İç Kalite Kontrol Süreçlerinde Geçmiş ve Gelecekteki Kontrol Dışı Olayları Tahmin Etmede Yeni Bir Paradigma: Makine Öğrenimi için Gaussian Modeli

Öz

İç Kalite Kontrol (İKK), hasta numunelerini çalıştırmadan önce bir laboratuvar testinin güvenilirliğini değerlendirme ve kontrol etme sürecidir. Mevcut İKK süreci, kural tabanlı yaklaşımlar kullanarak Toplam Analitik Hatanın (TAE) yönetimine odaklanmaktadır. Toplam İzin Verilebilir Hata (TEa) ihlallerinin zamanlamasını tam olarak tahmin edemez. Çalışmada, Tahmine Dayalı Kalite Kontrol Algoritması (PQCA) için Gaussian Process for Machine Learning (GPML) yöntemini kullanarak İKK sürecini değerlendirmede tahmine dayalı bir hesaplama yaklaşımı önerildi. Python ve Scikit-learn kütüphanesinde yürütülen yazılım uygulaması, Windows tabanlı standart bir PC üzerinde çalıştırıldı. PQCA’ya dayalı bir dijital kontrol tablosu oluşturuldu. Gözlemlerin, PQCA tarafından üretilen karşılık gelen tahminlerinin %95 güven aralığı içinde kaldığı gösterildi. Ayrıca, klasik formül kullanılarak hesaplanan TAE’nin tüm TEa ihlallerini yakalayamadığı da ortaya konuldu. PQCA, ham kontrol verilerini doğrudan kalite hedefleriyle ilişkilendirebilen basit bir prosedür olup, yüksek derecede doğrulukla tahmine dayalı bir yaklaşım sağlamıştır. Klasik TAE hesaplama modeli, tek değişkenli bir Gauss modeline dayanır. PQCA’nın temel aldığı GPML, çok değişkenli bir Gaussian modeldir. Bu nedenle PQCA, klasik IQC modelinin bir genellemesi olarak görülebilir. Laboratuvarlar, PQCA’yı kullanarak analitik kalitenin kontrolüne proaktif bir yaklaşım getirebilir, düzenleyici kurumların gereksinimlerini karşılayabilir ve dolayısıyla daha doğru ve güvenilir hasta sonuçları sağlayabilir. PQCA tabanlı İKK, geleneksel yöntemlerin eksikliklerinin üstesinden gelen tek bir algoritma kullanarak analitik değişkenliğin kontrolünü sağlayabilir. Gelecekte, yeni kullanılabilir hesaplama modelleri, İKK için daha karmaşık, tahmine dayalı matematiksel çerçeveleri mümkün kılacaktır.

Anahtar Kelimeler

• Kalite güvencesi
• iç kalite kontrolü
• Gauss Süreci Makine Öğrenimi
• tahmine dayalı kalite kontrol algoritması
• kalite kontrol prosedürü
• toplam analitik hata

A New Paradigm For Predicting Past And Future Out of Control Events In Internal Quality Control: Gaussian Process For Machine Learning

Abstract

controlling the reliability of a laboratory test before running patient samples. Currently used IQC process focus on the management of Total Analytical Error (TAE) using rule-based approaches. The process cannot predict timings of Total Allowable Error (TEa) violations, precisely. In the study, we proposed a predictive computational approach for IQC, Predictive Quality Control Algorithm (PQCA), to solve with this problem using Gaussian Process for Machine Learning (GPML) method. The software implementation carried out in Python and Scikit-learn library running on a standard Windows-based PC. A digital control chart based on PQCA was introduced. It is demonstrated that observations fall within the 95% confidence intervals of their corresponding predictions generated by PQCA. It also presented that TAE calculated using classical formula is unable to capture all violations of TEa. PQCA is a simple procedure that can directly relate raw control data to quality targets and enabled a predictive approach with a high degree of accuracy. The classical TAE calculation model is based on a univariate Gaussian model. GPML, which PQCA is based on, is generalized by a multivariate Gaussian. Therefore, PQCA can be viewed as a generalization of the classical IQC model. Using PQCA, laboratories can take a proactive approach to the control of analytical quality, meet regulatory institutions’ requirements, and hence provide better patient outcomes. PQCA based IQC can achieve controlling of analytical variability using a single algorithm overcoming the shortcomings of conventional methods. In the future, newly available computational models make possible more sophisticated, predictive mathematical frameworks for IQC.

Keywords

• Quality assurance
• internal quality control
• Gaussian Process Machine Learning
• predictive quality control algorithm
• quality control procedure

References

1. 1. Clinical and Laboratory Standards Institute (CLSI). Statistical Quality Control for Quantitative Measurement Procedures: Principles and Definitions; Approved Guideline—Third Edition. CLSI document C24-A3 (ISBN 1-56238-613-1). 2006 Vol. 26 No. 25. Clinical and Laboratory Standards Institute, 950 West Valley Road, Suite 2500, Wayne, Pennsylvania 19087 USA, 2006. Clinical & Laboratory Standards Institute C24-A3. Statistical Quality Control for Quantitative Measurement Procedures: Principles and Definitions; Approved Guideline— Third Edition.
2. 2. United States Department of Health and Human Services. Medicare, Medicaid, and CLIA programs: regulations implementing the Clinical Laboratory Improvement Amendments of 1988 (CLIA). Final rule. 57 Federal Register 7002-7186; 1992. Available at: www.phppo.cdc.gov/clia/regs/toc.aspx. Accessed February 11, 2020.
3. 3. Westgard JO, Barry PL, Hunt MR, Groth T. A multi-rule Shewhart chart for quality control in clinical chemistry. Clin Chem 1981;27:493-501.
4. 4. Westgard JO, Westgard SA. Measuring Analytical Quality: Total Analytical Error Versus Measurement Uncertainty. Clin Lab Med 2017;37 (1):1-13.
5. 5. https://www.westgard.com/biodatabase1.htm. Accessed December 27, 2022.
6. 6. Rasmussen CE, Williams CKI. Gaussian processes for machine learning, Cambridge (MA): the MIT Press, 2006, p. 13-21, ISBN 026218253X.
7. 7. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in Python. Journal of machine learning research 2011;12:2825-30.
8. 8. Futoma J, Sendak M, Cameron CB, Heller K. Scalable modeling of multivariate longitudinal data for prediction of chronic kidney disease progression. Machine Learning and Healthcare Conference, Los Angeles, CA. 2016, eprint arXiv:1608.046152016arXiv160804615F

9. 9. Colopy GW, Pimentel MAF, Roberts SJ, Clifton DA. Bayesian gaussian processes for identifying the deteriorating patient. 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL. 2016, 5311-4 p. doi: 10.1109/EMBC.2016.7591926
10. 10. Forouzanfar MH, Liu P, Roth GA, Ng M, Biryukov S, Marczak L, et. al. Global burden of hypertension and systolic blood pressure of at least 110 to 115 mm Hg, 1990-2015. JAMA. 2017;317(2):165–82. doi:10.1001/jama.2016.1904.
11. 11. Rasmussen CE, Williams CKI. Gaussian processes for machine learning, Cambridge (MA): the MIT Press, 2006, p. 79-85, ISBN 026218253X.
12. 12. Challen R, Denny J, Pitt M, Gompels L, Edwards T, Tsaneva-Atanasova. Artificial intelligence, bias and clinical safety. BMJ Qual Saf 2019;28:231–237.
13. 13. 510(K) Summary: DiffMaster Octavia. https://www.accessdata.fda.gov/cdrh_docs/pdf/K003301.pdf. Accessed February 11, 2020.
14. 14. Pancholi P, Carroll KC, Buchan BW et al. Multicenter evaluation of the accelerate phenotest BC kit for rapid identification and phenotypic antimicrobial susceptibility testing using morphokinetic cellular analysis. J Clin Microbiol 2018;56:4:1-21.
15. 15. Cao Y, Cheng M, Hu C. UrineCART, a machine learning method for establishment of review rules based on UF-1000i flow cytometry and dipstick or reflectance photometer. Clin Chem Lab Med 2012;50:2155-61.
16. 16. Durant TJS, Olson EM, Schulz WL et al. Very deep convolutional neural networks for morphologic classification of erythrocytes. Clin Chem 2017;63:1847-55.
17. 17. Wilkes EH, Rummsby G, Woodward GM. Using machine learning to aid the interpretation of urine steroid profiles. Clin Chem 2018;64(11):1586-95.
18. 18. Demirci F, Akan P, Kume T et al. Artifical neural network approach in laboratory test reporting: learning algorithms. Am J Clin Pathol 2016;146:227-37.
19. 19. Luo Y, Szolovits P, Anand S. Dighe AS, Baron JM. Using Machine Learning to Predict Laboratory Test Results. Am J Clin Pathol 2016;145:778-88.
20. 20. Guncar G, Kukar M, Notar M, Brvar M, et al. An application of machine learning to haematological diagnosis. Sci Rep 2018;8:411.
21. 21. Yardim, M. Total analytical error assessment of Yerköy State Hospital biochemistry laboratory. International Journal of Medical Biochemistry 2022, 5(1),