慢性腎病(chronic kidney disease, CKD)已成為世界性的公共衛生議題超過數十年，台灣也深受影響。依據美國腎病資料系統(United States Renal Dada System (USRDS)的統計資料顯示，台灣的慢性腎病末期(end-stage renal disease, ESRD)的盛行率及發生率高居全球40個國家與區域的第一名多年。相對的，慢性腎病的自知率(awareness)僅約8%，這可能是慢性末期腎病在台灣的高盛行率與發生率的主因之一。
造成慢性腎病的主要原因之一是腎絲球持續受損，腎臟切片的病理檢查是最為直接的證據。然而，此項高度侵入性的檢驗並不可能常規持續的執行，在日後的追蹤檢查通常僅依賴尿液或血液的常規檢查輔助。現有的檢驗方法中，對於腎功能的評估，最常見的檢查是血清中肌酸酐(serum creatinine)、尿液中尿蛋白的濃度與尿沉渣鏡檢。然而，此三項檢查並非直接檢驗腎絲球，而且這三項檢驗也大多集中在專業的醫學檢驗實驗室中執行，造成病患想進行檢驗的不便，這可能是造成慢性腎病的自知率偏低的主因。此外，尿沉渣鏡檢報告的現有品質，尚未達到臨床醫師的期望。
基於前述原因，吾人開發與改良四項檢驗方法與裝置以期提高檢驗的專一性、可親性與敏感性。第一項，以表面電漿子共振法(surface plasmon resonance, SPR)，用於直接量測尿液中腎絲球之足細胞(podocyte)的表面蛋白分子podocalyxin。以Au/ZnO晶片配合GWC SPRimager可以量測到尿中podocalyxin濃度為1 ng/mL。第二項，以微流道(microfluidic channel)與毛細重力閥門(capillary-gravitational valve)開發出不含主動原件且可達成檢體定量與試劑分注及混合的可攜式尿中肌酸酐檢測晶片。與尿中肌酸酐的標準檢驗法比較，本晶片的檢驗偏差在正負10%以內。第三項，利用類神經網路(artificial neural networks, ANN)的人工智慧協助判斷尿液試紙中的檢驗結果，研判受測者的腎功能預測值(estimated glomerular filtration rate, eGFR)，增加尿液化學分析法對於腎功能評估指標的運用方式。檢驗結果的正確性達0.879，類神經網路的評估指標(area under the curve, AUC)達0.928，敏感度(sensitivity)達0.83，專一性(specificity)達0.88。第四項，改善現有尿沉渣鏡檢的檢驗程序，提高腎絲球出血型紅血球(dysmorphic red blood cell, dysmorphic RBC)的回收率，由34.7%提升至42.0% (p ＜0.001)，進而增加尿沉渣中的發現率，並以Sternheimer染色法增加尿沉渣中的細胞間對比度，以增進對於腎小管上皮細胞(renal tubular epithelial cell, RTEC)的鑑別度。
以表面電漿子共振法檢測尿液中之podocalyxin濃度，未來仍需以量化的製造法完成檢驗晶片，並找出可重複檢測的最佳反應條件，以達成檢驗方法的校正與量測的功能與應用。以微流道與毛細重力閥門開發出不具備主動原件且可達成檢體定量與試劑分注及混合的可攜式尿中肌酸酐檢測晶片，已具備發展成床邊檢驗(point-of-care test, POCT)的潛力，並已獲得中華民國專利I-446958。類神經網路用於尿液試紙中的檢驗結果，輔助研判受測者的腎功能預測值，增加尿液化學分析法對於腎功能評估指標的運用方式，並獲得中華民國專利M518332與日本專利6012781。關於尿沉渣鏡檢法的改良，目前已成為台灣醫檢驗驗學會的尿沉渣鏡檢指引TSLM-GP-U01(1)。

Chronic kidney disease (CKD) has been a has been a worldwide public issue for decades. Taiwanese also suffer from this disease. According to the data from United States Renal Data System (USRDS), the prevalence and incidence of end-stage renal disease (ESRD) are the highest in 40 countries and areas for years. In contrast, the awareness rate of CKD patients is only about 8%, which is relatively low. This depressed result might be a key factor for the high prevalence and incidence of ESRD.
The major cause for CKD is a progressive damage to glomeruli. Currently, the renal biopsy is the most solid evidence for glomerular damage. However, this extremely invasive examination is with potential risks thus the renal biopsy is neither a regular examination nor an examination for follow-up. In practice, the follow-up for glomerular damage is usually based on urinary and blood tests. The most popular tests for the evaluation of kidney function are serum creatinine, urinary protein, and urine sediment microscopy. However, these tests are not direct methods to the glomerular damage, which are usually carried out in medical laboratories. In such a scenario, it could be a barrier to patients for a CKD screening examination, which would be a major cause for a low CKD awareness. Also, the current report quality of urine sediment microscopy is not meet the clinical need for physicians.
Based on the previous reasons, we had developed and continuously improved four examinations and devices in order to increase the specificity, accessibility, and sensitivity of examinations for CKD screening. First, we applied the principle of surface plasmon resonance (SPR) to detect the urinary podocalyxin which is a surface protein of podocyte originating from the glomerulus. By an Au/ZnO chip with GWC SPRimager, the lower detection limit is 1 ng/mL. Second, we utilized microfluidic channels with capillary-gravitational valves to design a portable chip without active parts for the detection of urinary creatinine, which had multiple functions for sample quantifying, regent adding, and mixing. Compared with the standard method for the measurement of urinary creatinine, the result errors by this chip were within ±10%. Third, artificial neuro networks (ANN) was applied to judge the result of a urinary dipstick, which could estimate the estimated glomerular filtration rate (eGFR). This approach could generate a new application for the kidney function evaluation by a urinary dipstick. The accurate rate was 0.879 and the performance of ANN by area under the curve (AUC) was 0.928. The sensitivity and the specificity were 0.83 and 0.88, respectively. Fourth, we improved the procedures for urine sediment microscopy, which increased the recovery rate of dysmorphic red blood cell (RBC) from 34.7% to 42.0% ( p ＜0.001). This improvement increased the probability of finding dysmorphic RBC in urine sediment microscopy. Also, we applied the Sternheimer stain to increase the contrast between formed elements in urine sediment, which increased the capability to correctly identify renal tubular epithelial cell (RTEC) in urine sediment microscopy.
For future works, the SPR sensor chip for urinary podocalyxin will need to be advanced studied for an optimal condition. This approach will establish a reusable chip, which can be carried out for the calibration procedure in order to measure the level of urinary podocalyxin. The portable chip with microfluidic channels and capillary-gravitational valves has serial functions for sample quantifying, reagent adding, and mixing, which has a potential for a point-of-care test (POCT) developing. And this innovation has a patent by Republic of China, I-446958. ANN has developed a new application for eGFR by a urinary dipstick, which has a good performance and gets two patents by Republic of China M518332 and Japan 6012781. About the improvement of urine sediment microscopy, this modified protocol for urine sediment microscopy has been adopted by Taiwan Society of Laboratory Medicine as the guideline of urine sediment microscopy, TSLM-GP-U01(1).

口試委員會審書
致謝
中文摘要 … I
ABSTRACT … III
CONTENT … VI
FIGURE CAPTION … X
TABLE CAPTION … XII
ABBREVIATION … XIII
Chapter 1 Introduction … 1
1.1 Kidney function and glomerular filtration rate … 4
1.2 Glomerular injury and the evidences of glomerular injury … 6
1.3 Examinations for the evaluation of kidney injury and limitations … 8
1.4 Increasing the convenience and the accuracy of examinations for
CKD screening … 9
Chapter 2 Literatures and theories review … 11
2.1 Urinary podocalyxin biosensor … 11
2.1.1 Podocyte and podocalyxin … 11
2.1.2 Surface plasmon resonance biosensor … 12
2.2 Lab-on-a-chip designed by sequential capillary-gravitational
creatinine detection … 15
2.2.1 Lab-on-a-chip … 15
2.2.2 Microfluidic channels and capillary-gravitational
valves … 16
2.3 Artificial neural networks for estimating glomerular filtration rate by
urinary dipstick for type 2 diabetic patients … 21
2.3.1 Artificial neural networks in medical application … 21
2.3.2 Urinalysis for the screening of CKD … 24
2.4 Enhancing the detection of dysmorphic red blood cells and renal tubular cells with a modified urinalysis protocol … 24
2.4.1 The value of urine sediment microscopy … 25
2.4.2 Discrepancies between guidelines of urine sediment microscopy … 25
Chapter 3 Material and methods …28
3.1 Urinary podocalyxin biosensor … 28
3.2 Lab-on-a-chip designed by sequential capillary-gravitational
creatinine detection … 29
3.2.1 Creatinine chemical assay … 29
3.2.2 Design of the microfluidic channel and capillary-gravitational valves in chip … 30
3.2.3 Detection urinary creatinine with chip … 33
3.3 Artificial neural networks for estimating glomerular filtration rate by
urinary dipstick for type 2 diabetic patients … 35
3.3.1 Blood analysis … 35
3.3.2 Urinalysis … 35
3.3.3 Database and data sets … 38
3.3.4 BPN-ANN analysis … 38
3.4 Enhancing the detection of dysmorphic red blood cells and renal
tubular cells with a modified urinalysis protocol … 41
3.4.1 The settings of urine sample volume, centrifuge duration, concentration factor, and centrifuge force for urine sediment microscopy … 41
3.4.2 Observation method … 42
3.4.3 A modified protocol urine sediment microscopy … 43
Chapter 4 Results … 45
4.1 Urinary podocalyxin biosensor … 45

4.2 Lab-on-a-chip designed by sequential capillary-gravitational
creatinine detection … 50
4.3 Artificial neural networks for estimating glomerular filtration rate by
urinary dipstick for type 2 diabetic patients … 59
4.4 Enhancing the detection of dysmorphic red blood cells and renal
tubular cells with a modified urinalysis protocol … 69
Chapter 5 Discussions and future works … 83
5.1 Urinary podocalyxin biosensor … 83
5.2 Lab-on-a-chip designed by sequential capillary-gravitational
creatinine detection … 83
5.3 Artificial neural networks for estimating glomerular filtration rate by urinary dipstick for type 2 diabetic patients … 84
5.4 Enhancing the detection of dysmorphic red blood cells and renal
tubular cells with a modified urinalysis protocol … 86
5.5 Future works … 89
References … 91
Appendix … 107

[1]A. M. El Nahas and A. K. Bello, "Chronic kidney disease: the global challenge," The Lancet, vol. 365, pp. 331-340, 2005.
[2]"USRDS 2010 Annual Data Report," United States Renal Data System, pp. 223-238.
[3]" USRDS 2015 Annual Data Report," United States Renal Data System, pp. 291-334.
[4]"K/DOQI clinical practice guidelines for chronic kidney disease: evaluation, classification, and stratification," Am J Kidney Dis, vol. 39, pp. S1-266, Feb 2002.
[5]A. S. Levey, K.-U. Eckardt, Y. Tsukamoto, A. Levin, J. Coresh, J. Rossert, D. D. Zeeuw, T. H. Hostetter, N. Lameire, and G. Eknoyan, "Definition and classification of chronic kidney disease: a position statement from Kidney Disease: Improving Global Outcomes (KDIGO)," Kidney international, vol. 67, pp. 2089-2100, 2005.
[6]P. E. Stevens and A. Levin, "Evaluation and management of chronic kidney disease: synopsis of the kidney disease: improving global outcomes 2012 clinical practice guideline," Ann Intern Med, vol. 158, pp. 825-830, 2013.
[7]"USRDS 2013 Annual Data Report," United States Renal Data System, pp. 333-344
[8]"USRDS 2015 Annual Data Report" United States Renal Data System, pp. 13-24.
[9]M. Morcos, A. A. Sayed, A. Bierhaus, B. Yard, R. Waldherr, W. Merz, I. Kloeting, E. Schleicher, S. Mentz, and R. F. A. el Baki, "Activation of tubular epithelial cells in diabetic nephropathy," Diabetes, vol. 51, pp. 3532-3544, 2002.
[10]"USRDS 2005 Annual Data Report," United States Renal Data System, pp. 215-226.
[11]"Population statistics of Taiwan," Misnistry of the Interior, Taiwan, 2013.
[12]"Medicalcare statistics of Taiwan Bureau of National Health Insurance " Taiwan Bureau of National Health Insurance, 2013.
[13]C.-C. Hsu, S.-J. Hwang, C.-P. Wen, H.-Y. Chang, T. Chen, R.-S. Shiu, S.-S. Horng, Y.-K. Chang, and W.-C. Yang, "High prevalence and low awareness of CKD in Taiwan: a study on the relationship between serum creatinine and awareness from a nationally representative survey," American journal of kidney diseases, vol. 48, pp. 727-738, 2006.
[14]V. Jha, G. Garcia-Garcia, K. Iseki, Z. Li, S. Naicker, B. Plattner, R. Saran, A. Y.-M. Wang, and C.-W. Yang, "Chronic kidney disease: global dimension and perspectives," The Lancet, vol. 382, pp. 260-272, 2013.
[15]L. A. Stevens, G. Fares, J. Fleming, D. Martin, K. Murthy, J. Qiu, P. C. Stark, K. Uhlig, F. Van Lente, and A. S. Levey, "Low rates of testing and diagnostic codes usage in a commercial clinical laboratory: evidence for lack of physician awareness of chronic kidney disease," Journal of the American Society of Nephrology, vol. 16, pp. 2439-2448, 2005.
[16]J. E. Hall and A. C. Guyton, Guyton and Hall textbook of medical physiology, 12th ed. Philadelphia, Pa.: Saunders/Elsevier, 2011.
[17]Y. Chu-Su, Atlas of Clinical Microscopy, Second Edition., 9th ed. Taipei: Chu-Su, Yu, 2011.
[18]R. Lewis, N. Kerr, C. Van Buren, P. Lowry, C. Sandler, O. Frazier, P. Powers, J. Herson, J. Corriere Jr, and R. Kerman, "Comparative evaluation of urographic contrast media, inulin, and 99mTc-DTPA clearance methods for determination of glomerular filtration rate in clinical transplantation," Transplantation, vol. 48, pp. 790-795, 1989.
[19]M. Abbate, C. Zoja, and G. Remuzzi, "How does proteinuria cause progressive renal damage?," J Am Soc Nephrol, vol. 17, pp. 2974-84, Nov 2006.
[20]A. B. Fogo, "Mechanisms of progression of chronic kidney disease," Pediatr Nephrol, vol. 22, pp. 2011-22, Dec 2007.
[21]C. Fligny, M. Barton, and P. L. Tharaux, "Endothelin and podocyte injury in chronic kidney disease," Contrib Nephrol, vol. 172, pp. 120-38, 2011.
[22]M. Eiro, T. Katoh, and T. Watanabe, "Risk factors for bleeding complications in percutaneous renal biopsy," Clinical and experimental nephrology, vol. 9, pp. 40-45, 2005.
[23]G. Fuiano, G. Mazza, N. Comi, A. Caglioti, L. De Nicola, C. Iodice, M. Andreucci, and V. E. Andreucci, "Current indications for renal biopsy: a questionnaire-based survey," American journal of kidney diseases, vol. 35, pp. 448-457, 2000.
[24]C.-C. Szeto, F. M.-M. Lai, K.-F. To, T. Y.-H. Wong, K.-M. Chow, P. C.-L. Choi, S.-F. Lui, and P. K.-T. Li, "The natural history of immunoglobulin a nephropathy among patients with hematuria and minimal proteinuria," The American journal of medicine, vol. 110, pp. 434-437, 2001.
[25]A. S. Levey, J. Coresh, E. Balk, A. T. Kausz, A. Levin, M. W. Steffes, R. J. Hogg, R. D. Perrone, J. Lau, and G. Eknoyan, "National Kidney Foundation practice guidelines for chronic kidney disease: evaluation, classification, and stratification," Ann Intern Med, vol. 139, pp. 137-47, Jul 15 2003.
[26]M. E. Molitch, R. A. DeFronzo, M. J. Franz, W. F. Keane, C. E. Mogensen, and H. H. Parving, "Diabetic nephropathy," Diabetes Care, vol. 26 Suppl 1, pp. S94-8, Jan 2003.
[27]Y. Kuan, M. Hossain, J. Surman, A. M. El Nahas, and J. Haylor, "GFR prediction using the MDRD and Cockcroft and Gault equations in patients with end-stage renal disease," Nephrology Dialysis Transplantation, vol. 20, pp. 2394-2401, 2005.
[28]G. Vervoort, H. L. Willems, and J. F. Wetzels, "Assessment of glomerular filtration rate in healthy subjects and normoalbuminuric diabetic patients: validity of a new (MDRD) prediction equation," Nephrology Dialysis Transplantation, vol. 17, pp. 1909-1913, 2002.
[29]E. D. Poggio, X. Wang, T. Greene, F. Van Lente, and P. M. Hall, "Performance of the modification of diet in renal disease and Cockcroft-Gault equations in the estimation of GFR in health and in chronic kidney disease," Journal of the American Society of Nephrology, vol. 16, pp. 459-466, 2005.
[30]E. A. Hoste, J. Damen, R. C. Vanholder, N. H. Lameire, J. R. Delanghe, K. Van den Hauwe, and F. A. Colardyn, "Assessment of renal function in recently admitted critically ill patients with normal serum creatinine," Nephrology Dialysis Transplantation, vol. 20, pp. 747-753, 2005.
[31]L. Duncan, J. Heathcote, O. Djurdjev, and A. Levin, "Screening for renal disease using serum creatinine: who are we missing?," Nephrology Dialysis Transplantation, vol. 16, pp. 1042-1046, 2001.
[32]R. J. Glassock and C. Winearls, "An epidemic of chronic kidney disease: fact or fiction?," Nephrology Dialysis Transplantation, vol. 23, pp. 1117-1121, 2008.
[33]Y.-C. Ma, L. Zuo, J.-H. Chen, Q. Luo, X.-Q. Yu, Y. Li, J.-S. Xu, S.-M. Huang, L.-N. Wang, and W. Huang, "Modified glomerular filtration rate estimating equation for Chinese patients with chronic kidney disease," Journal of the American Society of Nephrology, vol. 17, pp. 2937-2944, 2006.
[34]B. M. Sibai, "Diagnosis and management of gestational hypertension and preeclampsia," Obstetrics and gynecology, vol. 102, pp. 181-192, 2003.
[35]B. R. Hemmelgarn, B. J. Manns, A. Lloyd, M. T. James, S. Klarenbach, R. R. Quinn, N. Wiebe, M. Tonelli, and A. K. D. Network, "Relation between kidney function, proteinuria, and adverse outcomes," Jama, vol. 303, pp. 423-429, 2010.
[36]C. Burton and K. Harris, "The role of proteinuria in the progression of chronic renal failure," American journal of kidney diseases, vol. 27, pp. 765-775, 1996.
[37]J. J. Tsai, J. Y. Yeun, V. A. Kumar, and B. R. Don, "Comparison and interpretation of urinalysis performed by a nephrologist versus a hospital-based clinical laboratory," Am J Kidney Dis, vol. 46, pp. 820-9, Nov 2005.
[38]M. A. Perazella, S. G. Coca, I. E. Hall, U. Iyanam, M. Koraishy, and C. R. Parikh, "Urine microscopy is associated with severity and worsening of acute kidney injury in hospitalized patients," Clin J Am Soc Nephrol, vol. 5, pp. 402-8, Mar 2010.
[39]L. S. Chawla, A. Dommu, A. Berger, S. Shih, and S. S. Patel, "Urinary sediment cast scoring index for acute kidney injury: a pilot study," Nephron Clinical Practice, vol. 110, pp. c145-c150, 2008.
[40]M. A. Perazella, S. G. Coca, M. Kanbay, U. C. Brewster, and C. R. Parikh, "Diagnostic value of urine microscopy for differential diagnosis of acute kidney injury in hospitalized patients," Clinical Journal of the American Society of Nephrology, vol. 3, pp. 1615-1619, 2008.
[41]Y. Chu-Su, "Detection of urine podocalyxin for nephropathy of type II diabetic mellitus," presented at the 9th Asian Conference on Chemical Sensors, Chientan Youth Activity Center, Taipei, Taiwan, 2011.
[42]A.-B. Wang, P.-H. Fang, Y. Chu-Su, Y.-W. Hsieh, C.-W. Lin, Y.-T. Chen, and Y.-C. Hsu, "A novel lab-on-a-chip design by sequential capillary–gravitational valves for urinary creatinine detection," Sensors and Actuators B: Chemical, vol. 222, pp. 721-727, 2016.
[43]Y. Chu-Su, C.-S. Liu, R.-S. Chen, and C.-W. Lin, "Artificial neural networks for estimating glomerular filtration rate by urinary dipstick for type 2 diabetic patients," Biomedical Engineering: Applications, Basis and Communications, vol. 28, p. 1650016, 2016.
[44]Y. Chu-Su, K. Shukuya, T. Yokoyama, W.-C. Lin, C.-K. Chiang, and C.-W. Lin, "Enhancing the Detection of Dysmorphic Red Blood Cells and Renal Tubular Epithelial Cells with a Modified Urinalysis Protocol," Scientific Reports, vol. 7, p. 40521, 2017.
[45]T. Nakamura, C. Ushiyama, S. Suzuki, M. Hara, N. Shimada, I. Ebihara, and H. Koide, "Urinary excretion of podocytes in patients with diabetic nephropathy," Nephrology Dialysis Transplantation, vol. 15, pp. 1379-1383, 2000.
[46]S. U. Vogelmann, W. J. Nelson, B. D. Myers, and K. V. Lemley, "Urinary excretion of viable podocytes in health and renal disease," American Journal of Physiology-Renal Physiology, vol. 285, pp. F40-F48, 2003.
[47]E. J. Weil, K. V. Lemley, C. C. Mason, B. Yee, L. I. Jones, K. Blouch, T. Lovato, M. Richardson, B. D. Myers, and R. G. Nelson, "Podocyte detachment and reduced glomerular capillary endothelial fenestration promote kidney disease in type 2 diabetic nephropathy," Kidney international, vol. 82, pp. 1010-1017, 2012.
[48]M. Dalla Vestra, A. Masiero, A. M. Roiter, A. Saller, G. Crepaldi, and P. Fioretto, "Is podocyte injury relevant in diabetic nephropathy? Studies in patients with type 2 diabetes," Diabetes, vol. 52, pp. 1031-1035, 2003.
[49]D. B. Kershaw, P. E. Thomas, B. L. Wharram, M. Goyal, J. E. Wiggins, C. I. Whiteside, and R. C. Wiggins, "Molecular cloning, expression, and characterization of podocalyxin-like protein 1 from rabbit as a transmembrane protein of glomerular podocytes and vascular endothelium," Journal of Biological Chemistry, vol. 270, pp. 29439-29446, 1995.
[50]A. Padiyar and J. Sedor, "Genetic and genomic approaches to glomerulosclerosis," Current molecular medicine, vol. 5, pp. 497-507, 2005.
[51]R. G. Fassett, S. K. Venuthurupalli, G. C. Gobe, J. S. Coombes, M. A. Cooper, and W. E. Hoy, "Biomarkers in chronic kidney disease: a review," Kidney international, vol. 80, pp. 806-821, 2011.
[52]H. Ye, X. Bai, H. Gao, L. Li, C. Wu, X. Sun, C. Zhang, Y. Shen, J. Zhang, and Z. Lu, "Urinary podocalyxin positive-element occurs in the early stage of diabetic nephropathy and is correlated with a clinical diagnosis of diabetic nephropathy," Journal of Diabetes and its Complications, vol. 28, pp. 96-100, 2014.
[53]J. Homola, S. S. Yee, and G. Gauglitz, "Surface plasmon resonance sensors: review," Sensors and Actuators B: Chemical, vol. 54, pp. 3-15, 1999.
[54]P. A. Van Der Merwe, "Surface plasmon resonance, Oxford University Press: New York, NY, USA, 2001, pp. 137-170.
[55]Y.-H. Lin, S.-H. Wang, M.-H. Wu, T.-M. Pan, C.-S. Lai, J.-D. Luo, and C.-C. Chiou, "Integrating solid-state sensor and microfluidic devices for glucose, urea and creatinine detection based on enzyme-carrying alginate microbeads," Biosensors and Bioelectronics, vol. 43, pp. 328-335, 2013.
[56]Y.-H. Lin, C.-H. Chiang, M.-H. Wu, T.-M. Pan, J.-D. Luo, and C.-C. Chiou, "Solid-state sensor incorporated in microfluidic chip and magnetic-bead enzyme immobilization approach for creatinine and glucose detection in serum," Applied Physics Letters, vol. 99, p. 253704, 2011.
[57]A. Soldatkin, J. Montoriol, W. Sant, C. Martelet, and N. Jaffrezic-Renault, "Development of potentiometric creatinine-sensitive biosensor based on ISFET and creatinine deiminase immobilised in PVA/SbQ photopolymeric membrane," Materials Science and Engineering: C, vol. 21, pp. 75-79, 2002.
[58]K. L. Schnabl, S. Bagherpoor, P. Diker, C. Cursio, J. DuBois, and P. M. Yip, "Evaluation of the analytical performance of the Nova StatSensor creatinine meter and reagent strip technology for whole blood testing," Clinical biochemistry, vol. 43, pp. 1026-1029, 2010.
[59]S. Chakraborty, "Dynamics of capillary flow of blood into a microfluidic channel," Lab on a Chip, vol. 5, pp. 421-430, 2005.
[60]H. Cho, H. Y. Kim, J. Y. Kang, and T. S. Kim, "How the capillary burst microvalve works," J Colloid Interface Sci, vol. 306, pp. 379-85, Feb 15 2007.
[61]H. Cho, H.-Y. Kim, J. Y. Kang, and T. S. Kim, "How the capillary burst microvalve works," Journal of colloid and interface science, vol. 306, pp. 379-385, 2007.
[62]Hachiro Yamanishi, Masami Hotta, Soyoko Moromoto, and N. Imai, "Probability that estimated GFR is less than 60ml/min/1.73m2 calculated from results of urinary test strip," Medical Technology, vol. 58, pp. 1311-1316, 2009.
[63]J. V. Tu, "Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes," Journal of clinical epidemiology, vol. 49, pp. 1225-1231, 1996.
[64]J. T. Wei, Z. Zhang, S. D. Barnhill, K. R. Madyastha, H. Zhang, and J. E. Oesterling, "Understanding artificial neural networks and exploring their potential applications for the practicing urologist," Urology, vol. 52, pp. 161-172, 1998.
[65]P. J. Lisboa, "A review of evidence of health benefit from artificial neural networks in medical intervention," Neural networks, vol. 15, pp. 11-39, 2002.
[66]M. E. Molitch, R. A. Defronzo, M. J. Franz, W. F. Keane, C. E. Mogensen, H. Parving, and M. Steffes, "Nephropathy in diabetes," Diabetes Care, vol. 27, pp. S79-83, 2004.
[67]K. Yamagata, K. Iseki, K. Nitta, H. Imai, Y. Iino, S. Matsuo, H. Makino, and A. Hishida, "Chronic kidney disease perspectives in Japan and the importance of urinalysis screening," Clinical and experimental nephrology, vol. 12, pp. 1-8, 2008.
[68]J. A. Vassalotti, L. A. Stevens, and A. S. Levey, "Testing for chronic kidney disease: a position statement from the National Kidney Foundation," American journal of kidney diseases, vol. 50, pp. 169-180, 2007.
[69]S. L. White, R. Yu, J. C. Craig, K. R. Polkinghorne, R. C. Atkins, and S. J. Chadban, "Diagnostic accuracy of urine dipsticks for detection of albuminuria in the general community," American journal of kidney diseases, vol. 58, pp. 19-28, 2011.
[70]K. F. Fairley and D. F. Birch, "Hematuria: a simple method for identifying glomerular bleeding," Kidney international, vol. 21, pp. 105-108, 1982.
[71]B. S. Chang, "Red cell morphology as a diagnostic aid in hematuria," Jama, vol. 252, pp. 1747-1749, 1984.
[72]G. J. Becker, G. Garigali, and G. B. Fogazzi, "Advances in urine microscopy," American journal of kidney diseases, vol. 67, pp. 954-964, 2016.
[73]G. B. Fogazzi and G. Garigali, "The clinical art and science of urine microscopy," Current opinion in nephrology and hypertension, vol. 12, pp. 625-632, 2003.
[74]M. A. Perazella, "The urine sediment as a biomarker of kidney disease," American journal of kidney diseases, vol. 66, pp. 748-755, 2015.
[75]O. Hotta, N. Yusa, H. Kitamura, and Y. Taguma, "Urinary macrophages as activity markers of renal injury," Clinica chimica acta, vol. 297, pp. 123-133, 2000.
[76]J. M. Sutton, "Urinary eosinophils," Archives of internal medicine, vol. 146, pp. 2243-2244, 1986.
[77]R. W. Chan, F. M. Lai, E. K. Li, L. Tam, K. Chung, K. Chow, P. K. Li, and C. Szeto, "Urinary mononuclear cell and disease activity of systemic lupus erythematosus," Lupus, vol. 15, pp. 262-267, 2006.
[78]G. B. Fogazzi, M. Cantú, and L. Saglimbeni, "‘Decoy cells’ in the urine due to polyomavirus BK infection: easily seen by phase‐contrast microscopy," Nephrology Dialysis Transplantation, vol. 16, pp. 1496-1498, 2001.
[79]D. Birch and K. Fairley, "Haematuria: glomerular or non-glomerular?," The Lancet, vol. 314, pp. 845-846, 1979.
[80]M. Kanbay, B. Kasapoglu, and M. A. Perazella, "Acute tubular necrosis and pre-renal acute kidney injury: utility of urine microscopy in their evaluation-a systematic review," International urology and nephrology, vol. 42, pp. 425-433, 2010.
[81]"European urinalysis guidelines," Scand J Clin Lab Invest Suppl, vol. 231, pp. 1-86, 2000.
[82]CLSI, Urinalysis; Approved guideline - Third Edition, GP 16 A-3 2nd ed. Wayne, Pa.: Clinical and Laboratory Standards Institute, 2009.
[83]G. D. Grossfeld, J. S. Wolf, Jr., M. S. Litwan, H. Hricak, C. L. Shuler, D. C. Agerter, and P. R. Carroll, "Asymptomatic microscopic hematuria in adults: summary of the AUA best practice policy recommendations," Am Fam Physician, vol. 63, pp. 1145-54, Mar 15 2001.
[84]JCCLS, Urine Sediement Microscopy, Guideline GP1–P4. Tokyo: Japanese Committee for Clinical Laboratory Standards, 2010.
[85]C.-C. Chang, N.-F. Chiu, D. S. Lin, Y. Chu-Su, Y.-H. Liang, and C.-W. Lin, "High-sensitivity detection of carbohydrate antigen 15-3 using a gold/zinc oxide thin film surface plasmon resonance-based biosensor," Analytical chemistry, vol. 82, pp. 1207-1212, 2010.
[86]H. Husdan and A. Rapoport, "Estimation of creatinine by the Jaffe reaction. A comparison of three methods," Clin Chem, vol. 14, pp. 222-38, Mar 1968.
[87]R. A. McPherson, M. R. Pincus, and J. B. Henry, Henry''s clinical diagnosis and management by laboratory methods, 21st ed. Philadelphia: Saunders Elsevier, 2007.
[88]V. Rigalleau, C. Lasseur, C. Perlemoine, N. Barthe, C. Raffaitin, C. Liu, P. Chauveau, L. Baillet-Blanco, M.-C. Beauvieux, and C. Combe, "Estimation of glomerular filtration rate in diabetic subjects," Diabetes Care, vol. 28, pp. 838-843, 2005.
[89]F. Angst, A. Aeschlimann, and G. Stucki, "Smallest detectable and minimal clinically important differences of rehabilitation intervention with their implications for required sample sizes using WOMAC and SF-36 quality of life measurement instruments in patients with osteoarthritis of the lower extremities," Arthritis Rheum, vol. 45, pp. 384-91, Aug 2001.
[90]G. D. Israel, Determining sample size: University of Florida Cooperative Extension Service, Institute of Food and Agriculture Sciences, EDIS, 1992.
[91]C.-S. Liu, W.-K. Tseng, J.-K. Lee, T.-C. Hsiao, and C.-W. Lin, "The differential method of phase space matrix for AF/VF discrimination application," Medical engineering & physics, vol. 32, pp. 444-453, 2010.
[92]H. Kohler, E. Wandel, and B. Brunck, "Acanthocyturia--a characteristic marker for glomerular bleeding," Kidney Int, vol. 40, pp. 115-20, Jul 1991.
[93]J. Chen, P. Muntner, L. L. Hamm, V. Fonseca, V. Batuman, P. K. Whelton, and J. He, "Insulin resistance and risk of chronic kidney disease in nondiabetic US adults," Journal of the American Society of Nephrology, vol. 14, pp. 469-477, 2003.
[94]C. Edwards, "Growing pains for deep learning," Communications of the ACM, vol. 58, pp. 14-16, 2015.
[95]J. Schmidhuber, "Deep learning in neural networks: an overview," Neural Netw, vol. 61, pp. 85-117, Jan 2015.
[96]B. Lettgen and A. Wohlmuth, "Validity of G1-cells in the differentiation between glomerular and non-glomerular haematuria in children," Pediatr Nephrol, vol. 9, pp. 435-7, Aug 1995.
[97]A. K. Dinda, S. Saxena, S. Guleria, S. C. Tiwari, S. C. Dash, R. N. Srivastava, and C. Singh, "Diagnosis of glomerular haematuria: role of dysmorphic red cell, G1 cell and bright-field microscopy," Scand J Clin Lab Invest, vol. 57, pp. 203-8, May 1997.
[98]M. Kanbay, B. Kasapoglu, and M. A. Perazella, "Acute tubular necrosis and pre-renal acute kidney injury: utility of urine microscopy in their evaluation- a systematic review," Int Urol Nephrol, vol. 42, pp. 425-33, Jun 2010.