Using ‘big data’ to validate claims made in the pharmaceutical approval process

Abstract

Big Data in the healthcare setting refers to the storage, assimilation, and analysis of large quantities of information regarding patient care. These data can be collected and stored in a wide variety of ways including electronic medical records collected at the patient bedside, or through medical records that are coded and passed to insurance companies for reimbursement. When these data are processed it is possible to validate claims as a part of the regulatory review process regarding the anticipated performance of medications and devices. In order to analyze properly claims by manufacturers and others,

Greater Expectations for Pharmaceutical Value: Better Care, Healthier People, Smarter Spending

“…To address the gap between current practice and the valuebased payment approaches that have emerged, Dr. Langley and colleagues have published a series of commentaries that lay a foundation for taking next steps in validating pharmaceutical product claims [13][14][15][16][17]. The principles are rooted in (1) addressing value-based care, (2) making evaluations practical, (3) using technical standards, (4) developing validation protocols, (5) using explicit formats, (6) conducting formal review, and (7) collaborating on access to data [13][14][15][16][17].…”

“…The principles are rooted in (1) addressing value-based care, (2) making evaluations practical, (3) using technical standards, (4) developing validation protocols, (5) using explicit formats, (6) conducting formal review, and (7) collaborating on access to data [13][14][15][16][17]. They have proposed that evaluating claims for pharmaceutical products and devices should be seen as a necessary part of any program of continuous quality improvement in health care delivery.…”

Imaginary Worlds: The Status of Modeled Quality Adjusted Life Year Claims for New Oral Anticoagulants in Atrial Fibrillation Published Between January 2012 and February 2016

“…These endpoints are currently accessible from claims data and from electronic medical records 71 . A recent presentation, for example, to the American College of Cardiology in April 2016 reports on a comparison of differences between rivaroxaban, dabigatran and apixaban in preventing stroke or systemic embolism in patients with atrial fibrillation 72 .…”

Development of stroke identification algorithm for claims data using the multicenter stroke registry database

“…Claims data, as one type of "big data," have been actively used for medical research by virtue of a large number of cases, a long period of observation, comprehensiveness, and representativeness of data, especially where a national insurance system encompasses the entire population. [1][2][3][4] In stroke research, claims data are increasingly being used for epidemiological, qualityof-care, and cost studies. [5][6][7][8][9][10][11][12][13] However, there are crucial limitations in previous claims data-based studies with respect to identification of stroke cases.…”