Triple Point Pooled Sera (TriPPS) QC for Laboratory Analyte Error Detection: A Machine Learning based Quality Control...

Area of Science:

• Clinical Chemistry
• Laboratory Medicine
• Artificial Intelligence in Healthcare

Background:

• Conventional rule-based internal quality control (IQC) systems lack sensitivity for subtle analytical shifts.
• Existing methods often detect errors retrospectively, impacting patient care.
• There is a need for advanced IQC systems in clinical laboratories.

Purpose of the Study:

• To introduce the Triple-Point Pooled Sera (TriPPS) Quality Control system, a novel machine-learning-based framework.
• To enhance error detection sensitivity and reduce detection lag in laboratory diagnostics.
• To provide a stable, matrix-relevant, and cost-efficient IQC material.

Main Methods:

• Development of TriPPS using in-house pooled patient sera for 60 days.
• Application of three machine learning models: k-Nearest Neighbour (k-NN), Isolation Forest (IF), and Gaussian Process Regression (GPR).
• Simulation of analytical drift using controlled biases and random errors for sodium and potassium analysis.

Main Results:

• k-NN detected trend errors within 0-2 days; IF identified random errors with minimal false positives.
• GPR accurately modeled nonlinear systematic drift, surpassing linear methods.
• The integrated pooled sera enhanced system stability, reproducibility, and cost-efficiency.

Conclusions:

• The TriPPS system offers a scalable, data-driven approach to laboratory quality control.
• It enhances analytical vigilance and enables proactive error identification.
• TriPPS provides a practical, resource-efficient solution for real-time QC monitoring in clinical chemistry.