1
|
Li YX, Li Y, Bao SY, Xue N, Ding XQ, Fang Y. The application of new complex indicators in the detection of urine. BMC Nephrol 2023; 24:45. [PMID: 36849937 PMCID: PMC9972632 DOI: 10.1186/s12882-023-03087-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2022] [Accepted: 02/15/2023] [Indexed: 03/01/2023] Open
Abstract
BACKGROUND Accurate diagnosis and assessment of hematuria is crucial for the early detection of chronic kidney disease(CKD). As instability of urinary RBC count (URBC) often results with clinical uncertainty, therefore new urinary indexes are demanded to improve the accuracy of diagnosis of hematuria. In this study, we aimed to investigate the benefit of applying new complex indicators based on random urine red blood cell counts confirmed in hematuric kidney diseases. METHODS All patients enrolled underwent renal biopsy, and their clinical information was collected. Urinary and blood biomedical indexes were implemented with red blood cell counts to derive complex indicators. Patients were divided into two groups (hematuria-dominant renal histologic lesions and non-hematuria-dominant renal histologic lesions) based on their renal pathological manifestations. The target index was determined by comparing the predictive capabilities of the candidate parameters for hematuric kidney diseases. Hematuria stratification was divided into four categories based on the scale of complex indicators and distributional features. The practicality of the new complex indicators was demonstrated by fitting candidate parameters to models comprising demographic information. RESULTS A total of 1,066 cases (678 hematuria-dominant renal histologic lesions) were included in this study, with a mean age of 44.9 ± 15 years. In differentiating hematuria-dominant renal histologic lesion from the non-hematuria-dominant renal histologic lesion, the AUC value of "The ratio of the random URBC to 24-h albumin excretion" was 0.76, higher than the standard approach of Lg (URBC) [AUC = 0.744] (95% Confidence interval (CI) 0.712 ~ 0.776). The odds ratio of hematuria-dominant renal histologic lesion (Type I) increased from Q2 (3.81, 95% CI 2.66 ~ 5.50) to Q4 (14.17, 95% CI 9.09 ~ 22.72). The predictive model, composed of stratification of new composite indexes, basic demographic characteristics, and biochemical parameters, performed best with AUC value of 0.869 (95% CI 0.856-0.905). CONCLUSION The new urinary complex indicators improved the diagnostic accuracy of hematuria and may serve as a useful parameter for screening hematuric kidney diseases.
Collapse
Affiliation(s)
- Ying-Xiang Li
- Department of Nephrology, Zhongshan Hospital, Fudan University, 111 Yixueyuan Road, Shanghai, 200032, China.,Shanghai Key laboratory of Kidney and Blood Purification, Shanghai, 200032, China
| | - Yang Li
- Department of Nephrology, Zhongshan Hospital, Fudan University, 111 Yixueyuan Road, Shanghai, 200032, China.,Shanghai Medical Center of Kidney Disease, Shanghai, 200032, China.,Shanghai Institute of Kidney Disease and Dialysis, Shanghai, 200032, China.,Shanghai Key laboratory of Kidney and Blood Purification, Shanghai, 200032, China
| | - Si-Yu Bao
- Department of Nephrology, Zhongshan Hospital, Fudan University, 111 Yixueyuan Road, Shanghai, 200032, China.,Shanghai Key laboratory of Kidney and Blood Purification, Shanghai, 200032, China
| | - Ning Xue
- Department of Nephrology, Zhongshan Hospital, Fudan University, 111 Yixueyuan Road, Shanghai, 200032, China.,Shanghai Medical Center of Kidney Disease, Shanghai, 200032, China.,Shanghai Institute of Kidney Disease and Dialysis, Shanghai, 200032, China.,Shanghai Key laboratory of Kidney and Blood Purification, Shanghai, 200032, China
| | - Xiao-Qiang Ding
- Department of Nephrology, Zhongshan Hospital, Fudan University, 111 Yixueyuan Road, Shanghai, 200032, China.,Shanghai Medical Center of Kidney Disease, Shanghai, 200032, China.,Shanghai Institute of Kidney Disease and Dialysis, Shanghai, 200032, China.,Shanghai Key laboratory of Kidney and Blood Purification, Shanghai, 200032, China
| | - Yi Fang
- Department of Nephrology, Zhongshan Hospital, Fudan University, 111 Yixueyuan Road, Shanghai, 200032, China. .,Shanghai Medical Center of Kidney Disease, Shanghai, 200032, China. .,Shanghai Institute of Kidney Disease and Dialysis, Shanghai, 200032, China. .,Shanghai Key laboratory of Kidney and Blood Purification, Shanghai, 200032, China.
| |
Collapse
|
2
|
Keshvari-Shad F, Hajebrahimi S, Pilar Laguna Pes M, Mahboub-Ahari A, Nouri M, Seyednejad F, Yousefi M. A Systematic Review of Screening Tests for Chronic Kidney Disease: An Accuracy Analysis. Galen Med J 2020; 9:e1573. [PMID: 34466554 PMCID: PMC8344133 DOI: 10.31661/gmj.v9i0.1573] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2019] [Revised: 07/25/2019] [Accepted: 08/13/2019] [Indexed: 12/18/2022] Open
Abstract
This systematic review was conducted to assess the diagnostic accuracy of chronic kidney disease screening tests in the general population. MEDLINE, EMBASE, Web of Science, Scopus, The Cochrane Library and ProQuest databases were searched for English-language publications up to November 2016. Two reviewers independently screened studies and extracted study data in standardized tables. Methodological quality was assessed using the QUADAS-2 tool. Sensitivity and specificity of all available screening methods were identified through included studies. Ten out of 1349 screened records included for final analysis. Sensitivities of the dipstick test with a cutoff value of trace were ranged from 37.1% to 69.4% and specificities from 93.7% to 97.3% for the detection of ACR>30 mg/g. The diagnostic sensitivities of the UAC>10 mg/dL testing was shown to vary from 40% to 87%, and specificities ranged from 75% to 96%. While the sensitivities of ACR were fluctuating between 74% and 90%, likewise the specificities were between 77% and 88%. Sensitivities for C-G, Grubb and Larsson equations were 98.9%, 86.2%, and 70.1% respectively. In the meantime the study showed specificities of 84.8%, 84.2% and 90.5% respectively for these equations. Individual studies were highly heterogeneous in terms of target populations, type of screening tests, thresholds used to detect CKD and variations in design. Results pointed to the superiority of UAC and dipstick over the other tests in terms of all parameters involved. The diversity of methods and thresholds for detection of CKD, necessitate considering the cost parameter along with the effectiveness of tests to scale-up an efficient strategy.
Collapse
Affiliation(s)
- Fatemeh Keshvari-Shad
- Department of Health Economics, School of Management and Medical Informatics, Tabriz University of Medical Sceinecs, Tabriz, Iran
| | - Sakineh Hajebrahimi
- Research Center for Evidence Based Medicine, Faculty of Medicine, Urology Department, Tabriz University of Medical Sciences, Tabriz, Iran
| | | | - Alireza Mahboub-Ahari
- Department of Health Economics, Iranian Evidence-Based Medicine Center of Excellence, School of Management and Medical Informatics, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Mohammad Nouri
- Department of Biochemistry and Clinical Laboratories, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Farshad Seyednejad
- Department of Radiation Oncology, Madani Hospital, Tabriz Medical University, Tabriz, Iran
| | - Mahmood Yousefi
- Department of Health Economics, Iranian Center of Excellence in Health Management, School of Management and Medical Informatics, Tabriz University of Medical Sciences, Tabriz, Iran
- Correspondence to: Mahmood Yousefi, Department of Health Economics, Iranian Center of Excellence in Health Management, School of Management and Medical Informatics, Tabriz University of Medical Sciences, Tabriz, Iran Telephone Number: 09121755785 Email Address:
| |
Collapse
|
3
|
Kuo CC, Chang CM, Liu KT, Lin WK, Chiang HY, Chung CW, Ho MR, Sun PR, Yang RL, Chen KT. Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning. NPJ Digit Med 2019; 2:29. [PMID: 31304376 PMCID: PMC6550224 DOI: 10.1038/s41746-019-0104-2] [Citation(s) in RCA: 97] [Impact Index Per Article: 19.4] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2018] [Accepted: 03/19/2019] [Indexed: 12/22/2022] Open
Abstract
Prediction of kidney function and chronic kidney disease (CKD) through kidney ultrasound imaging has long been considered desirable in clinical practice because of its safety, convenience, and affordability. However, this highly desirable approach is beyond the capability of human vision. We developed a deep learning approach for automatically determining the estimated glomerular filtration rate (eGFR) and CKD status. We exploited the transfer learning technique, integrating the powerful ResNet model pretrained on an ImageNet dataset in our neural network architecture, to predict kidney function based on 4,505 kidney ultrasound images labeled using eGFRs derived from serum creatinine concentrations. To further extract the information from ultrasound images, we leveraged kidney length annotations to remove the peripheral region of the kidneys and applied various data augmentation schemes to produce additional data with variations. Bootstrap aggregation was also applied to avoid overfitting and improve the model's generalization. Moreover, the kidney function features obtained by our deep neural network were used to identify the CKD status defined by an eGFR of <60 ml/min/1.73 m2. A Pearson correlation coefficient of 0.741 indicated the strong relationship between artificial intelligence (AI)- and creatinine-based GFR estimations. Overall CKD status classification accuracy of our model was 85.6% -higher than that of experienced nephrologists (60.3%-80.1%). Our model is the first fundamental step toward realizing the potential of transforming kidney ultrasound imaging into an effective, real-time, distant screening tool. AI-GFR estimation offers the possibility of noninvasive assessment of kidney function, a key goal of AI-powered functional automation in clinical practice.
Collapse
Affiliation(s)
- Chin-Chi Kuo
- Big Data Center, China Medical University Hospital, China Medical University, Taichung, Taiwan
- Kidney Institute and Division of Nephrology, Department of Internal Medicine, China Medical University Hospital and College of Medicine, China Medical University, Taichung, Taiwan
| | - Chun-Min Chang
- Institute of Information Science, Academia Sinica, Taichung, Taiwan
| | - Kuan-Ting Liu
- Institute of Information Science, Academia Sinica, Taichung, Taiwan
| | - Wei-Kai Lin
- Institute of Information Science, Academia Sinica, Taichung, Taiwan
| | - Hsiu-Yin Chiang
- Big Data Center, China Medical University Hospital, China Medical University, Taichung, Taiwan
| | - Chih-Wei Chung
- Big Data Center, China Medical University Hospital, China Medical University, Taichung, Taiwan
| | - Meng-Ru Ho
- Institute of Information Science, Academia Sinica, Taichung, Taiwan
| | - Pei-Ran Sun
- Information Office, China Medical University Hospital, China Medical University, Taichung, Taiwan
| | - Rong-Lin Yang
- Information Office, China Medical University Hospital, China Medical University, Taichung, Taiwan
| | - Kuan-Ta Chen
- Institute of Information Science, Academia Sinica, Taichung, Taiwan
| |
Collapse
|
4
|
Xue N, Fang Y, Ding X, Wang L, Xu L, Jiang X, Zhang X. Serum Triglycerides Are Related to Chronic Kidney Disease (CKD) Stage 2 in Young and Middle-Aged Chinese Individuals During Routine Health Examination. Med Sci Monit 2019; 25:2445-2451. [PMID: 30944297 PMCID: PMC6461005 DOI: 10.12659/msm.913506] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND The aim of this study was to determine the risk factors for early chronic kidney disease (CKD) (GFR 60-89 ml/min/1.73 m²; CKD stage 2) in asymptomatic Chinese individuals undergoing routine health examination. MATERIAL AND METHODS This cross-sectional study enrolled 9100 individuals who received voluntary medical examinations between 10/01/2011 and 09/30/2017. Demographic data, clinical history, clinical examination, medication, smoking, alcohol, blood biochemistry, urinalysis, and carotid ultrasound were extracted from the medical records. All laboratory analyses were performed routinely. Multivariable logistic regression for factors predicting CKD stage 2 was performed. RESULTS A total of 9100 individuals were enrolled (age of 18-65 and 65.4% male). CKD stage 2 was found in 1989/9100 individuals (21.9%). Male gender (OR=6.711, 95%CI: 5.376-8.403, P<0.001), older age (OR=1.077, 95%CI: 1.068-1.086, P<0.001), hemoglobin levels (OR=1.051, 95%CI: 1.046-1.057, P<0.001), triglycerides levels (OR=1.174, 95%CI: 1.067-1.292, P=0.001), HDL-C (OR=0.539, 95%CI: 0.380-0.763, P<0.001), Lp(a) levels (OR=1.000, 95%CI: 1.000-1.001, P=0.03), and carotid atherosclerosis (OR=1.248, 95%CI: 1.005-1.550, P=0.045) were associated with CKD stage 2 among all subjects. Serum triglycerides levels were associated with CKD stage 2 in the 18-45 and 45-65 years of age subgroups. CONCLUSIONS Factors that are routinely assessed during routine health examinations (male gender, age, hemoglobin levels, triglycerides levels, HDL-C, Lp(a) levels, and carotid atherosclerosis) can help identify individuals at higher risk of having CKD stage 2. The Chinese dyslipidemia is characterized by high triglycerides and low HDL-C and occurs in young and middle-aged individuals. Those factors could help identify individuals at higher risk for CKD stage 2 and who could benefit from preventive treatments.
Collapse
Affiliation(s)
- Ning Xue
- Department of Nephrology, Zhongshan Hospital, Fudan University, Shanghai, China (mainland)
| | - Yi Fang
- Department of Nephrology, Zhongshan Hospital, Fudan University, Shanghai, China (mainland)
| | - Xiaoqiang Ding
- Department of Nephrology, Zhongshan Hospital, Fudan University, Shanghai, China (mainland)
| | - Li Wang
- Department of Nephrology, Zhongshan Hospital, Fudan University, Shanghai, China (mainland)
| | - Linghan Xu
- Department of Nephrology, Zhongshan Hospital, Fudan University, Shanghai, China (mainland)
| | - Xiaotian Jiang
- Department of Nephrology, Zhongshan Hospital, Fudan University, Shanghai, China (mainland)
| | - Xiaoyan Zhang
- Department of Nephrology, Zhongshan Hospital, Fudan University, Shanghai, China (mainland)
| |
Collapse
|