UrineCART, a machine learning method for establishment of review rules based on UF-1000i flow cytometry and dipstick or reflectance photometer
-
Cao Yuan
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.
We thank W. Li for critical reading of the manuscript, Vivien Soo for assistance withmanuscript revising.
Conflict of interest statement
Authors’ conflict of interest disclosure: The authors stated that there are no conflicts of interest regarding the publication of this article.
Research funding: None declared.
Employment and leadership: Authors of this study are employees of 90th General Hospital of Jinan.
Honorarium: None declared.
References
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;48:1107–11.10.1515/CCLM.2010.233Suche in Google Scholar
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;301:1–18.10.1016/S0009-8981(00)00342-9Suche in Google Scholar
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.Suche in Google Scholar PubMed
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=b7bc2757938ac7a7a821505f8243d9f310.3109/00365513.2010.535011Suche in Google Scholar PubMed
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-0YUMSuche in Google Scholar PubMed
6. Ben-Ezra J, Bork L, McPherson RA. Evaluation of the Sysmex UF-100 automated urinalysis analyzer. Clin Chem 1998;44:92–5.10.1093/clinchem/44.1.92Suche in Google Scholar
7. Valenstein PN, Koepke JA. Unnecessary microscopy in routine urinalysis. Am J Clin Pathol 1984;82:444–8.10.1093/ajcp/82.4.444Suche in Google Scholar PubMed
8. Shaw ST, Jr., Poon SY, Wong ET.‘Routine urinalysis’. Is the dipstick enough? J Am Med Assoc 1985;253:1596–600.10.1001/jama.1985.03350350090028Suche in Google Scholar
9. Akin OK, Serdar MA, Cizmeci Z, Genc O, Aydin S. Comparison of LabUMat-with-UriSed and iQ200 fully automatic urine sediment analysers with manual urine analysis. Biotechnol Appl Biochem 2009;53:139–44.http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000266788400008&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f310.1042/BA20080188Suche in Google Scholar PubMed
10. Nanos NE, Delanghe JR. Evaluation of Sysmex UF-1000i for use in cerebrospinal fluid analysis. Clin Chim Acta 2008;392:30–3.http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000256581000007&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f310.1016/j.cca.2008.02.020Suche in Google Scholar PubMed
11. Hoffmann P, Hoffmann C, Ziebig R, Zimmermann M. Evaluation of the iChem(R) Velocity urine chemistry analyzer in a hospital routine laboratory. Clin Chem Lab Med 2011;49:509–13.10.1515/CCLM.2011.065Suche in Google Scholar PubMed
12. Ping W, Erik DG, Tang J, Min P. A hybrid GA-based fuzzy classifying approach to urinary analysis modeling. GECCO’09 Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference, Vol. Montréal, Québec, Canada, 2009:2671–8.10.1145/1570256.1570381Suche in Google Scholar
13. Clinical and Laboratory Standards Institute (CLSI). Urinalysis; Approved Guideline, 3rd ed. CLSI document GP16-A3. Wayne, PA: Clinical and Laboratory Standards Institute, 2009.Suche in Google Scholar
14. Mayo S, Acevedo D, Quinones-Torrelo C, Canos I, Sancho M. Clinical laboratory automated urinalysis: comparison among automated microscopy, flow cytometry, two test strips analyzers, and manual microscopic examination of the urine sediments. J Clin Lab Anal 2008;22:262–70.10.1002/jcla.20257http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000257900400007&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f3Suche in Google Scholar PubMed
15. Manoni F, Fornasiero L, Ercolin M, Tinello A, Ferrian M, Hoffer P, et al. Cut-off values for bacteria and leukocytes for urine flow cytometer Sysmex UF-1000i in urinary tract infections. Diagn Microbiol Infect Dis 2009;65:103–7.http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000270260400004&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f310.1016/j.diagmicrobio.2009.06.003Suche in Google Scholar
16. Ottiger C, Huber AR. Quantitative urine particle analysis: integrative approach for the optimal combination of automation with UF-100 and microscopic review with KOVA cell chamber. Clin Chem 2003;49:617–23.10.1373/49.4.617Suche in Google Scholar
17. Mark Hall EF, Holmes G, Pfahringer B, Reutemann P, Witten IH. The WEKA data mining software: an update. SIGKDD Explorations 2009;11.10.1145/1656274.1656278Suche in Google Scholar
18. Vergara IA, Norambuena T, Ferrada E, Slater AW, Melo F. StAR: a simple tool for the statistical comparison of ROC curves. BMC Bioinformatics 2008;9:265.10.1186/1471-2105-9-265http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000257159900001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f3Suche in Google Scholar
19. Emden R. Gansner SC. An open graph visualization system and its applications to software engineering. Softw Pract Exper 1999;30:1203–33.10.1002/1097-024X(200009)30:11<1203::AID-SPE338>3.0.CO;2-NSuche in Google Scholar
20. Vapnik V. Statistical learning theory. New York: John Wiley and Sons, 1998.Suche in Google Scholar
21. Kadkhoda K, Manickam K, Degagne P, Sokolowski P, Pang P, Kontzie N, et al. UF-1000i flow cytometry is an effective screening method for urine specimens. Diagn Microbiol Infect Dis 2011;69:130–6.http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000287117800003&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f310.1016/j.diagmicrobio.2010.09.013Suche in Google Scholar
22. Budak YU, Huysal K. Comparison of three automated systems for urine chemistry and sediment analysis in routine laboratory practice. Clin Lab 2011;57:47–52.Suche in Google Scholar PubMed
23. Langlois MR, Delanghe JR, Steyaert SR, Everaert KC, De Buyzere ML. Automated flow cytometry compared with an automated dipstick reader for urinalysis. Clin Chem 1999;45:118–22.10.1093/clinchem/45.1.118Suche in Google Scholar PubMed
24. Altekin E, Kadicesme O, Akan P, Kume T, Vupa O, Ergor G, et al. New generation IQ-200 automated urine microscopy analyzer compared with KOVA cell chamber. J Clin Lab Anal 2010;24:67–71.http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000276167700002&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f310.1002/jcla.20319Suche in Google Scholar
25. Chien TI, Kao JT, Liu HL, Lin PC, Hong JS, Hsieh HP, et al. Urine sediment examination: a comparison of automated urinalysis systems and manual microscopy. Clin Chim Acta 2007;384:28–34.http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000249548700004&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f310.1016/j.cca.2007.05.012Suche in Google Scholar
26. Pieretti B, Brunati P, Pini B, Colzani C, Congedo P, Rocchi M, et al. Diagnosis of bacteriuria and leukocyturia by automated flow cytometry compared with urine culture. J Clin Microbiol 2010;48:3990–6.10.1128/JCM.00975-10http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000283588500023&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f3Suche in Google Scholar PubMed PubMed Central
27. Marschal M, Wienke M, Hoering S, Autenrieth IB, Frick JS. Evaluation of 3 different rapid automated systems for diagnosis of urinary tract infections. Diagn Microbiol Infect Dis 2012;72:125–30.10.1016/j.diagmicrobio.2011.10.001http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000299600300002&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f3Suche in Google Scholar PubMed
28. De Rosa R, Grosso S, Bruschetta G, Avolio M, Stano P, Modolo ML, et al. Evaluation of the Sysmex UF1000i flow cytometer for ruling out bacterial urinary tract infection. Clin Chim Acta 2010;411:1137–42.http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=000279299100023&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=b7bc2757938ac7a7a821505f8243d9f310.1016/j.cca.2010.03.027Suche in Google Scholar PubMed
©2012 by Walter de Gruyter Berlin Boston
Artikel in diesem Heft
- Masthead
- Masthead
- Editorials
- Phlebotomy, stat testing and laboratory organization: an intriguing relationship
- Human epididymis protein 4: the start of a post-ROMAn era?
- Hyperhomocysteinemia in health and disease: where we are now, and where do we go from here?
- Reviews
- The usefulness of cystatin C and related formulae in pediatrics
- The emerging role of biomarkers and bio-impedance in evaluating hydration status in patients with acute heart failure
- Biomarkers in primary open angle glaucoma
- Mini Review
- Identification of circulating microRNAs as biomarkers in cancers: what have we got?
- Opinion Paper
- HE4 in gynecological cancers: report of a European investigators and experts meeting
- Guidelines and Recommendations
- Position paper on laboratory testing for patients taking new oral anticoagulants. Consensus document of FCSA, SIMeL, SIBioC and CISMEL1)
- General Clinical Chemistry and Laboratory Medicine
- Reducing the number of clinical stat phlebotomy orders: feasible or not?
- Calculating acid-base and oxygenation status during COPD exacerbation using mathematically arterialised venous blood
- UrineCART, a machine learning method for establishment of review rules based on UF-1000i flow cytometry and dipstick or reflectance photometer
- Reference Values and Biological Variations
- Assessing seasonality in clinical research
- Cancer Diagnostics
- Identification of a novel in-frame deletion in BRCA2 and analysis of variants of BRCA1/2 in Italian patients affected with hereditary breast and ovarian cancer
- Human epididymis protein 4 (HE4) in benign and malignant diseases
- Human epididymis protein 4 as a serum marker for diagnosis of endometrial carcinoma and prediction of clinical outcome
- A predictive equation to adjust for clinical variables in soluble mesothelin-related protein (SMRP) levels
- Cardiovascular Diseases
- Vitamin D deficiency parallels inflammation and immune activation, the Ludwigshafen Risk and Cardiovascular Health (LURIC) study
- Plasma homocysteine and the risk of venous thromboembolism: insights from the FIELD study
- Letters to the Editor
- A two-base-pairs deletion in the albumin gene causes a new case of analbuminemia
- Usefulness of an antiglycolytic granular mixture of sodium fluoride and citrate for stabilizing plasma homocysteine levels
- Further insights on the relationship between bilirubin and C-reactive protein
- Phosphoethanolamine normal range in pediatric urines for hypophosphatasia screening
- Risk of false positive hepatitis C virus RNA due to sample to sample carryover on an automated hematology analyzer
- Lack of commutability between a quality control material and plasma samples in a troponin I measurement system
- Biological variation in pregnancy-associated plasma protein-A in healthy men and non-pregnant healthy women
- Investigation of a slope discontinuity in a patients’ results distribution for D-dimer
- Acknowledgment
- Acknowledgment
Artikel in diesem Heft
- Masthead
- Masthead
- Editorials
- Phlebotomy, stat testing and laboratory organization: an intriguing relationship
- Human epididymis protein 4: the start of a post-ROMAn era?
- Hyperhomocysteinemia in health and disease: where we are now, and where do we go from here?
- Reviews
- The usefulness of cystatin C and related formulae in pediatrics
- The emerging role of biomarkers and bio-impedance in evaluating hydration status in patients with acute heart failure
- Biomarkers in primary open angle glaucoma
- Mini Review
- Identification of circulating microRNAs as biomarkers in cancers: what have we got?
- Opinion Paper
- HE4 in gynecological cancers: report of a European investigators and experts meeting
- Guidelines and Recommendations
- Position paper on laboratory testing for patients taking new oral anticoagulants. Consensus document of FCSA, SIMeL, SIBioC and CISMEL1)
- General Clinical Chemistry and Laboratory Medicine
- Reducing the number of clinical stat phlebotomy orders: feasible or not?
- Calculating acid-base and oxygenation status during COPD exacerbation using mathematically arterialised venous blood
- UrineCART, a machine learning method for establishment of review rules based on UF-1000i flow cytometry and dipstick or reflectance photometer
- Reference Values and Biological Variations
- Assessing seasonality in clinical research
- Cancer Diagnostics
- Identification of a novel in-frame deletion in BRCA2 and analysis of variants of BRCA1/2 in Italian patients affected with hereditary breast and ovarian cancer
- Human epididymis protein 4 (HE4) in benign and malignant diseases
- Human epididymis protein 4 as a serum marker for diagnosis of endometrial carcinoma and prediction of clinical outcome
- A predictive equation to adjust for clinical variables in soluble mesothelin-related protein (SMRP) levels
- Cardiovascular Diseases
- Vitamin D deficiency parallels inflammation and immune activation, the Ludwigshafen Risk and Cardiovascular Health (LURIC) study
- Plasma homocysteine and the risk of venous thromboembolism: insights from the FIELD study
- Letters to the Editor
- A two-base-pairs deletion in the albumin gene causes a new case of analbuminemia
- Usefulness of an antiglycolytic granular mixture of sodium fluoride and citrate for stabilizing plasma homocysteine levels
- Further insights on the relationship between bilirubin and C-reactive protein
- Phosphoethanolamine normal range in pediatric urines for hypophosphatasia screening
- Risk of false positive hepatitis C virus RNA due to sample to sample carryover on an automated hematology analyzer
- Lack of commutability between a quality control material and plasma samples in a troponin I measurement system
- Biological variation in pregnancy-associated plasma protein-A in healthy men and non-pregnant healthy women
- Investigation of a slope discontinuity in a patients’ results distribution for D-dimer
- Acknowledgment
- Acknowledgment
