【摘要】目的探讨基于计算机视觉算法的尿液定量分析系统在白蛋白尿筛检中的应用效果。方法选取2021 年2 月在北京大学第一医院接受尿液检验分析，不同尿微量白蛋白肌酐比值范围的143 例受试者纳入研究。采集受试者的随机尿液样本，分别送到医院临床检验实验室和使用尿液定量分析系统进行检测分析。以实验室检测结果为金标准，从筛检的真实性、可靠性、预测值和受试者工作特征曲线下面积(AUC)4 个方面评价基于计算机视觉算法的尿液定量分析系统用于白蛋白尿筛检的效果。结果共纳入143 例受试者，白蛋白尿A1 分级的59(41.3%)例，A2 分级的39(27.3%)例，A3 分级的45(31.5%)例。基于计算机视觉算法的尿液定量分析系统在白蛋白尿筛检的真实性、可靠性、预测值和AUC 方面均表现良好。以白蛋白尿A1 分级为阴性，A2 和A3 分级为阳性，尿液定量分析系统准确率达到88.8%，灵敏度和特异度分别达到94.0%和81.4%，阳性预测值和阴性预测值分别达到87.8%和90.6%，AUC 达到0.962。结论基于计算机视觉算法的尿液定量分析系统在白蛋白尿筛检中的应用效果较好，诊断准确率、AUC 和灵敏度均较高。由于其便捷性与低成本，该分析系统在我国大规模人群调查用于慢性肾脏病初筛中有较大的应用推广价值。
【Abstract】Objectives This study aimed to evaluate the diagnostic performance of a computer visionbased urine quantitative analysis system for albuminuria screening. Methods A total of 143 participants with various levels of urinary albumin to creatinine ratio (uACR) recruited from the patients subjected to urinary analysis at Peking University First Hospital during February 2021 were included in this study. Randomly selected spot urine samples were collected from these participants and measured using both clinical laboratory method and the computer vision-based urine quantitative analysis system. With the results of clinical laboratory
method as golden criteria, the diagnostic performance of the computer vision-based urine quantitative analysis system in albuminuria screening was evaluated in terms of validity, reliability, predictive value, and area under the receiver operating curve (AUC). Results In the 143 participants, albuminuria A1, A2 and A3 accounted for 59 case (41.3%), 39 cases (27.3%) and 45 cases (31.5%), respectively. The computer visionbased urine quantitative analysis system achieved better performance in albuminuria screening in terms of validity, reliability, predictive value and AUC. When albuminuria A1 was set as negative albuminuria and albuminuria A2 and A3 were set as positive albuminuria, the urine quantitative analysis system achieved an accuracy of 88.8%, a sensitivity of 94.0% and a specificity of 81.4%; the positive and negative predictive values were 87.8% and 90.6%, respectively, with an AUC of 0.962. Conclusions The computer vision-based urine quantitative analysis system had better diagnostic performance in albuminuria screening with higher accuracy, sensitivity and AUC. Due to its convenience and low cost, the computer vision-based urine quantitative analysis system is especially suitable for the preliminary screening of chronic kidney disease in large scales of population.
[1] Zhang L, Wang F, Wang L, et al. Prevalence of chronic kidney disease in China: a cross-sectional survey [J]. The lancet, 2012, 379(9818): 815-822.
[2] Huang Y M, Xu D, Long J, et al. Spectrum of chronic kidney disease in China: a national study based on hospitalized patients from 2010 to 2015 [J]. Nephrology, 2019, 24(7): 725-736.
[3] Zhang L, Wang H. Chronic kidney disease epidemic: cost and health care implications in China; proceedings of the Seminars in nephrology, F, 2009 [C]. Elsevier.
[4] Levin A, Stevens P E, Bilous R W, et al. Kidney Disease: Improving Global Outcomes (KDIGO) CKD Work Group. KDIGO 2012 clinical practice guideline for the evaluation and management of chronic kidney disease [J]. Kidney international supplements, 2013, 3(1): 1-150.
[5] Webster A C, Nagler E V, Morton R L, et al. Chronic kidney disease [J]. The lancet, 2017, 389(10075): 1238-1252.
[6] James M T, Hemmelgarn B R, Tonelli M. Early recognition and prevention of chronic kidney disease [J]. The Lancet, 2010, 375(9722): 1296-1309.
[7] 张路霞, 王海燕. 中国慢性肾脏病的高患病率及其对检验医学的挑战 [J]. 中华检验医学杂志, 2012, (2012 年 09): 769-772.
[8] 杨绍基, 任红. 传染病学.第7版 [M]. 传染病学.第7版, 2008.
[9] 杨任兵, 程文播, 钱庆, et al. 尿液试纸条的手机图像比色分析新方法的研究 [J]. 影像科学与光化学, 2018, (2018 年 04): 340-349.
[10] Forman J P, Fisher N D, Schopick E L, et al. Higher levels of albuminuria within the normal range predict incident hypertension [J]. J Am Soc Nephrol, 2008, 19(10): 1983-1988.
[11] De Zeeuw D, Parving H H, Henning R H. Microalbuminuria as an early marker for cardiovascular disease [J]. J Am Soc Nephrol, 2006, 17(8): 2100-2105.
[12] 高碧霞, 张路霞. 非透析慢性肾脏病患者管理模式 [J]. 华西医学, 2019, 7.
[13] Glassock R J, Warnock D G, Delanaye P. The global burden of chronic kidney disease: estimates, variability and pitfalls [J]. Nature Reviews Nephrology, 2017, 13(2): 104.
[14] Wang Y, Zhang L, Li X, et al. Improvement of awareness, treatment and control of hypertension among chronic kidney disease patients in China from 1999 to 2005 [J]. Hypertension Research, 2009, 32(6): 444-449.
[15] Xu Y, Wang L, He J, et al. Prevalence and control of diabetes in Chinese adults [J]. Jama, 2013, 310(9): 948-959.
[16] Zhang L, Long J, Jiang W, et al. Trends in chronic kidney disease in China N Engl J Med. 2016; 375: 905–6 doi: 10.1056 [J]. NEJMc1602469.
[17] Radi?i? Biljak V, Honovi? L, Matica J, et al. The role of laboratory testing in detection and classification of chronic kidney disease: national recommendations [J]. Biochemia medica, 2017, 27(1): 153-176.
[18] Komenda P, Ferguson T W, Macdonald K, et al. Cost-effectiveness of primary screening for CKD: a systematic review [J]. American Journal of Kidney Diseases, 2014, 63(5): 789-797.
[19] Ferguson T W, Tangri N, Tan Z, et al. Screening for chronic kidney disease in Canadian indigenous peoples is cost-effective [J]. Kidney international, 2017, 92(1): 192-200.
[20] Chen N, Hsu C C, Yamagata K, et al. Challenging chronic kidney disease: experience from chronic kidney disease prevention programs in Shanghai, Japan, Taiwan and Australia [J]. Nephrology, 2010, 15: 31-36.
[21] Stevens P E, De Lusignan S, Farmer C K, et al. Engaging primary care in CKD initiatives: the UK experience [J]. Nephrology Dialysis Transplantation, 2012, 27(suppl_3): iii5-iii11.
[22] 王芳, 张路霞, 张普洪, et al. 人群调查中尿白蛋白检测方法的探讨 [D], 2011.
[23] 喜杨, 王鸿懿, 杨帆, et al. 半定量试纸法评价微量白蛋白尿的探索性研究 [J]. 中国全科医学, 2021, 24(14): 1776-1779.
[24] White S L, Yu R, Craig J C, et al. Diagnostic accuracy of urine dipsticks for detection of albuminuria in the general community [J]. American journal of kidney diseases, 2011, 58(1): 19-28.
[25] Cho M C, Ji M, Kim S Y, et al. Evaluation of the URiSCAN super cassette ACR semiquantitative urine dipstick for microalbuminuria screening [J]. J Clin Lab Anal, 2014, 28(4): 281-286.
[26] Graziani M S, Gambaro G, Mantovani L, et al. Diagnostic accuracy of a reagent strip for assessing urinary albumin excretion in the general population [J]. Nephrology Dialysis Transplantation, 2008, 24(5): 1490-1494.
