Information-theoretic multistage sampling framework for medical audits

News

  • Author: Muzaffer Musal and Tahir Ekin
  • Date: 03 May 2019
  • Copyright: Image copyright of Patrick Rhodes

The sampling resource allocation decisions for medical audits of outpatient procedures are crucial and challenging because of the large payment amounts and heterogeneity of the claims. A number of frameworks are utilized to help auditors address the trade‐offs between efficiency and cost while having valid overpayment amount estimates. As a potential improvement, a paper published in Applied Stochastic Models in Business and Industry presents a novel information‐theoretic multistage sampling framework. In particular, we propose an iterative stratified sampling method that uses Lindley's entropy measure to evaluate the expected amount of information. We use US Medicare Part B claims outpatient payment data and investigate the versatility of the framework for different overpayment scenarios and resource allocation designs.

The paper is available via this link and the authors explain their findings below:

Information‐theoretic multistage sampling framework for medical audits

Muzaffer Musal and Tahir Ekin

Applied Stochastic Models in Business and Industry, Volume 34, Issue 6, November/December 2018, pages 893-907

thumbnail image: Information-theoretic multistage sampling framework for medical audits

Health care expenditures constitute a significant portion of the governmental budgets, especially in developed countries with high median age populations. It is estimated that up to 10 percent of annual health care spending is lost to fraudulent transactions. The complexity of healthcare industry makes it attractive for fraudsters, therefore medical fraud assessment has gained more importance. The utilization of statistical methods in medical fraud assessment is paramount because of the size of the healthcare systems. There are more than a billion claims processed every year. Auditing medical records for fraud analysis requires the collaboration of multiple subject matter experts, which makes comprehensive auditing infeasible because of lack of time and resources. Therefore, selection of a representative group of claim samples for investigations is important for auditors. The results of these samples are extrapolated to estimate overpayments for the overall population of claims and the margin of error is reported. In addition to having a small margin of error, efficient allocation of investigation resources is important. Currently used procedures generally divide the medical claims data into groups with respect to a variable of interest such as payment amounts.

This paper suggests a novel multi stage framework based on information theoretic tools. In particular, a multiple stage perspective is proposed in which the information on the uncertainty of fraud is computed after audit of every claim. The decisions to select the group to audit from are based on the updated information involving the likelihood of fraud. A comparison between the current and the proposed methods is presented by using a real-life payment dataset and the simulations of fraud data under different uncertainty scenarios for fraud. The proposed method results in reasonable coverage and lower estimation errors for proportion of overpaid claims and overpayment recovery amounts for a variety of scenarios. The efficiency gains are highest when the overpayment probabilities are different across groups. The framework also can be used to make probability statements on variables of interest, such as number of overpaid claims. Such evaluation of information of the samples can be especially beneficial for outpatient procedures with high medical audit costs. Moreover, the proposed method is general; and it can be adapted to settings that can benefit from an iterative stratified sampling framework.

Related Topics

Related Publications

Related Content

Site Footer

Address:

This website is provided by John Wiley & Sons Limited, The Atrium, Southern Gate, Chichester, West Sussex PO19 8SQ (Company No: 00641132, VAT No: 376766987)

Published features on StatisticsViews.com are checked for statistical accuracy by a panel from the European Network for Business and Industrial Statistics (ENBIS)   to whom Wiley and StatisticsViews.com express their gratitude. This panel are: Ron Kenett, David Steinberg, Shirley Coleman, Irena Ograjenšek, Fabrizio Ruggeri, Rainer Göb, Philippe Castagliola, Xavier Tort-Martorell, Bart De Ketelaere, Antonio Pievatolo, Martina Vandebroek, Lance Mitchell, Gilbert Saporta, Helmut Waldl and Stelios Psarakis.