Searching For The Urine Osmolality Surrogate: An Automated Machine Learning Approach

dc.contributor.authorTopcu, Deniz Ilhan
dc.contributor.authorBayraktar, Nilufer
dc.contributor.orcIDhttps://orcid.org/0000-0002-1219-6368en_US
dc.contributor.orcIDhttps://orcid.org/0000-0002-7886-3688en_US
dc.contributor.pubmedID000819864400001en_US
dc.contributor.researcherIDE-3717-2019en_US
dc.contributor.researcherIDY-8758-2018en_US
dc.date.accessioned2022-12-19T11:11:22Z
dc.date.available2022-12-19T11:11:22Z
dc.date.issued2022
dc.description.abstractObjectives Automated machine learning (AutoML) tools can help clinical laboratory professionals to develop machine learning models. The objective of this study was to develop a novel formula for the estimation of urine osmolality using an AutoML tool and to determine the efficiency of AutoML tools in a clinical laboratory setting. Methods Three hundred routine urinalysis samples were used for reference osmolality and urine clinical chemistry analysis. The H2O AutoML engine completed the machine learning development steps with minimum human intervention. Four feature groups were created, which include different urinalysis measurements according to the Boruta feature selection algorithm. Method comparison statistics including Spearman correlation, Passing-Bablok regression analysis were performed, and Bland Altman plots were created to compare model predictions with the reference method. The minimum allowable bias (24.17%) from biological variation data was used as the limit of agreement. Results The AutoML engine developed a total of 183 ML models. Conductivity and specific gravity had the highest variable importance. Models that include conductivity, specific gravity, and other urinalysis parameters had the highest R-2 (0.70-0.83), and 70-84% of results were within the limit of agreement. Conclusions Combining urinary conductivity with other urinalysis parameters using validated machine learning models can yield a promising surrogate. Additionally, AutoML tools facilitate the machine learning development cycle and should be considered for developing ML models in clinical laboratories.en_US
dc.identifier.endpage1920en_US
dc.identifier.issn1434-6621en_US
dc.identifier.issue12en_US
dc.identifier.scopus2-s2.0-85134394555en_US
dc.identifier.startpage1911en_US
dc.identifier.urihttps://www.degruyter.com/document/doi/10.1515/cclm-2022-0415/html
dc.identifier.urihttp://hdl.handle.net/11727/8343
dc.identifier.volume60en_US
dc.identifier.wos000819864400001en_US
dc.language.isoengen_US
dc.relation.isversionof10.1515/cclm-2022-0415en_US
dc.relation.journalCLINICAL CHEMISTRY AND LABORATORY MEDICINEen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergien_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectautomated machine learningen_US
dc.subjectAutoMLen_US
dc.subjectconductivityen_US
dc.subjectmachine learningen_US
dc.subjecturine osmolalityen_US
dc.titleSearching For The Urine Osmolality Surrogate: An Automated Machine Learning Approachen_US
dc.typearticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
104.pdf
Size:
1.69 MB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: