AUTHOR=Tariq Muhammad Haseeb , Price Claire , Laher Ahmed , Harrison Melissa , Ammoun Mariam , Amir Afreenish , 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 VOLUME=Volume 83 - 2026 YEAR=2026 URL=https://www.frontierspartnerships.org/journals/british-journal-of-biomedical-science/articles/10.3389/bjbs.2026.17568 DOI=10.3389/bjbs.2026.17568 ISSN=2474-0896 ABSTRACT=BackgroundInternal 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.MethodsWe 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.ResultsStep 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).ConclusionNo 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.