Use of data mining algorithms to estimate reference intervals for laboratory biomarkers – experience report

Authors

  • Gustavo Oliveira Gonçalves FAMINAS BH https://orcid.org/0000-0003-4909-3829
  • Alan Carvalho Dias Sabin Medicina Diagnóstica. Brasília, Distrito Federal, Brasil.
  • Daniel Henrique Bücker Unidade Funcional Laboratório de Análises Clínicas do Hospital das Clínicas da Universidade Federal de Minas Gerais Belo Horizonte, Minas Gerais, Brasil. https://orcid.org/0009-0002-1098-9660
  • Leonardo de Souza Vasconcellos Departamento de Propedêutica Complementar, Faculdade de Medicina da Universidade Federal de Minas Gerais Belo Horizonte, Minas Gerais, Brasil. Programa de Pós-graduação em Ciências Aplicadas à Saúde do Adulto da Faculdade de Medicina da Universidade Federal de Minas Gerais Belo Horizonte, Minas Gerais, Brasil.

Keywords:

Reference values, Biomarkers, Laboratory Tests, Clinical Chemistry Tests, Patient safety

Abstract

The clinical laboratory is a protagonist in personalized medicine and healthcare safety. From laboratory analyzes it is possible to make important clinical decisions. The use of reference intervals (RI) appropriate to the population served becomes a priority in laboratory medicine to comply with regulatory standards and the growing demand for greater precision in the interpretation of laboratory analysis results. The laboratory needs to document the criteria, methodology and steps used to determine the IRs. The general objective of this work is to describe the experience in using the main data mining algorithms derived from the laboratory information system to estimate reference intervals of laboratory biomarkers through the indirect method approach proposed in computational tools that apply the Bhattacharya method, Kosmic, refineR and LabRI. This is a descriptive study, of the experience report type, which describes the work developed by the Clinical Pathology/Laboratory Medicine Research Group at the Federal University of Minas Gerais (GPPCML/CNPq). The most recent approaches apply data mining algorithms using computational tools (software) developed in a programming language. Considering the advantages, disadvantages, ease of use of computational tools, application of rigorous criteria for selection and increasingly robust algorithms, it is possible to consider the use of different computational tools that apply the indirect approach proposed by the Bhattacharya, Kosmic, refineR and LabRI methods.

Keywords: Reference values; Biomarkers; Laboratory Tests; Clinical Chemistry Tests; Patient safety.

Downloads

Download data is not yet available.

Author Biography

Gustavo Oliveira Gonçalves, FAMINAS BH

Biomédico, habilitado em Análises Clínicas, Docência e Auditoria. Possui experiência em instituições de ensino e saúde, de diferentes níveis e complexidade, atuando com atividades acadêmico-administrativas, gestão de equipe e foco em resultados e desenvolvimento de competências organizacionais conectado à diretriz estratégica da instituição. A vivência profissional aliada à formação acadêmica foi determinante para o desenvolvimento de competências relacionadas à coordenação de equipes, gestão por processos, pensamento da melhoria contínua e inovação, cultura para a qualidade, Ensino e Docência no Ensino Superior.

References

ABEBE, M.; MELKU, M.; ENAWGAW, B.; BIRHAN, W., et al. Reference intervals of routine clinical chemistry parameters among apparently healthy young adults in Amhara National Regional State, Ethiopia. PLoS One, v. 13, n. 8, p. e0201782, 2018.

ADELI, K.; HIGGINS, V.; TRAJCEVSKI, K.; WHITE-AL HABEEB, N. The Canadian laboratory initiative on pediatric reference intervals: A CALIPER white paper. Crit Rev Clin Lab Sci, v. 54, n. 6, p. 358-413, set. 2017.

AGARAVATT, A.; KANSARA, G.; KHUBCHANDANI, A.; SANGHANI, H., et al. Verification of Reference Interval of Thyroid Hormones With Manual and Automated Indirect Approaches: Comparison of Hoffman, KOSMIC and refineR Methods. Cureus, v. 15, n. 5, p. e39066, maio 2023.

AMMER, T.; SCHUTZENMEISTER, A.; PROKOSCH, H. U.; RAUH, M., et al. refineR: A Novel Algorithm for Reference Interval Estimation from Real-World Data. Sci Rep, v. 11, n. 1, p. 16023, 6 ago. 2021.

AMMER, T.; SCHUTZENMEISTER, A.; PROKOSCH, H. U.; ZIERK, J., et al. RIbench: A Proposed Benchmark for the Standardized Evaluation of Indirect Methods for Reference Interval Estimation. Clin Chem, v. 68, n. 11, p. 1410-1424, 3 nov. 2022.

AMMER, T.; SCHUTZENMEISTER, A.; RANK, C. M.; DOYLE, K. Estimation of Reference Intervals from Routine Data Using the refineR Algorithm-A Practical Guide. J Appl Lab Med, v. 8, n. 1, p. 84-91, 4 jan. 2023.

BRASIL. Resolução de Diretoria Colegiada nº 786, de 5 de maio de 2023. Dispõe sobre os requisitos técnico-sanitários para o funcionamento de Laboratórios Clínicos, de Laboratórios de Anatomia Patológica e de outros Serviços que executam as atividades relacionadas aos Exames de Análises Clínicas (EAC) e dá outras providências. Diário Oficial da União: Seção 1, Brasília, DF, p. 161, 5 maio 2023.

BURTIS, C. A.; BURNS, D. E. Tietz Fundamentos de Química Clínica e Diagnóstico Molecular. Tradução: RODRIGUES, F. S. M. Rio de Janeiro: Elsevier, 2016.

CERIOTTI, F.; HINZMANN, R.; PANTEGHINI, M. Reference intervals: the way forward. Ann Clin Biochem, v. 46, n. Pt 1, p. 8-17, jan. 2009.

CHEN, J.; FAN, L.; YANG, Z.; YANG, D. Comparison of results and age-related changes in establishing reference intervals for CEA, AFP, CA125, and CA199 using four indirect methods. Pract Lab Med, v. 38, p. e00353, jan. 2024.

CLSI. EP28-A3c: Defining, Establishing, and Verifying Reference Intervals in the Clinical Laboratory; Approved Guidelines - Third Edition. Wayne: Clinical and Laboratory Standards Institute, 2010.

COSKUN, A.; SANDBERG, S.; UNSAL, I.; SERTESER, M., et al. Personalized reference intervals: from theory to practice. Crit Rev Clin Lab Sci, p. 1-16, 17 maio 2022.

HAECKEL, R.; ADELI, K.; JONES, G.; SIKARIS, K., et al. Definitions and major prerequisites of direct and indirect approaches for estimating reference limits. Clin Chem Lab Med, v. 61, n. 3, p. 402-406, 23 fev. 2023.

HALLWORTH, M. J. The '70% claim': what is the evidence base? Ann Clin Biochem, v. 48, n. Pt 6, p. 487-488, nov. 2011.

HENNY, J.; VASSAULT, A.; BOURSIER, G.; VUKASOVIC, I., et al. Recommendation for the review of biological reference intervals in medical laboratories. Clin Chem Lab Med, v. 54, n. 12, p. 1893-1900, 1 dez. 2016.

HOLMES, D. T.; BUHR, K. A. Widespread Incorrect Implementation of the Hoffmann Method, the Correct Approach, and Modern Alternatives. Am J Clin Pathol, v. 151, n. 3, p. 328-336, 4 fev. 2019.

HUBER, K. R.; MOSTAFAIE, N.; STANGL, G.; WOROFKA, B., et al. Clinical chemistry reference values for 75-year-old apparently healthy persons. Clin Chem Lab Med, v. 44, n. 11, p. 1355-1360, 2006.

JONES, G. R. D.; HAECKEL, R.; LOH, T. P.; SIKARIS, K., et al. Indirect methods for reference interval determination - review and recommendations. Clin Chem Lab Med, v. 57, n. 1, p. 20-29, 19 dez. 2018.

LIU, Y. F.; WILSON, C.; BEDNY, M. Contribution of the language network to the comprehension of Python programming code. Brain Lang, v. 251, p. 105392, abr. 2024.

MA, C.; YU, Z.; QIU, L. Development of next-generation reference interval models to establish reference intervals based on medical data: current status, algorithms and future consideration. Crit Rev Clin Lab Sci, p. 1-19, 26 dez. 2023.

MA, C.; ZOU, Y.; HOU, L.; YIN, Y., et al. Validation and comparison of five data mining algorithms using big data from clinical laboratories to establish reference intervals of thyroid hormones for older adults. Clin Biochem, v. 107, p. 40-49, set. 2022.

MARTÍNEZ-SÁNCHEZ, L.; MARQUES-GARCÍA, F.; OZARDA, Y.; BLANCO, A., et al. Big data e intervalos de referencia: motivación, prácticas actuales, prerrequisitos de armonización y estandarización y futuras perspectivas en el cálculo de intervalos de referencia mediante métodos indirectos. Advances in Laboratory Medicine / Avances en Medicina de Laboratorio, v. 2, n. 1, p. 17-25, 2021.

MELILLO, K. D. Interpretation of laboratory values in older adults. Nurse Pract, v. 18, n. 7, p. 59-67, jul. 1993.

MEYER, A.; MÜLLER, R.; HOFFMANN, M.; SKADBERG, Ø., et al. Comparison of three indirect methods for verification and validation of reference intervals at eight medical laboratories: a European multicenter study. Clin Chem Lab Med, v. 47, n. 4, p. 155-163, 2023.

NAYUPE, S. F.; MBULAJE, P.; MUNHARO, S.; PATEL, P., et al. Medical laboratory practice in Malawi - Current status. Afr J Lab Med, v. 12, n. 1, p. 1921, 2023.

NILSSON, S. E.; EVRIN, P. E.; TRYDING, N.; BERG, S., et al. Biochemical values in persons older than 82 years of age: report from a population-based study of twins. Scand J Clin Lab Invest, v. 63, n. 1, p. 1-13, 2003.

OZARDA, Y. Reference intervals: current status, recent developments and future considerations. Biochem Med (Zagreb), v. 26, n. 1, p. 5-16, 2016.

OZARDA, Y.; HIGGINS, V.; ADELI, K. Verification of reference intervals in routine clinical laboratories: practical challenges and recommendations. Clin Chem Lab Med, v. 57, n. 1, p. 30-37, 19 dez. 2018.

OZARDA, Y.; ICHIHARA, K.; JONES, G.; STREICHERT, T., et al. Comparison of reference intervals derived by direct and indirect methods based on compatible datasets obtained in Turkey. Clin Chim Acta, v. 520, p. 186-195, set. 2021.,

PLEBANI, M. Towards quality specifications in extra-analytical phases of laboratory activity. Clin Chem Lab Med, v. 42, n. 6, p. 576-577, 2004.

ROHR, U. P.; BINDER, C.; DIETERLE, T.; GIUSTI, F., et al. The Value of In Vitro Diagnostic Testing in Medical Practice: A Status Report. PLoS One, v. 11, n. 3, p. e0149856, 2016.

SOCIEDADE BRASILEIRA DE PATOLOGIA CLÍNICA / MEDICINA LABORATORIAL (SBPC/ML). Norma PALC: Programa de Acreditação de Laboratórios Clínicos. São Paulo: SBPC/ML, 2021.

SOCIEDADE BRASILEIRA DE ANÁLISES CLÍNICAS (SBAC). Manual para Acreditação: Sistema de Gestão da Qualidade de Laboratórios Clínicos. 8. ed. Rio de Janeiro: SBAC, 2023.

STAPLES, T. L. Expansion and evolution of the R programming language. R Soc Open Sci, v. 10, n. 4, p. 221550, abr. 2023.

VASARHELYI, B.; DEBRECZENI, L. A. Lab Test Findings in the Elderly. EJIFCC, v. 28, n. 4, p. 328-332, dez. 2017.

VELEV, J.; LEBIEN, J.; ROCHE-LIMA, A. Unsupervised machine learning method for indirect estimation of reference intervals for chronic kidney disease in the Puerto Rican population. Sci Rep, v. 13, n. 1, p. 17198, 11 out. 2023.

WINKEL, P. A programming language and a system for automated time- and laboratory test level dependent decision-making during patient monitoring. Comput Biomed Res, v. 23, n. 5, p. 426-446, out. 1990.

YANG, C.; LANG, L.; WANG, S.; FANG, H., et al. Application of the Hoffmann, Bhattacharya, nonparametric test, and Q-Q plot methods for establishing reference intervals from laboratory databases. Clin Biochem, v. 113, p. 9-16, mar. 2023.

YANG, D.; SU, Z.; ZHAO, M. Big data and reference intervals. Clin Chim Acta, v. 527, p. 23-32, 15 fev. 2022.

ZHONG, J.; MA, C.; HOU, L.; YIN, Y., et al. Utilization of five data mining algorithms combined with simplified preprocessing to establish reference intervals of thyroid-related hormones for non-elderly adults. BMC Med Res Methodol, v. 23, n. 1, p. 108, 2 maio 2023.

ZIERK, J.; ARZIDEH, F.; KAPSNER, L. A.; PROKOSCH, H. U., et al. Reference Interval Estimation from Mixed Distributions using Truncation Points and the Kolmogorov-Smirnov Distance (kosmic). Sci Rep, v. 10, n. 1, p. 1704, 3 fev. 2020.

Published

2025-08-26

How to Cite

Gonçalves, G. O., Dias, A. C., Bücker, D. H., & Vasconcellos, L. de S. (2025). Use of data mining algorithms to estimate reference intervals for laboratory biomarkers – experience report. REVISTA CIENTÍFICA DA FAMINAS, 19(2), 931. Retrieved from https://periodicos.faminas.edu.br/index.php/RCFaminas/article/view/931

Issue

Section

Relato de experiência