Home Machine learning-based nonlinear regression-adjusted real-time quality control modeling: a multi-center study
Article
Licensed
Unlicensed Requires Authentication

Machine learning-based nonlinear regression-adjusted real-time quality control modeling: a multi-center study

  • Yu-fang Liang , Andrea Padoan ORCID logo , Zhe Wang , Chao Chen , Qing-tao Wang EMAIL logo , Mario Plebani ORCID logo EMAIL logo and Rui Zhou EMAIL logo
Published/Copyright: November 21, 2023
Become an author with De Gruyter Brill
Submit Manuscript Author Information
Clinical Chemistry and Laboratory Medicine (CCLM)
From the journal Clinical Chemistry and Laboratory Medicine (CCLM) Volume 62 Issue 4

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.

Keywords: patient-based real-time quality control; machine learning; nonlinear regression; residual
Corresponding authors: Qing-tao Wang and Rui Zhou, Department of Laboratory Medicine, Beijing Chao-yang Hospital, Capital Medical University, Beijing, P.R. China, and Beijing Center for Clinical Laboratories, No. 8 Gongti South Road, Chaoyang District, Beijing, 100020, P.R. China, E-mail: (Q.-t. Wang), (R. Zhou); and Mario Plebani, Department of Medicine-DIMED, University of Padova, Padova, Italy, Phone: +39049663240, Fax: +39049663240, E-mail:
Yu-fang Liang, Andrea Padoan and Zhe Wang contributed equally to this work and should be considered first authors.

Funding source: Excellence project of key clinical specialty in Beijing

Funding source: Beijing Municipal Administration of Hospitals Clinical Medicine Development of Special Funding Support

Award Identifier / Grant number: ZYLX201811

Funding source: National Natural Science Foundation of China

Award Identifier / Grant number: 72374145

Acknowledgments

We thank all those who participated in this study.

  1. Research ethics: The project was approved by the local hospital Ethics Committee.

  2. Informed consent: Not applicable.

  3. Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.

  4. Competing interests: Authors state no conflict of interest.

  5. Research funding: This work was supported by Beijing Municipal Administration of Hospitals Clinical Medicine Development of Special Funding Support (ZYLX201811) , Excellence project of key clinical specialty in Beijing and National Natural Science Foundation of China (72374145).

  6. Data availability: The data are not publicly available.

References

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.Search in Google Scholar PubMed

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.Search in Google Scholar PubMed

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.Search in Google Scholar PubMed

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.Search in Google Scholar PubMed

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.Search in Google Scholar PubMed

6. Loh, TP, Lee, LC, Sethi, SK, Deepak, DS. Clinical consequences of erroneous laboratory results that went unnoticed for 10 days. J Clin Pathol 2013;66:260–1. https://doi.org/10.1136/jclinpath-2012-201165.Search in Google Scholar PubMed

7. Thaler, MA, Iakoubov, R, Bietenbeck, A, Luppa, PB. Clinically relevant lot-to-lot reagent difference in a commercial immunoturbidimetric assay for glycated hemoglobin A1c. Clin Biochem 2015;48:1167–70. https://doi.org/10.1016/j.clinbiochem.2015.07.018.Search in Google Scholar PubMed

8. Koerbin, G, Liu, J, Eigenstetter, A, Tan, CH, Badrick, T, Loh, TP. Missed detection of significant positive and negative shifts in gentamicin assay: implications for routine laboratory quality practices. Biochem Med 2018;28:010705. https://doi.org/10.11613/bm.2018.010705.Search in Google Scholar PubMed PubMed Central

9. Loh, TP, van Rossum, HH, Katayev, A, Cervinski, MA, Bietenbeck, A, Badrick, T. Patient-based real-time quality control: review and recommendations. Clin Chem 2019;65:962–71. https://doi.org/10.1373/clinchem.2019.305482.Search in Google Scholar PubMed

10. Bietenbeck, A, Cervinski, MA, Katayev, A, Loh, TP, van Rossum, HH, Badrick, T. Understanding patient-based real-time quality control using simulation modeling. Clin Chem 2020;66:1072–83. https://doi.org/10.1093/clinchem/hvaa094.Search in Google Scholar PubMed

11. Hoffmann, RG, Waid, ME. The “average of normals” method of quality control. Am J Clin Pathol 1965;43:134–41. https://doi.org/10.1093/ajcp/43.2.134.Search in Google Scholar PubMed

12. Duan, X, Wang, B, Zhu, J, Shao, W, Wang, H, Shen, J, et al.. Assessment of patient-based real-time quality control algorithm performance on different types of analytical error. Clin Chim Acta 2020;511:329–35. https://doi.org/10.1016/j.cca.2020.10.006.Search in Google Scholar PubMed

13. Smith, FA, Kroft, SH. Exponentially adjusted moving mean procedure for quality control. An optimized patient sample control procedure. Am J Clin Pathol 1996;105:44–51. https://doi.org/10.1093/ajcp/105.1.44.Search in Google Scholar PubMed

14. Neubauer, AS. The EWMA control chart: properties and comparison with other quality-control procedures by computer simulation. Clin Chem 1997;43:594–601. https://doi.org/10.1093/clinchem/43.4.594.Search in Google Scholar

15. Linnet, K. The exponentially weighted moving average (EWMA) rule compared with traditionally used quality control rules. Clin Chem Lab Med 2006;44:396–9. https://doi.org/10.1515/cclm.2006.077.Search in Google Scholar PubMed

16. Bietenbeck, A, Thaler, MA, Luppa, PB, Klawonn, F. Stronger together: aggregated Z-values of traditional quality control measurements and patient medians improve detection of biases. Clin Chem 2017;63:1377–87. https://doi.org/10.1373/clinchem.2016.269845.Search in Google Scholar PubMed

17. Jones, GR. Average of delta: a new quality control tool for clinical laboratories. Ann Clin Biochem 2016;53:133–40. https://doi.org/10.1177/0004563215581400.Search in Google Scholar PubMed

18. Zhou, R, Wang, W, Padoan, A, Wang, Z, Feng, X, Han, Z, et al.. Traceable machine learning real-time quality control based on patient data. Clin Chem Lab Med 2022;60:1998–2004. https://doi.org/10.1515/cclm-2022-0548.Search in Google Scholar PubMed

19. van Rossum, HH. Moving average quality control: principles, practical application and future perspectives. Clin Chem Lab Med 2019;57:773–82. https://doi.org/10.1515/cclm-2018-0795.Search in Google Scholar PubMed

20. Zhou, R, Liang, YF, Cheng, HL, Padoan, A, Wang, Z, Feng, X, et al.. A multi-model fusion algorithm as a real-time quality control tool for small shift detection. Comput Biol Med 2022;148:105866. https://doi.org/10.1016/j.compbiomed.2022.105866.Search in Google Scholar PubMed

21. Liang, Y, Wang, Z, Huang, D, Wang, W, Feng, X, Han, Z, et al.. A study on quality control using delta data with machine learning technique. Heliyon 2022;8:e09935. https://doi.org/10.1016/j.heliyon.2022.e09935.Search in Google Scholar PubMed PubMed Central

22. Zhou, Q, Loh, TP, Badrick, T, Lim, CY. Impact of combining data from multiple instruments on performance of patient-based real-time quality control. Biochem Med 2021;31:020705. https://doi.org/10.11613/bm.2021.020705.Search in Google Scholar PubMed PubMed Central

23. Duan, X, Wang, B, Zhu, J, Zhang, C, Jiang, W, Zhou, J, et al.. Regression-adjusted real-time quality control. Clin Chem 2021;67:1342–50. https://doi.org/10.1093/clinchem/hvab115.Search in Google Scholar PubMed

24. Loh, TP, Bietenbeck, A, Cervinski, MA, van Rossum, HH, Katayev, A, Badrick, T. Recommendation for performance verification of patient-based real-time quality control. Clin Chem Lab Med 2020;58:1205–13. https://doi.org/10.1515/cclm-2019-1024.Search in Google Scholar PubMed

25. Loh, TP, Cervinski, MA, Katayev, A, Bietenbeck, A, van Rossum, H, Badrick, T. Recommendations for laboratory informatics specifications needed for the application of patient-based real time quality control. Clin Chim Acta 2019;495:625–9. https://doi.org/10.1016/j.cca.2019.06.009.Search in Google Scholar PubMed

26. Westgard, JO, Bayat, H, Westgard, S. Advanced QC strategies: risk-based design for medical laboratories, 1st ed 7614 Gray Fox Trail Madison WI 53717: Westgard Quality Corporation; 2022:131 p.10.1016/j.cca.2021.08.028Search in Google Scholar PubMed

27. van Rossum, HH, van den Broek, D. Design and implementation of quality control plans that integrate moving average and internal quality control: incorporating the best of both worlds. Clin Chem Lab Med 2019;57:1329–38. https://doi.org/10.1515/cclm-2019-0027.Search in Google Scholar PubMed

Supplementary Material

This article contains supplementary material (https://doi.org/10.1515/cclm-2023-0964).

Received: 2023-08-31
Accepted: 2023-10-25
Published Online: 2023-11-21
Published in Print: 2024-03-25

© 2023 Walter de Gruyter GmbH, Berlin/Boston

Articles in the same Issue

  1. Frontmatter
  2. Editorial
  3. Value-based laboratory medicine: the time is now
  4. Review
  5. Cardiovascular risk evaluation in pregnancy: focus on cardiac specific biomarkers
  6. Opinion Papers
  7. From volume to value: a watershed moment for the clinical laboratory
  8. APS calculator: a data-driven tool for setting outcome-based analytical performance specifications for measurement uncertainty using specific clinical requirements and population data
  9. Guidelines and Recommendations
  10. Analytical interference of intravascular contrast agents with clinical laboratory tests: a joint guideline by the ESUR Contrast Media Safety Committee and the Preanalytical Phase Working Group of the EFLM Science Committee
  11. Genetics and Molecular Diagnostics
  12. Specifications of qPCR based epigenetic immune cell quantification
  13. General Clinical Chemistry and Laboratory Medicine
  14. An appraisal of the practice of duplicate testing for the detection of irregular analytical errors
  15. Machine learning-based nonlinear regression-adjusted real-time quality control modeling: a multi-center study
  16. The effect of ratios upon improving patient-based real-time quality control (PBRTQC) performance
  17. Diagnostic sample transport via pneumatic tube systems: data logger and their algorithms are sensitive to transport effects
  18. Ambulatory human chorionic gonadotrophin (hCG) testing: a verification of two hCG point of care devices
  19. Monitoring patients with celiac disease on gluten free diet: different outcomes comparing three tissue transglutaminase IgA assays
  20. Verification, implementation and harmonization of automated chemiluminescent immunoassays for MPO- and PR3-ANCA detection
  21. Performance evaluation of a novel platelet count parameter, hybrid platelet count, on the BC-780 automated hematology analyzer
  22. Reference Values and Biological Variations
  23. Pediatric reference intervals for serum neurofilament light and glial fibrillary acidic protein using the Canadian Laboratory Initiative on Pediatric Reference Intervals (CALIPER) cohort
  24. Biological variation of serum neopterin concentrations in apparently healthy individuals
  25. Short-term biological variation of serum tryptase
  26. Cancer Diagnostics
  27. Quantification of the lung cancer tumor marker CYFRA 21-1 using protein precipitation, immunoaffinity bottom-up LC-MS/MS
  28. Cardiovascular Diseases
  29. Prognostic significance of chronic myocardial injury diagnosed by three different cardiac troponin assays in patients admitted with suspected acute coronary syndrome
  30. Deep learning-based NT-proBNP prediction from the ECG for risk assessment in the community
  31. Diabetes
  32. Innovations in HbA1c analysis: finding the balance between speed and accuracy. An investigation of a potential new Secondary Reference Measurement Procedure for the IFCC
  33. Precise glucose measurement in sodium fluoride-citrate plasma affects estimates of prevalence in diabetes and prediabetes
  34. Infectious Diseases
  35. Urinary phenotyping of SARS-CoV-2 infection connects clinical diagnostics with metabolomics and uncovers impaired NAD+ pathway and SIRT1 activation
  36. Letters to the Editor
  37. Analytical performance specifications for measurement uncertainty in therapeutic monitoring of immunosuppressive drugs
  38. Capillary blood collection tubes containing serum separator gel result in lower measurements of oestradiol and total testosterone
  39. Re.: Louise Guillaume et al. Biological variation of CA 15-3, CA 125 and HE 4 on lithium heparinate plasma in apparently healthy Caucasian volunteers. Clin Chem Lab Med 2023;61(7):1319–1326; https://doi.org/10.1515/cclm-2022-0966
  40. A comparison of cannabidiol (CBD) concentrations in venous vs. fingertip-capillary blood
  41. Identification of sulfamethoxazole’s residues in sulfamethoxazole induced kidney stones by mass spectrometry
  42. Impact of different preservation methods on urinary red blood cell counts
  43. Diagnosis of IRAK-4-deficiency by flow cytometric measurement of IκB-α degradation
https://doi.org/10.1515/cclm-2023-0964
Keywords for this article
patient-based real-time quality control; machine learning; nonlinear regression; residual

Articles in the same Issue

  1. Frontmatter
  2. Editorial
  3. Value-based laboratory medicine: the time is now
  4. Review
  5. Cardiovascular risk evaluation in pregnancy: focus on cardiac specific biomarkers
  6. Opinion Papers
  7. From volume to value: a watershed moment for the clinical laboratory
  8. APS calculator: a data-driven tool for setting outcome-based analytical performance specifications for measurement uncertainty using specific clinical requirements and population data
  9. Guidelines and Recommendations
  10. Analytical interference of intravascular contrast agents with clinical laboratory tests: a joint guideline by the ESUR Contrast Media Safety Committee and the Preanalytical Phase Working Group of the EFLM Science Committee
  11. Genetics and Molecular Diagnostics
  12. Specifications of qPCR based epigenetic immune cell quantification
  13. General Clinical Chemistry and Laboratory Medicine
  14. An appraisal of the practice of duplicate testing for the detection of irregular analytical errors
  15. Machine learning-based nonlinear regression-adjusted real-time quality control modeling: a multi-center study
  16. The effect of ratios upon improving patient-based real-time quality control (PBRTQC) performance
  17. Diagnostic sample transport via pneumatic tube systems: data logger and their algorithms are sensitive to transport effects
  18. Ambulatory human chorionic gonadotrophin (hCG) testing: a verification of two hCG point of care devices
  19. Monitoring patients with celiac disease on gluten free diet: different outcomes comparing three tissue transglutaminase IgA assays
  20. Verification, implementation and harmonization of automated chemiluminescent immunoassays for MPO- and PR3-ANCA detection
  21. Performance evaluation of a novel platelet count parameter, hybrid platelet count, on the BC-780 automated hematology analyzer
  22. Reference Values and Biological Variations
  23. Pediatric reference intervals for serum neurofilament light and glial fibrillary acidic protein using the Canadian Laboratory Initiative on Pediatric Reference Intervals (CALIPER) cohort
  24. Biological variation of serum neopterin concentrations in apparently healthy individuals
  25. Short-term biological variation of serum tryptase
  26. Cancer Diagnostics
  27. Quantification of the lung cancer tumor marker CYFRA 21-1 using protein precipitation, immunoaffinity bottom-up LC-MS/MS
  28. Cardiovascular Diseases
  29. Prognostic significance of chronic myocardial injury diagnosed by three different cardiac troponin assays in patients admitted with suspected acute coronary syndrome
  30. Deep learning-based NT-proBNP prediction from the ECG for risk assessment in the community
  31. Diabetes
  32. Innovations in HbA1c analysis: finding the balance between speed and accuracy. An investigation of a potential new Secondary Reference Measurement Procedure for the IFCC
  33. Precise glucose measurement in sodium fluoride-citrate plasma affects estimates of prevalence in diabetes and prediabetes
  34. Infectious Diseases
  35. Urinary phenotyping of SARS-CoV-2 infection connects clinical diagnostics with metabolomics and uncovers impaired NAD+ pathway and SIRT1 activation
  36. Letters to the Editor
  37. Analytical performance specifications for measurement uncertainty in therapeutic monitoring of immunosuppressive drugs
  38. Capillary blood collection tubes containing serum separator gel result in lower measurements of oestradiol and total testosterone
  39. Re.: Louise Guillaume et al. Biological variation of CA 15-3, CA 125 and HE 4 on lithium heparinate plasma in apparently healthy Caucasian volunteers. Clin Chem Lab Med 2023;61(7):1319–1326; https://doi.org/10.1515/cclm-2022-0966
  40. A comparison of cannabidiol (CBD) concentrations in venous vs. fingertip-capillary blood
  41. Identification of sulfamethoxazole’s residues in sulfamethoxazole induced kidney stones by mass spectrometry
  42. Impact of different preservation methods on urinary red blood cell counts
  43. Diagnosis of IRAK-4-deficiency by flow cytometric measurement of IκB-α degradation
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 8.10.2025 from https://www.degruyterbrill.com/document/doi/10.1515/cclm-2023-0964/html
Scroll to top button