Dataset Information

Machine-learning enhancement of urine dipstick tests for chronic kidney disease detection.

ABSTRACT:

Objective

Screening for chronic kidney disease (CKD) requires an estimated glomerular filtration rate (eGFR, mL/min/1.73 m2) from a blood sample and a proteinuria level from a urinalysis. We developed machine-learning models to detect CKD without blood collection, predicting an eGFR less than 60 (eGFR60 model) or 45 (eGFR45 model) using a urine dipstick test.

Materials and methods

The electronic health record data (n = 220 018) obtained from university hospitals were used for XGBoost-derived model construction. The model variables were age, sex, and 10 measurements from the urine dipstick test. The models were validated using health checkup center data (n = 74 380) and nationwide public data (KNHANES data, n = 62 945) for the general population in Korea.

Results

The models comprised 7 features, including age, sex, and 5 urine dipstick measurements (protein, blood, glucose, pH, and specific gravity). The internal and external areas under the curve (AUCs) of the eGFR60 model were 0.90 or higher, and a higher AUC for the eGFR45 model was obtained. For the eGFR60 model on KNHANES data, the sensitivity was 0.93 or 0.80, and the specificity was 0.86 or 0.85 in ages less than 65 with proteinuria (nondiabetes or diabetes, respectively). Nonproteinuric CKD could be detected in nondiabetic patients under the age of 65 with a sensitivity of 0.88 and specificity of 0.71.

Discussion and conclusions

The model performance differed across subgroups by age, proteinuria, and diabetes. The CKD progression risk can be assessed with the eGFR models using the levels of eGFR decrease and proteinuria. The machine-learning-enhanced urine-dipstick test can become a point-of-care test to promote public health by screening CKD and ranking its risk of progression.

SUBMITTER: Jang EC

PROVIDER: S-EPMC10198537 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine-learning enhancement of urine dipstick tests for chronic kidney disease detection.

Jang Eun Chan EC Park Young Min YM Han Hyun Wook HW Lee Christopher Seungkyu CS Kang Eun Seok ES Lee Yu Ho YH Nam Sang Min SM

Journal of the American Medical Informatics Association : JAMIA 20230501 6

<h4>Objective</h4>Screening for chronic kidney disease (CKD) requires an estimated glomerular filtration rate (eGFR, mL/min/1.73 m2) from a blood sample and a proteinuria level from a urinalysis. We developed machine-learning models to detect CKD without blood collection, predicting an eGFR less than 60 (eGFR60 model) or 45 (eGFR45 model) using a urine dipstick test.<h4>Materials and methods</h4>The electronic health record data (n = 220 018) obtained from university hospitals were used for XGBo ...[more]

PMID: 37027837

Similar Datasets

Project description:BackgroundChronic kidney disease (CKD) is a prevalent condition with significant global health implications. Early detection and management are critical to prevent disease progression and complications. Deep learning (DL) models using retinal images have emerged as potential noninvasive screening tools for CKD, though their performance may be limited, especially in identifying individuals with proteinuria and in specific subgroups.ObjectiveWe aim to evaluate the efficacy of integrating retinal images and urine dipstick data into DL models for enhanced CKD diagnosis.MethodsThe 3 models were developed and validated: eGFR-RIDL (estimated glomerular filtration rate-retinal image deep learning), eGFR-UDLR (logistic regression using urine dipstick data), and eGFR-MMDL (multimodal deep learning combining retinal images and urine dipstick data). All models were trained to predict an eGFR<60 mL/min/1.73 m², a key indicator of CKD, calculated using the 2009 CKD-EPI (Chronic Kidney Disease Epidemiology Collaboration) equation. This study used a multicenter dataset of participants aged 20-79 years, including a development set (65,082 people) and an external validation set (58,284 people). Wide Residual Networks were used for DL, and saliency maps were used to visualize model attention. Sensitivity analyses assessed the impact of numerical variables.ResultseGFR-MMDL outperformed eGFR-RIDL in both the test and external validation sets, with area under the curves of 0.94 versus 0.90 and 0.88 versus 0.77 (P<.001 for both, DeLong test). eGFR-UDLR outperformed eGFR-RIDL and was comparable to eGFR-MMDL, particularly in the external validation. However, in the subgroup analysis, eGFR-MMDL showed improvement across all subgroups, while eGFR-UDLR demonstrated no such gains. This suggested that the enhanced performance of eGFR-MMDL was not due to urine data alone, but rather from the synergistic integration of both retinal images and urine data. The eGFR-MMDL model demonstrated the best performance in individuals younger than 65 years or those with proteinuria. Age and proteinuria were identified as critical factors influencing model performance. Saliency maps indicated that urine data and retinal images provide complementary information, with urine offering insights into retinal abnormalities and retinal images, particularly the arcade vessels, being key for predicting kidney function.ConclusionsThe MMDL model integrating retinal images and urine dipstick data show significant promise for noninvasive CKD screening, outperforming the retinal image-only model. However, routine blood tests are still recommended for individuals aged 65 years and older due to the model's limited performance in this age group.

Project description:BackgroundIndividual lifestyle varies in the real world, and the comparative efficacy of lifestyles to preserve renal function remains indeterminate. We aimed to systematically compare the effects of lifestyles on chronic kidney disease (CKD) incidence, and establish a lifestyle scoring system for CKD risk identification.MethodsUsing the data of the UK Biobank cohort, we included 470,778 participants who were free of CKD at the baseline. We harnessed the light gradient boosting machine algorithm to rank the importance of 37 lifestyle factors (such as dietary patterns, physical activity (PA), sleep, psychological health, smoking, and alcohol) on the risk of CKD. The lifestyle score was calculated by a combination of machine learning and the Cox proportional-hazards model. A CKD event was defined as an estimated glomerular filtration rate <60 ml/min/1.73 m2, mortality and hospitalization due to chronic renal failure, and self-reported chronic renal failure, initiated renal replacement therapy.ResultsDuring a median of the 11-year follow-up, 13,555 participants developed the CKD event. Bread, walking time, moderate activity, and vigorous activity ranked as the top four risk factors of CKD. A healthy lifestyle mainly consisted of whole grain bread, walking, moderate physical activity, oat cereal, and muesli, which have scored 12, 12, 10, 7, and 7, respectively. An unhealthy lifestyle mainly included white bread, tea >4 cups/day, biscuit cereal, low drink temperature, and processed meat, which have scored -12, -9, -7, -4, and -3, respectively. In restricted cubic spline regression analysis, a higher lifestyle score was associated with a lower risk of CKD event (p for linear relation < 0.001). Compared to participants with the lifestyle score < 0, participants scoring 0-20, 20-40, 40-60, and >60 exhibited 25, 42, 55, and 70% lower risk of CKD event, respectively. The C-statistic of the age-adjusted lifestyle score for predicting CKD events was 0.710 (0.703-0.718).ConclusionA lifestyle scoring system for CKD prevention was established. Based on the system, individuals could flexibly choose healthy lifestyles and avoid unhealthy lifestyles to prevent CKD.

Project description:BackgroundAlthough measuring albuminuria is the preferred method for defining and staging chronic kidney disease (CKD), total urine protein or dipstick protein is often measured instead.ObjectiveTo develop equations for converting urine protein-creatinine ratio (PCR) and dipstick protein to urine albumin-creatinine ratio (ACR) and to test their diagnostic accuracy in CKD screening and staging.DesignIndividual participant-based meta-analysis.Setting12 research and 21 clinical cohorts.Participants919 383 adults with same-day measures of ACR and PCR or dipstick protein.MeasurementsEquations to convert urine PCR and dipstick protein to ACR were developed and tested for purposes of CKD screening (ACR ≥30 mg/g) and staging (stage A2: ACR of 30 to 299 mg/g; stage A3: ACR ≥300 mg/g).ResultsMedian ACR was 14 mg/g (25th to 75th percentile of cohorts, 5 to 25 mg/g). The association between PCR and ACR was inconsistent for PCR values less than 50 mg/g. For higher PCR values, the PCR conversion equations demonstrated moderate sensitivity (91%, 75%, and 87%) and specificity (87%, 89%, and 98%) for screening (ACR >30 mg/g) and classification into stages A2 and A3, respectively. Urine dipstick categories of trace or greater, trace to +, and ++ for screening for ACR values greater than 30 mg/g and classification into stages A2 and A3, respectively, had moderate sensitivity (62%, 36%, and 78%) and high specificity (88%, 88%, and 98%). For individual risk prediction, the estimated 2-year 4-variable kidney failure risk equation using predicted ACR from PCR had discrimination similar to that of using observed ACR.LimitationDiverse methods of ACR and PCR quantification were used; measurements were not always performed in the same urine sample.ConclusionUrine ACR is the preferred measure of albuminuria; however, if ACR is not available, predicted ACR from PCR or urine dipstick protein may help in CKD screening, staging, and prognosis.Primary funding sourceNational Institute of Diabetes and Digestive and Kidney Diseases and National Kidney Foundation.

Dataset Information

Machine-learning enhancement of urine dipstick tests for chronic kidney disease detection.

Objective

Materials and methods

Results

Discussion and conclusions

Publications

Machine-learning enhancement of urine dipstick tests for chronic kidney disease detection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets