Machine learning-based nonlinear regression-adjusted real-time quality control modeling: a multi-center study
Author:
Liang Yu-fang1, Padoan Andrea2ORCID, Wang Zhe3, Chen Chao3, Wang Qing-tao14, Plebani Mario5ORCID, Zhou Rui14
Affiliation:
1. Department of Laboratory Medicine, Beijing Chao-yang Hospital , Capital Medical University , Beijing , P.R. China 2. Laboratory Medicine Unit , University-Hospital of Padova , Padova , Italy 3. Beijing Jinfeng Yitong Technology Co., Ltd , Beijing , P.R. China 4. Beijing Center for Clinical Laboratories , Beijing , P.R. China 5. Department of Medicine-DIMED , University of Padova , Padova , Italy
Abstract
Abstract
Objectives
Patient-based real-time quality control (PBRTQC), a laboratory tool for monitoring the performance of the testing process, has gained increasing attention in recent years. It has been questioned for its generalizability among analytes, instruments, laboratories, and hospitals in real-world settings. Our purpose was to build a machine learning, nonlinear regression-adjusted, patient-based real-time quality control (mNL-PBRTQC) with wide application.
Methods
Using computer simulation, artificial biases were added to patient population data of 10 measurands. An mNL-PBRTQC was created using eight hospital laboratory databases as a training set and validated by three other hospitals’ independent patient datasets. Three different Patient-based models were compared on these datasets, the IFCC PBRTQC model, linear regression-adjusted real-time quality control (L-RARTQC), and the mNL-PBRTQC model.
Results
Our study showed that in the three independent test data sets, mNL-PBRTQC outperformed the IFCC PBRTQC and L-RARTQC for all measurands and all biases. Using platelets as an example, it was found that for 20 % bias, both positive and negative, the uncertainty of error detection for mNL-PBRTQC was smallest at the median and maximum values.
Conclusions
mNL-PBRTQC is a robust machine learning framework, allowing accurate error detection, especially for analytes that demonstrate instability and for detecting small biases.
Funder
Excellence project of key clinical specialty in Beijing Beijing Municipal Administration of Hospitals Clinical Medicine Development of Special Funding Support National Natural Science Foundation of China
Publisher
Walter de Gruyter GmbH
Subject
Biochemistry (medical),Clinical Biochemistry,General Medicine
Reference27 articles.
1. Bull, BS, Elashoff, RM, Heilbron, DC, Couperus, J. A study of various estimators for the derivation of quality control procedures from patient erythrocyte indices. Am J Clin Pathol 1974;61:473–81. https://doi.org/10.1093/ajcp/61.4.473. 2. Liu, J, Tan, CH, Badrick, T, Loh, TP. Moving sum of number of positive patient result as a quality control tool. Clin Chem Lab Med 2017;55:1709–14. https://doi.org/10.1515/cclm-2016-0950. 3. Liu, J, Tan, CH, Badrick, T, Loh, TP. Moving standard deviation and moving sum of outliers as quality tools for monitoring analytical precision. Clin Biochem 2018;52:112–6. https://doi.org/10.1016/j.clinbiochem.2017.10.009. 4. Miller, WG, Erek, A, Cunningham, TD, Oladipo, O, Scott, MG, Johnson, RE. Commutability limitations influence quality control results with different reagent lots. Clin Chem 2011;57:76–83. https://doi.org/10.1373/clinchem.2010.148106. 5. Algeciras-Schimnich, A, Bruns, DE, Boyd, JC, Bryant, SC, La Fortune, KA, Grebe, SK. Failure of current laboratory protocols to detect lot-to-lot reagent differences: findings and possible solutions. Clin Chem 2013;59:1187–94. https://doi.org/10.1373/clinchem.2013.205070.
|
|