based payments.