Screening Strategies for Unrecognized CKD

Komenda, Paul; Rigatto, Claudio; Tangri, Navdeep

doi:10.2215/cjn.04190416

Cited by 17 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…38 By contrast, the American Society of Nephrology strongly recommends regular screening of CKD, given its clinical silence and preventable progression with relatively low cost of testing. 39,40 More conclusive research is required to fill the practice gaps in key areas ranging from the identification of novel and cost-effective techniques to the development of systemic evaluation methods that are economically efficient for mass CKD screening.…”

Section: Discussionmentioning

confidence: 99%

Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning

et al. 2019

View full text Add to dashboard Cite

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 m 2 . 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.

show abstract

Section: Discussionmentioning

confidence: 99%

Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Monitoring activities should integrate national data at regional and local levels with data obtained in research and screening activities to optimize efficiency, facilitate surveillance, and permit the rapid identification of geographic hotspots for CKD that require focused attention. 19 A task force supported by global experts should be setup to investigate hotspots rapidly. Investigations should include standardized data on social, structural, and clinical risk factors, clinical course, and potential interventions.…”

Section: Prioritization Of Ckd and Detection And Investigation Of Ckdmentioning

confidence: 99%

Reducing major risk factors for chronic kidney disease

Luyckx

Tuttle

Garcia-Garcia

et al. 2017

Kidney International Supplements

198

152

View full text Add to dashboard Cite

“…Large universal CKD screening programs have taken place in the Netherlands, the United States, Japan, and China. 52,53 This strategy is of particular importance in LMICs, where approximately half of people affected with these conditions are undiagnosed. 54 Current recommendations suggest limiting screening for CKD to those with known risk factors such as hypertension, diabetes, older age, family history of kidney disease, and certain ethnicities.…”

Section: Innovations In Health Care Delivery: Manpower Restructuring mentioning

confidence: 99%

Understanding kidney care needs and implementation strategies in low- and middle-income countries: conclusions from a “Kidney Disease: Improving Global Outcomes” (KDIGO) Controversies Conference

Jha

Arıcı

Collins

et al. 2016

Kidney International

View full text Add to dashboard Cite

Evidence-based cinical practice guidelines improve delivery of uniform care to patients with and at risk of developing kidney disease, thereby reducing disease burden and improving outcomes. These guidelines are not well-integrated into care delivery systems in most low- and middle-income countries (LMICs). The KDIGO Controversies Conference on Implementation Strategies in LMIC reviewed the current state of knowledge in order to define a road map to improve the implementation of guideline-based kidney care in LMICs. An international group of multidisciplinary experts in nephrology, epidemiology, health economics, implementation science, health systems, policy, and research identified key issues related to guideline implementation. The issues examined included the current kidney disease burden in the context of health systems in LMIC, arguments for developing policies to implement guideline-based care, innovations to improve kidney care, and the process of guideline adaptation to suit local needs. This executive summary serves as a resource to guide future work, including a pathway for adapting existing guidelines in different geographical regions.

show abstract

Screening Strategies for Unrecognized CKD

Cited by 17 publications

References 21 publications

Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning

Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning

Reducing major risk factors for chronic kidney disease

Understanding kidney care needs and implementation strategies in low- and middle-income countries: conclusions from a “Kidney Disease: Improving Global Outcomes” (KDIGO) Controversies Conference

Contact Info

Product

Resources

About