A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations

The Lancet Digital Health - Tập 2 - Trang e295-e302 - 2020
Charumathi Sabanayagam1,2, Dejiang Xu3, Daniel S W Ting1,2, Simon Nusinovici1, Riswana Banu1, Haslina Hamzah1, Cynthia Lim4, Yih-Chung Tham1, Carol Y Cheung5, E Shyong Tai6, Ya Xing Wang7, Jost B Jonas7,8, Ching-Yu Cheng1,2, Mong Li Lee3, Wynne Hsu3, Tien Y Wong1,2
1Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
2Ophthalmology and Visual Sciences Academic Clinical Program, Duke-NUS Medical School, Singapore
3School of Computing, National University of Singapore, Singapore
4Singapore General Hospital, Singapore
5Department of Ophthalmology and Visual Sciences, Chinese University of Hong Kong, Hong Kong
6Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore
7Beijing Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing Ophthalmology & Visual Sciences Key Laboratory, Beijing, China
8Department of Ophthalmology, Medical Faculty Mannheim of the Ruprecht-Karls-University Heidelberg, Mannheim, Germany

Tài liệu tham khảo

Fox, 2012, Associations of kidney disease measures with mortality and end-stage renal disease in individuals with and without diabetes: a meta-analysis, Lancet, 380, 1662, 10.1016/S0140-6736(12)61350-6 Ene-Iordache, 2016, Chronic kidney disease and cardiovascular risk in six regions of the world (ISN-KDDC): a cross-sectional study, Lancet Glob Health, 4, e307, 10.1016/S2214-109X(16)00071-1 Berns, 2014, Routine screening for CKD should be done in asymptomatic adults...selectively, Clin J Am Soc Nephrol, 9, 1988, 10.2215/CJN.02250314 Qaseem, 2013, Screening, monitoring, and treatment of stage 1 to 3 chronic kidney disease: a clinical practice guideline from the American College of Physicians, Ann Intern Med, 159, 835, 10.7326/0003-4819-159-11-201312030-00009 Manski-Nankervis, 2018, Screening and diagnosis of chronic kidney disease in people with type 2 diabetes attending Australian general practice, Aust J Prim Health, 24, 280, 10.1071/PY17156 Reutens, 2013, Epidemiology of diabetic kidney disease, Med Clin North Am, 97, 1, 10.1016/j.mcna.2012.10.001 Wong, 2014, Kidney and eye diseases: common risk factors, etiological mechanisms, and pathways, Kidney Int, 85, 1290, 10.1038/ki.2013.491 Lim, 2013, Structural changes in the retinal microvasculature and renal function, Invest Ophthalmol Vis Sci, 54, 2970, 10.1167/iovs.13-11941 Sabanayagam, 2008, Retinal microvascular caliber and chronic kidney disease in an Asian population, Am J Epidemiol, 169, 625, 10.1093/aje/kwn367 Gulshan, 2016, Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, JAMA, 316, 2402, 10.1001/jama.2016.17216 Ting, 2017, Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes, JAMA, 318, 2211, 10.1001/jama.2017.18152 Esteva, 2017, Dermatologist-level classification of skin cancer with deep neural networks, Nature, 542, 115, 10.1038/nature21056 Kuo, 2019, Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning, NPJ Digit Med, 2, 29, 10.1038/s41746-019-0104-2 Foong, 2007, Rationale and methodology for a population-based study of eye diseases in Malay people: the Singapore Malay eye study (SiMES), Ophthalmic Epidemiol, 14, 25, 10.1080/09286580600878844 Lavanya, 2009, Methodology of the Singapore Indian Chinese Cohort (SICC) eye study: quantifying ethnic variations in the epidemiology of eye diseases in Asians, Ophthalmic Epidemiol, 16, 325, 10.3109/09286580903144738 Sabanayagam, 2017, Singapore Indian Eye Study-2: methodology and impact of migration on systemic and eye outcomes, Clin Exp Ophthalmol, 45, 779, 10.1111/ceo.12974 Sabanayagam, 2009, Retinal arteriolar narrowing increases the likelihood of chronic kidney disease in hypertension, J Hypertens, 27, 2209, 10.1097/HJH.0b013e328330141d Xu, 2014, Ten-year cumulative incidence of diabetic retinopathy. The Beijing Eye Study 2001/2011, PLoS One, 9 Levey, 2009, A new equation to estimate glomerular filtration rate, Ann Intern Med, 150, 604, 10.7326/0003-4819-150-9-200905050-00006 Xu D, Lee ML, Wynne Hsu. Propagation mechanism for deep and wide neural networks. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); Long Beach, CA, USA; June 16–20, 2019; 9212–20. Saunders, 2015, Screening for chronic kidney disease, JAMA, 314, 615, 10.1001/jama.2015.9425 Mitka, 2013, Nephrologists question ACP's kidney disease guidelines, JAMA, 310, 2387, 10.1001/jama.2013.282671 2002, K/DOQI clinical practice guidelines for chronic kidney disease: evaluation, classification, and stratification, Am J Kidney Dis, 39, S1 Hallan, 2006, Screening strategies for chronic kidney disease in the general population: follow-up of cross sectional health survey, BMJ, 333, 10.1136/bmj.39001.657755.BE Komenda, 2014, Cost-effectiveness of primary screening for CKD: a systematic review, Am J Kidney Dis, 63, 789, 10.1053/j.ajkd.2013.12.012 Bang, 2007, SCreening for Occult REnal Disease (SCORED): a simple prediction model for chronic kidney disease, Arch Intern Med, 167, 374, 10.1001/archinte.167.4.374 Bradshaw, 2019, Early detection of chronic kidney disease in low-income and middle-income countries: development and validation of a point-of-care screening strategy for India, BMJ Glob Health, 4, 10.1136/bmjgh-2019-001644 Delgado, 2019, Why Cohen's Kappa should be avoided as performance measure in classification, PLoS One, 14, 10.1371/journal.pone.0222916 Ozenne, 2015, The precision–recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases, J Clin Epidemiol, 68, 855, 10.1016/j.jclinepi.2015.02.010 Deacon, 2006, Fear of needles and vasovagal reactions among phlebotomy patients, J Anxiety Disord, 20, 946, 10.1016/j.janxdis.2006.01.004