Related Experiment Video
Updated: Jun 23, 2025

qPCR Is a Sensitive and Rapid Method for Detection of Cytomegaloviral DNA in Formalin-fixed, Paraffin-embedded Biopsy Tissue
Published on: July 9, 2014
Establishment and evaluation of Voting algorithm-based internal quality control (ViQC), a patient-based real-time
Yuan Liu1, Hexiang Zheng2, Wanying Zhang1
1Department of Laboratory Medicine, Nanjing Drum Tower Hospital Clinical College of Nanjing Medical University, Nanjing, Jiangsu, China.
An AI-powered Voting algorithm based internal quality control (ViQC) system enhances patient-based real-time quality control (PBRTQC) by improving error detection efficiency. This advanced method significantly reduces the number of patient samples needed for error identification in clinical settings.
Area of Science:
- Clinical Chemistry
- Artificial Intelligence in Healthcare
- Quality Control Systems
Background:
- Patient-Based Real-Time Quality Control (PBRTQC) is a supplementary program to traditional internal quality control (iQC).
- Existing PBRTQC systems face practical challenges in clinical settings, necessitating improved precision and reliability.
- Artificial Intelligence (AI) offers potential solutions for enhancing quality control mechanisms in healthcare.
Purpose of the Study:
- To introduce and develop an AI-based method, Voting algorithm based iQC (ViQC), for PBRTQC.
- To enhance the precision and reliability of existing PBRTQC systems using AI.
- To evaluate the analytical performance and clinical efficacy of the ViQC algorithm.
Main Methods:
- Retrospective analysis of 111,925 inpatient serum glucose test results from Nanjing Drum Tower Hospital.
- Development of the Voting iQC (ViQC) algorithm based on Voting algorithm principles.
- Evaluation of analytical performance via random error (RE) calculation and comparison with five statistical algorithms (MA, EWMA, MM, MQ, MovSD).
Main Results:
- The ViQC model, incorporating various machine learning models, demonstrated exceptional precision with a false positive rate below 0.002.
- ViQC achieved high accuracy (0.965) at an error factor of 2.0 and an AUC exceeding 0.97 for all evaluated error factors.
- Compared to conventional PBRTQC methods, ViQC significantly improved error detection efficiency, reducing required patient samples from 724 to 168.
Conclusions:
- The AI-based PBRTQC system (ViQC) demonstrated satisfactory performance in a real-world setting.
- ViQC offers superior error detection capabilities compared to traditional PBRTQC statistical methods.
- The developed ViQC algorithm enhances the reliability and efficiency of quality control in clinical laboratory testing.
More Related Videos
Related Concept Videos
Quality Assurance
Detection of Gross Error: The Q Test
Introduction to Statistical Process Control
Data Validation
Nursing assessment guides are generally based on holistic models rather than medical...
Health Information Technology and Healthcare Information System
Health Information Technology, commonly called HIT, integrates advanced information systems and technology in healthcare settings. Its primary functions include:
Systematic Sampling Method
Systematic sampling is one of the simplest methods...

