EUVIMEDEUVIMED entdecken
Crossref

From objective grouping to fuzzy reference intervals: A standardized machine learning approach for thyroid function tests

Semih Fazlı Kayahan, Muhammed Fatih Alaeddinoğlu, Mehmet Şeneş

Clinica Chimica Acta · 2026

DOI: 10.1016/j.cca.2025.120635 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Clinica Chimica Acta, 2026. Verfasst von Semih Fazlı Kayahan und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Biochemistry, Iğdır Dr. Nevruz Erez State Hospital, Iğdır, Turkey. Electronic address: semihfazlikayahan@gmail.com. Hauptthemen laut MEDLINE: Machine Learning, Thyroid Function Tests, Fuzzy Logic. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Accurate interpretation of thyroid function tests (TFTs) requires reliable reference intervals (RIs). Indirect methods based on retrospective laboratory data are increasingly used, but current strategies face major limitations, including rigid age cut-offs, inconsistent partitioning, and lack of objective evaluation of subgrouping criteria. To address these challenges, we developed a novel machine learning (ML)-based framework for the objective, data-driven determination of continuous and personalized RIs. METHODS: A total of 48,397 records (2019-2021) from individuals aged ≥18 years were retrieved from the hospital laboratory information system. After applying inclusion and exclusion criteria, 9455 individuals constituted the reference sample group. Partitioning was based on age, sex, thyroid-stimulating hormone (TSH), and free thyroxine (fT4). The Elbow method suggested the optimal number of clusters; K-means clustering was used to form subgroups, and the Extra Trees Classifier quantified the relative importance of partitioning criteria. RIs were estimated using the non-parametric percentile method, and Fuzzy C-Means clustering was applied to smooth sharp transitions between groups. RESULTS: Six subgroups were identified, with age as the dominant determinant (feature importance score = 0.96), whereas sex had a negligible effect. Fuzzy clustering generated continuous and personalized RIs. In clinical evaluation, applying fuzzy RIs reclassified 7 % of patients, predominantly shifting diagnoses toward hyperthyroidism. CONCLUSIONS: This study offers a universal and adaptable ML-based framework for generating continuous, personalized RIs. This advance toward precision laboratory medicine can enhance diagnostic accuracy, reduce misclassification, and support more patient-centered care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningThyroid Function TestsFuzzy LogicHumansFemaleMaleMiddle AgedAdultReference ValuesAgedYoung AdultRetrospective StudiesThyrotropinAdolescentThyroxine

Stichwörter der Autor:innen

Fuzzy C-meansIndirect methodMachine learningReference intervalsThyroid function tests

Substanzen

ThyrotropinThyroxine

Autor:innen und Institutionen

  • Department of Medical Biochemistry, Iğdır Dr. Nevruz Erez State Hospital, Iğdır, Turkey. Electronic address: semihfazlikayahan@gmail.com.
  • Faculty of Open and Distance Education, Atatürk University, Erzurum, Turkey.
  • Department of Medical Biochemistry, Ankara Training and Research Hospital, Ankara, Turkey.

Zitieren

APA

Kayahan, S. F., Alaeddinoğlu, M. F., & Şeneş, M. (2026). From objective grouping to fuzzy reference intervals: A standardized machine learning approach for thyroid function tests. Clinica Chimica Acta. https://doi.org/10.1016/j.cca.2025.120635

Vancouver

Kayahan SF, Alaeddinoğlu MF, Şeneş M. From objective grouping to fuzzy reference intervals: A standardized machine learning approach for thyroid function tests. Clinica Chimica Acta. 2026. doi:10.1016/j.cca.2025.120635

BibTeX
@article{Kayahan2026,
  author = {Kayahan, Semih Fazlı and Alaeddinoğlu, Muhammed Fatih and Şeneş, Mehmet},
  title = {From objective grouping to fuzzy reference intervals: A standardized machine learning approach for thyroid function tests},
  journal = {Clinica Chimica Acta},
  year = {2026},
  doi = {10.1016/j.cca.2025.120635}
}
Kostenlos starten →