Clustering of patient-derived laboratory data: A privacy-preserving distributed approach to enhance clinical laboratory quality control and regional external quality assessment
5 affiliations
- 1Laboratory Medicine Center, Zhejiang Center for Clinical Laboratories, Zhejiang Provincial People’s Hospital, Affiliated People’s Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China
- 2Department of Medical Affairs, Zhejiang Provincial People’s Hospital, Affiliated People’s Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China
- 3Department of Cilinical laboratory, Lishui Hospital of Wenzhou Medical University, The First Affiliated Hospital of Lishui University, Lishui People’s Hospital, Lishui, Zhejiang, China
- 4Department of Laboratory Medicine, Songyang People’s Hospital, Lishui, Zhejiang, China
- 5Department of Laboratory Medicine, Hangzhou Children’s Hospital, Hangzhou, Zhejiang, China
Abstract
Background: Traditional quality control (QC) has inherent limitations, and there are still various challenges existing in patient-based real-time QC (PBRTQC) and patient-based quality assurance (PBQA). We developed an integrated PBRTQC-PBQA model using density-based clustering and evaluated its effectiveness as a regional clinical laboratory quality assurance tool. Methods: A 20-month multicentre study across seven hospitals analysed five haematological analytes(white blood cell count [WBC], red blood cell count [RBC], haemoglobin [HGB], platelet count [PLT], and mean corpuscular volume [MCV]). Custom Clustering-PBRTQC-PBQA(CPP) models were developed using log/Box-Cox transformation, 3D spatial construction with companion analytes determined by distribution morphology, Mahalanobis distance filtering (chi-square = 0.3, ~ 47% exclusion rate), and iterative OPTICS clustering to identify hospital-specific core reference populations. A privacy-preserving distributed architecture transmitted only aggregated statistical summaries. Median/EWMA harts (PBRTQC) and Z-score/relative bias charts (PBQA) were created alongside a closed-loop quality improvement system and calibration event verification. Results: The CPP model reduced EWMA alert episodes by 25.0% (92–69) while increasing 1-3S alert episodes by 31.2% (64–84) compared with conventional moving-average PBRTQC, demonstrating selective elimination of systematic bias signals while preserving sensitivity to random errors (net change: 180–173 episodes, −3.9%). Overall calibration consistency was 82.3% (95% CI: 74.1%−88.7%). Among 52 confirmed true-positive alerts, 37 (71.2%) were detected without concurrent internal QC out-of-control signals, demonstrating the model’s capacity to capture low-magnitude biases that conventional IQC misses. Conclusion: Density-based clustering underpins the PBRTQC-PBQA model’s effectiveness in deriving hospital-specific core reference values, filtering unconfirmed QC alerts, validating calibration, and enhancing regional test consistency. The model’s ability to detect systematic biases not captured by IQC underscores its value as a complementary quality assurance layer. Its lightweight design supports regional deployment.
Related
- Comparative Assessment of Laboratory Safety Practices Among Biology Students and Teachers in Abeokuta, Nigeria
- Cognitive Control Neural Correlates of Negative Affective in Psychosis Spectrum Disorders: A Laboratory and Ecological Momentary Assessment Study
- Laboratory-based nutritional risk assessment including GDF15 in cirrhosis: a multicenter retrospective study
- CO112 | LIPOPROTEIN(a) PLASMA LEVELS AND COAGULATION BIOMARKERS: RESULTS FROM A COMPREHENSIVE LABORATORY ASSESSMENT IN AN ANGIOGRAPHICALLY-CONTROLLED CARDIOVASCULAR COHORT
- Integrating Anti-SARS-CoV-2 Spike Protein IgG, IL-6, and NK Cell Percentage with Routine Laboratory Markers for COVID-19 Severity Assessment: Development and Validation of the CORIS Nomogram.
BibTeX
@article{song2026clustering,
title = {{Clustering of patient-derived laboratory data: A privacy-preserving distributed approach to enhance clinical laboratory quality control and regional external quality assessment}},
author = {Chao Song and Qian Chen and Chunsheng Qu and Liqing Xu and Zhiming Shan and Jun Zhou and Weixing Li},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0359083},
url = {https://doi.org/10.1371/journal.pone.0359083},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Clustering of patient-derived laboratory data: A privacy-preserving distributed approach to enhance clinical laboratory quality control and regional external quality assessment
AU - Chao Song
AU - Qian Chen
AU - Chunsheng Qu
AU - Liqing Xu
AU - Zhiming Shan
AU - Jun Zhou
AU - Weixing Li
PY - 2026
DA - 2026/10/16
JO - PLOS One
DO - 10.1371/journal.pone.0359083
UR - https://doi.org/10.1371/journal.pone.0359083
AB - Background: Traditional quality control (QC) has inherent limitations, and there are still various challenges existing in patient-based real-time QC (PBRTQC) and patient-based quality assurance (PBQA). We developed an integrated PBRTQC-PBQA model using density-based clustering and evaluated its effectiveness as a regional clinical laboratory quality assurance tool. Methods: A 20-month multicentre study across seven hospitals analysed five haematological analytes(white blood cell count [WBC], red blood cell count [RBC], haemoglobin [HGB], platelet count [PLT], and mean corpuscular volume [MCV]). Custom Clustering-PBRTQC-PBQA(CPP) models were developed using log/Box-Cox transformation, 3D spatial construction with companion analytes determined by distribution morphology, Mahalanobis distance filtering (chi-square = 0.3, ~ 47% exclusion rate), and iterative OPTICS clustering to identify hospital-specific core reference populations. A privacy-preserving distributed architecture transmitted only aggregated statistical summaries. Median/EWMA harts (PBRTQC) and Z-score/relative bias charts (PBQA) were created alongside a closed-loop quality improvement system and calibration event verification. Results: The CPP model reduced EWMA alert episodes by 25.0% (92–69) while increasing 1-3S alert episodes by 31.2% (64–84) compared with conventional moving-average PBRTQC, demonstrating selective elimination of systematic bias signals while preserving sensitivity to random errors (net change: 180–173 episodes, −3.9%). Overall calibration consistency was 82.3% (95% CI: 74.1%−88.7%). Among 52 confirmed true-positive alerts, 37 (71.2%) were detected without concurrent internal QC out-of-control signals, demonstrating the model’s capacity to capture low-magnitude biases that conventional IQC misses. Conclusion: Density-based clustering underpins the PBRTQC-PBQA model’s effectiveness in deriving hospital-specific core reference values, filtering unconfirmed QC alerts, validating calibration, and enhancing regional test consistency. The model’s ability to detect systematic biases not captured by IQC underscores its value as a complementary quality assurance layer. Its lightweight design supports regional deployment.
SN - 1932-6203
ER -