Machine learning-based delta check method for detecting misidentification errors in tumor marker tests
Author:
Seok Hyeon Seok1ORCID, Choi Yuna2ORCID, Yu Shinae3ORCID, Shin Kyung-Hwa4ORCID, Kim Sollip2ORCID, Shin Hangsik5ORCID
Affiliation:
1. Interdisciplinary Program of Biomedical Engineering , Chonnam National University , Yeosu , Republic of Korea 2. Department of Laboratory Medicine, Asan Medical Center , University of Ulsan College of Medicine , Seoul , Republic of Korea 3. Department of Laboratory Medicine, Haeundae Paik Hospital , Inje University College of Medicine , Busan , Republic of Korea 4. Department of Laboratory Medicine and Biomedical Research Institute , Pusan National University Hospital , Busan , Republic of Korea 5. Department of Digital Medicine, Asan Medical Center , University of Ulsan College of Medicine , Seoul , Republic of Korea
Abstract
Abstract
Objectives
Misidentification errors in tumor marker tests can lead to serious diagnostic and treatment errors. This study aims to develop a method for detecting these errors using a machine learning (ML)-based delta check approach, overcoming limitations of conventional methods.
Methods
We analyzed five tumor marker test results: alpha-fetoprotein (AFP), cancer antigen 19-9 (CA19-9), cancer antigen 125 (CA125), carcinoembryonic antigen (CEA), and prostate-specific antigen (PSA). A total of 246,261 records were used in the analysis. Of these, 179,929 records were used for model training and 66,332 records for performance evaluation. We developed a misidentification error detection model based on the random forest (RF) and deep neural network (DNN) methods. We performed an in silico simulation with 1 % random sample shuffling. The performance of the developed models was evaluated and compared to conventional delta check methods such as delta percent change (DPC), absolute DPC (absDPC), and reference change values (RCV).
Results
The DNN model outperformed the RF, DPC, absDPC, and RCV methods in detecting sample misidentification errors. It achieved balanced accuracies of 0.828, 0.842, 0.792, 0.818, and 0.833 for AFP, CA19-9, CA125, CEA, and PSA, respectively. Although the RF method performed better than DPC and absDPC, it showed similar or lower performance compared to RCV.
Conclusions
Our research results demonstrate that an ML-based delta check method can more effectively detect sample misidentification errors compared to conventional delta check methods. In particular, the DNN model demonstrated superior and stable detection performance compared to the RF, DPC, absDPC, and RCV methods.
Funder
Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea
Publisher
Walter de Gruyter GmbH
Subject
Biochemistry (medical),Clinical Biochemistry,General Medicine
Reference18 articles.
1. Desai, S, Guddati, AK. Carcinoembryonic antigen, carbohydrate antigen 19-9, cancer antigen 125, prostate-specific antigen and other cancer markers: a primer on commonly used cancer markers. World J Oncol 2023;14:4–14. https://doi.org/10.14740/wjon1425. 2. Chang, J, Kim, S, Yoo, SJ, Park, EJ, Um, TH, Cho, CR. Preanalytical errors in the Central Laboratory of a University Hospital based on the analysis of year-round data. Clin Lab 2020;66:1783–91. https://doi.org/10.7754/clin.lab.2020.200110. 3. Lippi, G, Chance, JJ, Church, S, Dazzi, P, Fontana, R, Giavarina, D, et al.. Preanalytical quality improvement: from dream to reality. Clin Chem Lab Med 2011;49:1113–26. https://doi.org/10.1515/cclm.2011.600. 4. Lippi, G, Cadamuro, J, von Meyer, A, Simundic, AM, European Federation of Clinical C, Laboratory Medicine Working Group for Preanalytical P. Practical recommendations for managing hemolyzed samples in clinical chemistry testing. Clin Chem Lab Med 2018;56:718–27. https://doi.org/10.1515/cclm-2017-1104. 5. Clinical and Laboratory Standards Institute. Use of delta checks in the medical laboratory, 2nd ed. Wayne, PA, USA: CLSI guideline EP33; 2023.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|