Patient-based pre-classified real-time quality control with neural network (PCRTQC-NN)

Patient-based real-time quality control (PBRTQC) is essential for clinical laboratory management but struggles with detecting small systematic errors. This study presents the patient-based pre-classified real-time quality control with neural network (PCRTQC-NN) model, utilizing neural networks to im...

Full description

Saved in:
Bibliographic Details
Published in:Practical laboratory medicine Vol. 47; p. e00506
Main Authors: Zhou, Bo, Li, Xiaoying, Cheng, Shitong, Zhou, Zhiwei, Kang, Hui
Format: Journal Article
Language:English
Published: Netherlands Elsevier B.V 01.12.2025
Elsevier
Subjects:
Laboratory management
Neural network
PBRTQC
Quality control
Simulation
Laboratory management
CE
EWMA
PBRTQC
Neural network
SVM
TEA
Simulation
MA
PE
SNR
Quality control
ANPed
IQC
PCRTQC-NN
PCRTQC
MSE
ISSN:2352-5517, 2352-5517
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Patient-based real-time quality control (PBRTQC) is essential for clinical laboratory management but struggles with detecting small systematic errors. This study presents the patient-based pre-classified real-time quality control with neural network (PCRTQC-NN) model, utilizing neural networks to improve error detection by extracting analytical features from testing instruments. Using PCRTQC's clustering analysis, we pre-classified and processed Na, CHOL, ALT, and CR data from 611,031 patients. A neural network autoencoder, trained using TensorFlow with mean squared error (MSE) as the loss function, extracted the testing instrument's analytical features under error-free conditions. Systematic errors were identified by comparing reconstruction residuals between test and reconstructed data. The average number of patient samples until error detection (ANPed) evaluated the model performance. The PCRTQC-NN's error detection surpasses traditional algorithms Compared to PCRTQC, it reduced the ANPed for ALT by 37 % (constant error, CE) and 22 % (proportional error, PE) at 1 total error allowable (TEa), with comparable results for other analytes. For 0.5 TEa errors, the ANPed for CHOL decreased by 23 % (CE) and 22 % (PE), for ALT by 14 % (CE) and 6 % (PE), and for CR by 4 % (CE) and 9 % (PE), enhancing error detection capabilities for analytes with high inter-individual variability and sensitivity to smaller errors. PCRTQC-NN significantly enhances systematic error detection compared to PCRTQC, leveraging autoencoders to extract analytical features as discrete signals, thus improving SNR for high-variability analytes. It promises improved laboratory efficiency and inter-laboratory standardization via robust feature models. Future multi-center studies will validate broad applicability across diverse settings. •We extracted analytical features from the instrument via a neural network autoencoder, without additional patient clinical information.•The autoencoder can accurately predict and identify manually introduced systematic errors based on the analytical features in the standard state.•Error detection performance has improved, with increased sensitivity to small errors.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2352-5517
2352-5517
DOI:10.1016/j.plabm.2025.e00506