EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Simulation-based comparison of unsupervised anomaly detection and conventional multi-rules for clinical biochemistry quality control

Muhammad Haseeb Tariq, Claire Price, Ahmed Laher, Melissa Harrison, Mariam Ammoun, Afreenish Amir, Muhammad Muneeb Tariq

British Journal of Biomedical Science · 17.11.2026 · 83

DOI: 10.3389/bjbs.2026.17568 ↗

Kurz gefasst

Fachartikel in der Zeitschrift British Journal of Biomedical Science, online erschienen am 17.11.2026. Verfasst von Muhammad Haseeb Tariq und 6 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Internal quality control is commonly carried out using rule-based systems such as Westgard multirules and the exponentially weighted moving average. However, these methods may be slow to detect gradual drift and imprecision changes in current analyzers. Unsupervised anomaly detection algorithms, trained on in-control quality control data, provide an additional data-driven approach that does not require patient data.

Methods

We generate synthetic IQC data with four faults: a +2 SD step shift, a linear trend to +2 SD, an abrupt doubling of the SD, and intermittent ±4 SD outliers (3% of post-onset runs) on a standardized z-scale, including 54,000 QC-level series (12 analyte labels × 3 QC levels × 5 scenarios × 300 replications). We used Holm-corrected paired tests and bootstrap confidence intervals to summarise delay per replication (median across 12 analytes); outlier delay was calculated from the first injected outlier, and delay in fault-free streams served as the no-fault reference. A severity sweep changed the fault’s trajectory and size.

Results

Step shifts had median delays of 0.0–2.0 runs, while sudden imprecision increases had median delays of 0.5–3.5 runs, with CUSUM being the slowest. Delays from the initial injected outlier were 1.0 for EWMA, 12.5 for CUSUM, and 0.0 runs for Westgard, Isolation Forest, and One-Class SVM. The median delays for the trend were 19.8 (EWMA), 23.5 (Isolation Forest), 30.0 (Westgard), 31.5 (One-Class SVM), and 44.0 runs (CUSUM). Except for CUSUM, the trend delays were only roughly 2–7 runs shorter than the time to first alert in fault-free streams, and the false-alarm rates (2.2–5.2 per 100 analyte-runs) did not match. Most of the machine-learning discrimination was explained by engineered temporal features (imprecision AUC for Isolation Forest 0.93 with all features versus 0.70 with z and |z| only).

Conclusion

No method was consistently the fastest; instead, performance varied by defect type and false-alarm operating point. Discrepancies in the false-alarm rate were a major factor in explaining apparent discrepancies between techniques for slowly developing trends. Validation using actual laboratory QC data is necessary because these standardized simulations do not show clinical benefit.

Zitieren

APA

Tariq, M. H., Price, C., Laher, A., Harrison, M., Ammoun, M., Amir, A., & Tariq, M. M. (2026). Simulation-based comparison of unsupervised anomaly detection and conventional multi-rules for clinical biochemistry quality control. British Journal of Biomedical Science, 83. https://doi.org/10.3389/bjbs.2026.17568

Vancouver

Tariq MH, Price C, Laher A, Harrison M, Ammoun M, Amir A, et al. Simulation-based comparison of unsupervised anomaly detection and conventional multi-rules for clinical biochemistry quality control. British Journal of Biomedical Science. 2026;83. doi:10.3389/bjbs.2026.17568

BibTeX
@article{Tariq2026,
  author = {Tariq, Muhammad Haseeb and Price, Claire and Laher, Ahmed and Harrison, Melissa and Ammoun, Mariam and Amir, Afreenish and Tariq, Muhammad Muneeb},
  title = {Simulation-based comparison of unsupervised anomaly detection and conventional multi-rules for clinical biochemistry quality control},
  journal = {British Journal of Biomedical Science},
  year = {2026},
  volume = {83},
  doi = {10.3389/bjbs.2026.17568}
}
Kostenlos starten →