Title: Application of a record linkage software to identify mortality of enrolees of large integrated healthcare organisations

Authors: Yichen Zhou; Zhi Liang; Sungching Glenn; Wansu Chen; Fagen Xie

Addresses: Department of Research and Evaluation, Kaiser Permanente Southern California, 100 S. Los Robles Ave., 2nd Floor, Pasadena CA 91101, USA ' Department of Research and Evaluation, Kaiser Permanente Southern California, 100 S. Los Robles Ave., 2nd Floor, Pasadena CA 91101, USA ' Department of Research and Evaluation, Kaiser Permanente Southern California, 100 S. Los Robles Ave., 2nd Floor, Pasadena CA 91101, USA ' Department of Research and Evaluation, Kaiser Permanente Southern California, 100 S. Los Robles Ave., 2nd Floor, Pasadena CA 91101, USA ' Department of Research and Evaluation, Kaiser Permanente Southern California, 100 S. Los Robles Ave., 2nd Floor, Pasadena CA 91101, USA

Abstract: Information on mortality is important for the improvement of public health and the conduct of medical research. Healthcare organisations typically lack complete and accurate information on mortality. This paper proposes a comprehensive process to link the records of the enrolees of a healthcare organisation with the death records of 2015 obtained from the California State via a commercial data linkage software. The developed linkage process has successfully identified 23,628 and 21,009 death records of health plan enrolees from the state file after the initial and second post-linkage, respectively. Validation of the linkage process against the deaths records documented in the internal systems of the organisation achieved a sensitivity of 97.5% and a positive predictive value of 88.7% at the time of initial linkage but increased to 99.4% in three years using more information available later. The linkage process demonstrated high accuracy and can be utilised to support various business needs.

Keywords: data cleaning; data standardisation; data matching; mortality linkage.

DOI: 10.1504/IJBIDM.2023.127292

International Journal of Business Intelligence and Data Mining, 2023 Vol.22 No.1/2, pp.264 - 285

Received: 18 Jul 2021
Accepted: 14 Sep 2021
Published online: 30 Nov 2022 *