Predicting laboratory solution kit accuracy using artificial intelligence: a data-driven approach

Abstract This study developed and validated an artificial intelligence (AI)-based computational tool for standardizing glucose and urea measurements across different clinical laboratory systems (Biolabo and BioScien) using Biomagreb as the reference standard. Through empirical analysis of parallel-t...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdulwahab AL-Deib, Eshraq Alsherif, Husameddin Abuzgaia, Amel Rabti, Ruwaida Rtemi, Salem Elfard, Sheren Njaim
Format: Article
Language:English
Published: SpringerOpen 2025-08-01
Series:Bulletin of the National Research Centre
Subjects:
Online Access:https://doi.org/10.1186/s42269-025-01351-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226670653833216
author Abdulwahab AL-Deib
Eshraq Alsherif
Husameddin Abuzgaia
Amel Rabti
Ruwaida Rtemi
Salem Elfard
Sheren Njaim
author_facet Abdulwahab AL-Deib
Eshraq Alsherif
Husameddin Abuzgaia
Amel Rabti
Ruwaida Rtemi
Salem Elfard
Sheren Njaim
author_sort Abdulwahab AL-Deib
collection DOAJ
description Abstract This study developed and validated an artificial intelligence (AI)-based computational tool for standardizing glucose and urea measurements across different clinical laboratory systems (Biolabo and BioScien) using Biomagreb as the reference standard. Through empirical analysis of parallel-tested blood samples, four linear regression models were established, demonstrating excellent predictive accuracy (R2 > 0.99, mean absolute error < 1.2%). The glucose conversion models yielded precise transformations (Biolabo: Y = 1.01X−0.03357; BioScien: Y = 1.141X−13.71), while urea models showed robust consistency (Biolabo: Y = 0.9312X + 1.549; BioScien: Y = 0.7073X + 5.252). Validation confirmed near-perfect agreement with manual calculations, with minor discrepancies (≤ 0.5%) attributable only to rounding effects. The AI-driven software implementation enhanced clinical utility by automating conversions, displaying normal ranges, and eliminating human calculation errors. Despite high accuracy, limitations include unit restriction (mg/dL only), single-value processing, and lack of batch export functionality. The study highlights AI’s transformative role in laboratory standardization, particularly through machine learning (ML) techniques like linear regression and random forests. Challenges like data quality, understanding the model, and following regulations were tackled using explainable AI (XAI) and strict validation methods. Future improvements should expand analyte coverage, incorporate mmol/L conversion, and enable batch processing. These findings support AI’s potential to enhance diagnostic reliability and inter-laboratory comparability in clinical settings.
format Article
id doaj-art-b8982460dd9d44e2b165b2597ca9b085
institution Kabale University
issn 2522-8307
language English
publishDate 2025-08-01
publisher SpringerOpen
record_format Article
series Bulletin of the National Research Centre
spelling doaj-art-b8982460dd9d44e2b165b2597ca9b0852025-08-24T11:06:33ZengSpringerOpenBulletin of the National Research Centre2522-83072025-08-014911710.1186/s42269-025-01351-1Predicting laboratory solution kit accuracy using artificial intelligence: a data-driven approachAbdulwahab AL-Deib0Eshraq Alsherif1Husameddin Abuzgaia2Amel Rabti3Ruwaida Rtemi4Salem Elfard5Sheren Njaim6Department of Medical Laboratory, University of Tripoli AlahliaDepartment of Medical Laboratory, University of Tripoli AlahliaDepartment of Computer Science and Information Technology, University of Tripoli AlahliaDepartment of Medical Laboratory, University of Tripoli AlahliaDepartment of Computer Science and Information Technology, University of Tripoli AlahliaDepartment of Software Engineering, Faculty of Information Technology, University of ZawiaUniversity of Tripoli AlahliaAbstract This study developed and validated an artificial intelligence (AI)-based computational tool for standardizing glucose and urea measurements across different clinical laboratory systems (Biolabo and BioScien) using Biomagreb as the reference standard. Through empirical analysis of parallel-tested blood samples, four linear regression models were established, demonstrating excellent predictive accuracy (R2 > 0.99, mean absolute error < 1.2%). The glucose conversion models yielded precise transformations (Biolabo: Y = 1.01X−0.03357; BioScien: Y = 1.141X−13.71), while urea models showed robust consistency (Biolabo: Y = 0.9312X + 1.549; BioScien: Y = 0.7073X + 5.252). Validation confirmed near-perfect agreement with manual calculations, with minor discrepancies (≤ 0.5%) attributable only to rounding effects. The AI-driven software implementation enhanced clinical utility by automating conversions, displaying normal ranges, and eliminating human calculation errors. Despite high accuracy, limitations include unit restriction (mg/dL only), single-value processing, and lack of batch export functionality. The study highlights AI’s transformative role in laboratory standardization, particularly through machine learning (ML) techniques like linear regression and random forests. Challenges like data quality, understanding the model, and following regulations were tackled using explainable AI (XAI) and strict validation methods. Future improvements should expand analyte coverage, incorporate mmol/L conversion, and enable batch processing. These findings support AI’s potential to enhance diagnostic reliability and inter-laboratory comparability in clinical settings.https://doi.org/10.1186/s42269-025-01351-1Artificial intelligenceLinear regressionDiagnostic accuracyMedical laboratory departmentUniversity of Tripoli Alahlia
spellingShingle Abdulwahab AL-Deib
Eshraq Alsherif
Husameddin Abuzgaia
Amel Rabti
Ruwaida Rtemi
Salem Elfard
Sheren Njaim
Predicting laboratory solution kit accuracy using artificial intelligence: a data-driven approach
Bulletin of the National Research Centre
Artificial intelligence
Linear regression
Diagnostic accuracy
Medical laboratory department
University of Tripoli Alahlia
title Predicting laboratory solution kit accuracy using artificial intelligence: a data-driven approach
title_full Predicting laboratory solution kit accuracy using artificial intelligence: a data-driven approach
title_fullStr Predicting laboratory solution kit accuracy using artificial intelligence: a data-driven approach
title_full_unstemmed Predicting laboratory solution kit accuracy using artificial intelligence: a data-driven approach
title_short Predicting laboratory solution kit accuracy using artificial intelligence: a data-driven approach
title_sort predicting laboratory solution kit accuracy using artificial intelligence a data driven approach
topic Artificial intelligence
Linear regression
Diagnostic accuracy
Medical laboratory department
University of Tripoli Alahlia
url https://doi.org/10.1186/s42269-025-01351-1
work_keys_str_mv AT abdulwahabaldeib predictinglaboratorysolutionkitaccuracyusingartificialintelligenceadatadrivenapproach
AT eshraqalsherif predictinglaboratorysolutionkitaccuracyusingartificialintelligenceadatadrivenapproach
AT husameddinabuzgaia predictinglaboratorysolutionkitaccuracyusingartificialintelligenceadatadrivenapproach
AT amelrabti predictinglaboratorysolutionkitaccuracyusingartificialintelligenceadatadrivenapproach
AT ruwaidartemi predictinglaboratorysolutionkitaccuracyusingartificialintelligenceadatadrivenapproach
AT salemelfard predictinglaboratorysolutionkitaccuracyusingartificialintelligenceadatadrivenapproach
AT sherennjaim predictinglaboratorysolutionkitaccuracyusingartificialintelligenceadatadrivenapproach