Automated Prozone Effect Detection in Ferritin Homogeneous Immunoassays Using Neural Network Classifiers

Abstract

The application of turbidimetric homogeneous immunoassays made the determination of several plasma components widely available. The sensitivity and accuracy of these assays are appropriate enough for routine laboratory use; however, in the case of many pathologically high concentration samples, prozone effect (high dose hook effect) can be observed, that leads to false-negative determination. Up to the present there are no cost-effective algorithms available for the safe detection of the prozone effect. Pathological serum ferritin values can be elevated up to 5000 ng/ml, while the measuring range covers only the 0-440 ng/ml range by a commercial assay. The determination of samples with ferritin concentration higher than 1500 ng/ml results in false-negative values because of the overlapping measuring range and prozone effect range. The prozone effect can be recognised by analysis of reaction kinetics after measurement. We have developed a neural network classifier system to analyse reaction kinetics of the measurements and check the prozone effect. One thousand five hundred determinations and 77 patient samples were used for neural network training and test. Using the trained neural networks, false-negative results can be filtered immediately after the determination, without re-run; thus, the sensitivity of plasma ferritin determination may become reliable enough, even in the case of high concentration samples. Applying this new technology, false-negative serum ferritin determinations can be avoided, thus even a relatively high hook effect rate (5-12% in different patient groups) can be handled safely.

Upfront dilution of ferritin samples to reduce hook effect, improve turnaround time and reduce costs

“…Our approach avoids this by having upfront dilutions programmed on the instrument. In addition, our approach is simple and does not require the expertise to implement more complex approaches, such as neural learning networks ( 6 ).…”

“…Some have instituted a separate orderable for when there is clinical suspicion hook effect might occur ( 5 ). Others have employed neural learning networks to evaluate reaction curves and detect hook effect ( 6 ). With regards to lateral flow assays, recent efforts have been reported that investigate reaction kinetics to reduce hook effect ( 7 ).…”

Analysis of the applicability of artificial neural networks for studying blood plasma: determination of magnesium ion concentration as a case study

“…Many results have shown that ANNs are suitable tools for medical classification and prediction tasks and examples of these applications can be seen in Refs. (9)(10)(11)(12)(13)(14)(15)(16). The ability of ANNs to differentiate benign from malignant breast cancer has been tested, and correct diagnoses prediction of 80% of the tested patients has been observed (10).…”

“…Also predictions of antibiotic concentrations in blood plasma (11), drug release control (12) and glucose control models to improve diabetic care (13) using ANNs have shown satisfactory results. Therefore, the application of this methodology in clinical analysis may optimize the diagnostic utility of laboratory data (10,14,17), reduce the number of unnecessary biopsies (18), and develop specific software applications (9,15,16,19). Moreover, the increasing use of computational methodologies in clinical laboratories has shown a significant and profound effect on how they are organized, staffed, equipped, and operated (20).…”