Affiliation:
1. Department of Laboratory Medicine, 90th General Hospital of Jinan, Jinan , Shandong , P.R. China
2. Department of Neurology, 90th General Hospital of Jinan, Jinan , Shandong , P.R. China
Abstract
Abstract
Background: Automated systems have been broadly used in the counting of particles in urine, while manual microscopic analyses are still required for confirming components of urine sediments, especially pathologic casts and other unknown particles. Good review rules can reduce the number of manual urine microscopy examinations safely, thereby increasing productivity. Although several methods have been proposed, establishment of microscopic review rules for flow cytometer remains challenging.
Methods: A total of 3014 urine samples from outpatient and inpatient were examined using UF-1000i flow cytometry, Urisys-2400 dipstick and RS 2003 urine sediment workstation, respectively. Based on the results above, three supervised machine learning methods were employed to construct classifiers for screening urine samples.
Results: Here, we propose a novel method for construction of microscopic review rules, termed UrineCART, which was based on a classification and regression tree (CART) method. With a cut-off value of 0.0745 for UrineCART, we obtained a sensitivity of 92.0%, a specificity of 81.5% and a total review rate of 32.4% on an independent test set. Comparisons with the existing methods showed that UrineCART gave the acceptable sensitivity and lower total review rate.
Conclusions: An algorithm based on machine learning methods for review criteria can be achieved via systematic comparison of UF-1000i flow cytometry and microscopy. Using UrineCART, our microscopic review rate can be reduced to around 30%, while decreasing significant losses in urinalysis.
Subject
Biochemistry (medical),Clinical Biochemistry,General Medicine
Reference28 articles.
1. Manoni F, Tinello A, Fornasiero L, Hoffer P, Temporin V, Valverde S, et al. Urine particle evaluation: a comparison between the UF-1000i and quantitative microscopy. Clin Chem Lab Med 2010;48:1107–11.
2. Delanghe JR, Kouri TT, Huber AR, Hannemann-Pohl K, Guder WG, Lun A, et al. The role of automated urine particle flow cytometry in clinical practice. Clin Chim Acta 2000;301:1–18.
3. Bartolini L, Caldini A, Rapi S, Del Genovese A, Giganti E. Urine sediment analysis: comparison between microscopic evaluation and a fully automated flow cytometric analysis. Eur J Histochem 1997;41(Suppl 2):93–4.9859799
4. Jiang T, Chen P, Ouyang J, Zhang S, Cai D. Urine particles analysis: performance evaluation of Sysmex UF-1000i and comparison among urine flow cytometer, dipstick, and visual microscopic examination. Scand J Clin Lab Invest 2011;71:30–7.http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000286825100005&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f3
5. Roggeman S, Zaman Z. Safely reducing manual urine microscopy analyses by combining urine flow cytometer and strip results. Am J Clin Pathol 2001;116:872–8.10.1309/GRT7-Q6WP-VGWE-0YUM11764076
Cited by
15 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献