人工智能视网膜微血管分析在糖尿病并发症中的应用价值

doi:10.3969/j.issn.1006-5725.2024.08.021

Abstract

Abstract:

Objective To explore the application value of artificial intelligence（AI） based retinal microvascular analysis in the diagnosis of diabetes retinopathy （DR）， diabetes nephropathy （DN） and other diabetes complications. Methods From January to December 2022， 305 subjects from the Health Medicine Department and Endocrine Department of the Eastern Theater Command General Hospital of PLA were divided into healthy control group （n = 119）， diabetes without DR group （n = 100）， and diabetes with DR group （n = 86） according to the condition of diabetes and its complications. The group of diabetes with DR was further divided into the group without DN （n = 50） and the group with DN （n = 36）. Clinical data， laboratory test indicators， and fundus photography results of all the subjects were collected. Independent sample t-test， Kruskal Wallis H-test， and logistic regression analysis were used for data analysis. Results There were statistically significant differences in FBG， 2hPBG， HbA1c， central retinal artery equivalent （CRAE）， and retinal arteriovenous ratio （AVR） among the three groups （all P < 0.05）. In patients with diabetes complicated with DR， there were statistically significant differences in the history of diabetes， total number of bleeding， total area of exudation， maximum area of exudation and total number of exudation between non-DN group and DN group （all P < 0.05）. There was correlation between retinal microvascular indicators and diabetic retinopathy. When the total area of retinal hemorrhage， total area of exudation， and maximum area of exudation increased， the risk of diabetic retinopathy increased. Conclusion AI-based retinal microvascular analysis has value in providing prompt indication and assisting with the diagnosis of complications in diabetic patients.

Key words: physical examination, artificial intelligence, fundus photography, diabetes retinopathy, diabetic nephropathy

CLC Number:

R774.1

Rui ZHANG,Ying ZHOU,Wenji NI,Ya HUANG,Dandan LI,Tao JIN,Yong. ZHONG. Application value of artificial intelligence⁃basedretinal microvascular analysis in diagnosis of diabetes complications[J]. The Journal of Practical Medicine, 2024, 40(8): 1142-1147.

Figures/Tables 6

Fig.1

Fig.2

Tab.1

Tab.2

Tab.3

Tab.4

References 25

1	KHARROUBI A T， DARWISH H M. Diabetes mellitus： The epidemic of the century［J］. World J Diabetes， 2015， 6（6）：850-867. doi:10.4239/wjd.v6.i6.850 doi: 10.4239/wjd.v6.i6.850
2	MAGLIANO D J， BOYKO E J. IDF Diabetes Atlas 10th edition scientific committee. IDF Diabetes Atlas ［C］. 10th ed. Brussels： International Diabetes Federation， 2021.
3	HAUKKA J， SANDHOLM N， VALO E， et al. Novel linkage peaks discovered for diabetic nephropathy in individuals with type 1 diabetes［J］. Diabetes， 2021， 70（4）：986-995. doi:10.2337/db20-0158 doi: 10.2337/db20-0158
4	LV K， CUI C， FAN R， et al. Detection of diabetic patients in people with normal fasting glucose using machine learning［J］. BMC Med， 2023， 21（1）：342-354. doi:10.1186/s12916-023-03045-9 doi: 10.1186/s12916-023-03045-9
5	国家老年医学中心，中华医学会老年医学分会，中国老年保健协会糖尿病专业委员会，等. 中国老年糖尿病诊疗指南（2021年版）［J］. 中华糖尿病杂志，2021，13（1）：14-46. doi:10.3760/cma.j.cn115791-20201209-00707 doi: 10.3760/cma.j.cn115791-20201209-00707
6	中华医学会眼科学分会眼底病学组，中国医师协会眼科医师分会眼底病学组，许迅，等.我国糖尿病视网膜病变临床诊疗指南（2022年）-基于循证医学修订［J］. 中华眼底病杂志， 2023， 39（2）：99-124.
7	ALICIC R Z， COX E J， NEUMILLER J J， et al. Incretin drugs in diabetic kidney disease： biological mechanisms and clinical evidence［J］. Nat Rev Nephrol， 2021， 17（4）：227-244. doi:10.1038/s41581-020-00367-2 doi: 10.1038/s41581-020-00367-2
8	MA Y C， ZUO L， CHEN J H， et al. Modified glomerular filtration rate estimating equation for Chinese patients with chronic kidney disease［J］. J Am Soc Nephrol， 2006， 17（10）：2937-2944. doi:10.1681/asn.2006040368 doi: 10.1681/asn.2006040368
9	HUBBARD L D， BROTHERS R J， KING W N， et al. Methods for evaluation of retinal microvascular abnormalities associated with hypertension/sclerosis in the Atherosclerosis Risk in Communities Study［J］. Ophthalmology， 1999， 106（12）：2269-2280. doi:10.1016/s0161-6420(99)90525-0 doi: 10.1016/s0161-6420(99)90525-0
10	GBD 2019 Blindness and Vision Impairment Collaborators， Vision Loss Expert Group of the Global Burden of Disease Study. Causes of blindness and vision impairment in 2020 and trends over 30 years， and prevalence of avoidable blindness in relation to VISION 2020：the Right to Sight： an analysis for the Global Burden of Disease Study［J］. Lancet Glob Health， 2021， 9（2）：e144-e160.
11	RUIZ O M， RODRIGUES D R， LAVOZ C， et al. Special issue diabetic nephropathy：diagnosis， prevention and treatment［J］.Clin Med， 2020， 9（3）：813. doi:10.3390/jcm9030813 doi: 10.3390/jcm9030813
12	WANG Y， ZHAO H， WANG Q， et al. Chinese herbal medicine in ameliorating diabetic kidney disease via activating autophagy［J］. Diabetes Res， 2019，2019：9030893. doi:10.1155/2019/9030893 doi: 10.1155/2019/9030893
13	MORENO J A， GOMEZ-GUERRERO C， MAS S， et al. Targeting inflammation in diabetic nephropathy： a tale of hope［J］. Expert Opin Investig Drug， 2018， 27（11）： 917-930. doi:10.1080/13543784.2018.1538352 doi: 10.1080/13543784.2018.1538352
14	张喆，刘晓怡，叶佩仪，等. 2型糖尿病合并非糖尿病肾脏疾病患者临床及病理特征［J］. 实用医学杂志， 2023， 39（10）：1253-1257. doi:10.3969/j.issn.1006-5725.2023.10.011 doi: 10.3969/j.issn.1006-5725.2023.10.011
15	CHEN Y， LIU Q， SHAN Z， et al. Catalpol ameliorates podocyte injury by stabilizing cytoskeleton and enhancing autophagy in diabetic nephropathy［J］. Front Pharmacol， 2019， 10：1477. doi:10.3389/fphar.2019.01477 doi: 10.3389/fphar.2019.01477
16	MATOBA K， TAKEDA Y， NAGAI Y， et al. Unraveling the role of inflammation in the pathogenesis of diabetic kidney disease［J］.Int J Mol Sci， 2019， 20：3393. doi:10.3390/ijms20143393 doi: 10.3390/ijms20143393
17	RAO V， RAO L B V， TAN S H， et al. Diabetic nephropathy： an update on pathogenesis and drug development［J］. Diabetes Metab Syndr，2019， 13（1）： 754-762. doi:10.1016/j.dsx.2018.11.054 doi: 10.1016/j.dsx.2018.11.054
18	WARREN A M， KNUDSEN S T， COOPER M E. Diabetic nephropathy： an insight into molecular mechanisms and emerging therapies［J］. Expert Opin Ther Targets， 2019， 23（7）： 579-591. doi:10.1080/14728222.2019.1624721 doi: 10.1080/14728222.2019.1624721
19	李继红，牛梦琦. 血管内皮生长因子水平对2型糖尿病患者并发视网膜微血管病变的预测价值［J］. 实用医学杂志， 2022， 38（8）：1001-1005. doi:10.3969/j.issn.1006-5725.2022.08.017 doi: 10.3969/j.issn.1006-5725.2022.08.017
20	HE J， CAO T， XU F， et al. Artificial intelligence-based screening for diabetic retinopathy at community hospital［J］. Eye， 2020， 34（3）：572-576. doi:10.1038/s41433-019-0562-4 doi: 10.1038/s41433-019-0562-4
21	KLEIN R， MYERS C E， LEE K E， et al. Changes in retinal vessel diameter and incidence and progression of diabetic retinopathy［J］. Arch Ophthalmol， 2012， 130（6）： 749-755. doi:10.1001/archophthalmol.2011.2560 doi: 10.1001/archophthalmol.2011.2560
22	NGUYEN T T， WANG J J， SHARRETT A R， et al.Relationship of retinal vascular caliber with diabetes and retinopathy：the Multi-Ethnic Study of Atherosclerosis MESA）［J］. Diabetes Care，2008， 31（3）：544-549. doi:10.2337/dc07-1528 doi: 10.2337/dc07-1528
23	LIEW G， MITCHELL P， WONG T Y， et al. Retinal microvascular signs are associated with chronic kidney disease in persons with and without diabetes［J］. Kidney Blood Press Res， 2012， 35（6）：589-594. doi:10.1159/000339173 doi: 10.1159/000339173
24	TZIOMALOS K， ATHYROS V G. Diabetic nephropathy：new risk factors and improvements in diagnosis［J］. Rev Diabet Stud， 2015， 12（1/2）：110-118. doi:10.1900/rds.2015.12.110 doi: 10.1900/rds.2015.12.110
25	IZZEDINE H， BODAGHI B， LAUNAY-VACHER V， et al. Eye and kidney：from clinical findings to genetic explanations［J］. J Am Soc Nephrol， 2003， 14（2）：516-529. doi:10.1097/01.asn.0000051705.97966.ad doi: 10.1097/01.asn.0000051705.97966.ad

项目	健康对照组（n = 119）	糖尿病无DR组（n = 100）	糖尿病并发DR组（n = 86）	F/χ²值	P值
男性［例（%）］	57（48.00）	88（88.00）^ab	36（42.00）^ab	32.70	< 0.001
年龄（岁）	46.03 ± 5.31	51.02 ± 12.53^a	53.42 ± 10.73^a	15.641	< 0.001
身高（cm）	168.27 ± 0.67	176.67 ± 6.60	168.08 ± 0.86	1.731	< 0.001
体质量（kg）	64.51 ± 0.86	75.41 ± 1.27^a	70.55 ± 1.21^a	29.482	< 0.001
BMI（kg/m²）	22.73 ± 0.20	25.71 ± 0.46^a	24.90 ± 0.32^a	25.451	< 0.001
收缩压（mmol/L）	109.37 ± 0.76	129.57 ± 1.96^a	126.72 ± 1.867^a	71.168	< 0.001
舒张压（mmol/L）	67.92 ± 0.79	78.83 ± 1.22^a	78.58 ± 1.13^a	45.445	< 0.001
TC（mmol/L）	4.47 ± 0.05	4.97 ± 0.11^a	5.16 ± 0.16^a	17.431	< 0.001
TG（mmol/L）	0.85 ± 0.03	2.19 ± 0.17^a	2.34 ± 0.20^a	43.666	< 0.001
LDL-C（mmol/L）	2.22 ± 0.04	2.48 ± 0.09^a	2.81 ± 0.11^ab	17.573	< 0.001
HDL-C（mmol/L）	1.41 ± 0.03	1.24 ± 0.03^a	1.18 ± 0.05^a	17.160	< 0.001
BUA（μmol/L）	285.18 ± 4.86	387.08 ± 10.32^a	351.51 ± 11.08^ab	43.031	< 0.001
SCR（μmol/L）	67.96 ± 1.17	72.00 ± 1.60	72.53 ± 3.37	1.743	0.177
eGFR［mL/min·1.73 m²］	102.37 ± 1.26	101.70 ± 1.27	100.04 ± 2.17	0.574	0.564

组别	健康对照组（n = 119）	糖尿病无DR组（n = 100）	糖尿病并发DR组（n = 86）	H值	P值
FBG	4.80（4.60，5.10）	6.30（5.95，7.10）^ab	8.20（6.40，9.75）^ab	194.394	< 0.001
2hPBG	5.10（4.55，5.800）	6.80（6.40，7.55）^ab	13.40（10.60，17.40）^ab	200.346	< 0.001
HbA_1c	5.30（5.10，5.600）	10.70（8.20，12.60）^ab	8.40（7.05，9.80）^ab	188.033	< 0.001
CRAE	0.022（0.020，0.026）	0.021（0.020，0.025）^a	0.020（0.016，0.025）^ab	7.986	0.018
CRVE	0.030（0.027，0.035）	0.030（0.027，0.037）	0.030（0.025，0.034）	0.491	0.782
AVR	0.730（0.670，0.780）	0.700（0.670，0.740）^a	0.680（0.635，0.765）^a	11.110	0.004

组别	无DN组（n = 50）	并发DN组（n = 36）	t值	P值
年龄（岁）	53.30 ± 10.43	55.27 ± 12.31	-0.734	0.465
糖尿病病史（年）	9.61 ± 7.14	14.29 ± 8.44	-2.455	0.017
CRAE	0.021 ± 0.006	0.020 ± 0.006	1.117	0.268
CRVE	0.034 ± 0.027	0.029 ± 0.009	0.899	0.371
AVR	0.698 ± 0.131	0.687 ± 0.107	0.383	0.703
出血总面积（mm²）	0.170 ± 0.378	0.299 ± 0.372	-1.389	0.169
出血最大面积（mm²）	0.056 ± 0.102	0.092 ± 0.101	-1.418	0.161
出血总个数（个）	7.21 ± 11.54	17.76 ± 19.67	-2.465	0.019
渗出总面积（mm²）	0.100 ± 0.179	0.581 ± 0.992	-2.454	0.021
渗出最大面积（mm²）	0.049 ± 0.065	0.163 ± 0.276	-2.081	0.047
渗出总个数（个）	6.13 ± 14.67	19.96 ± 30.80	-2.159	0.039

自变量	OR	95%CI	P值
LogCRAE	0.031	0.000 ~ 3.276	0.144
LogCRVE	0.253	0.002 ~ 5.279	0.098
AVR	0.699	0.010 ~ 2.517	0.466
出血总面积	2.404	0.656 ~ 2.404	0.185
出血最大面积	2.019	0.235 ~ 2.198	0.173
出血总个数	1.046	1.009 ~ 1.048	0.013
渗出总面积	1.453	1.434 ~ 1.498	0.021
渗出最大面积	1.645	1.032 ~ 1.734	0.011
渗出总个数	1.033	1.001 ~ 1.067	0.045

[1]	Liangjiang HUANG,Dewen MAO,Jinghui ZHENG,Minggang WANG,Chun YAO. Application of artificial intelligence in HE risk prediction modelling and research advances [J]. The Journal of Practical Medicine, 2024, 40(3): 289-294.
[2]	Jingfang WAN,Kehong. CHEN. Advances in research on optimal dialysate bicarbonate concentration for maintenance hemodialysis patients [J]. The Journal of Practical Medicine, 2024, 40(18): 2520-2524.
[3]	Qingdong YAO,Chengbing ZHANG,Jun FU,Peng WANG,Bin LONG,Haifeng. LIU. The correlation analysis of coronary artery plaque AI quantitative parameter with FFR-CT in coronary CT angiography [J]. The Journal of Practical Medicine, 2024, 40(17): 2489-2494.
[4]	Qicheng JIN,Jianghong LV,Lilong XU,Hongfen WEI,Tongfang TANG,Chuanju ZHANG,Shiyan. LI. Impacts of different ultrasound imaging parameters on the differential diagnosis of benign and malignant breast nodules with S⁃Detect technology [J]. The Journal of Practical Medicine, 2023, 39(22): 2891-2897.
[5]	Yongming TIAN,Shifeng WU,Xi. ZHAO. Cluster analysis of TCM syndrome types in patients with type 2 diabetic nephropathy and its relationship with disease staging [J]. The Journal of Practical Medicine, 2023, 39(22): 2994-3000.
[6]	ZHANG Zhe, LIU Xiaoyi, YE Peiyi, XIE Chao, KONG Yaozhong. . Clinical and pathological characteristics of patients with type 2 diabetes mellitus complicated with non⁃dia⁃ betic renal disease [J]. The Journal of Practical Medicine, 2023, 39(10): 1253-1257.
[7]	WANG Lexin , LIU Chao, MA Tianlong, YANG Anning, XIONG Jiantuan, WU Kai, JIAO Yun, BAI Zhigang, JIANG Yideng, MA Shengchao, ZHANG Xu, LU Guanjun. Role of LncRNA H19 in pyrophosis of glomerular podocyte induced by high glucose [J]. The Journal of Practical Medicine, 2023, 39(1): 12-20.
[8]	LI Cong, KONG Lingcong, HU Lianting, YUAN Haiyun, REN Yun, ZHAO Hanpeng, WANG Yan, CHEN Xuanhui, LIU Huazhang, KUANG Yu, LIANG Huiying, YU Honghua, YANG Xiaohong. . A clinical study on intelligent prediction of perioperative outcomes in congenital heart disease based on optical coherence tomography angiography technology [J]. The Journal of Practical Medicine, 2022, 38(9): 1136-1140.
[9]	LIAO Shuting, YU Xiangrong. . Application of spectral CT and artificial intelligence in the diagnosis of thyroid cancer [J]. The Journal of Practical Medicine, 2022, 38(2): 129-1133.
[10]	WANG Shuang, FENG Yanhong.. Evaluation of right ventricular systolic function by fully automated three ⁃ dimensional echocardiography right ventricular quantification software in patients with chronic pulmonary heart disease [J]. The Journal of Practical Medicine, 2022, 38(19): 2476-2480.
[11]	YANG Linlin, LIU Gang, YI Rui, WANG Juan, XIE Zhenhua, LIU Chengqiong, CHEN Jie. Research progress on risk prediction of acute renal injury [J]. The Journal of Practical Medicine, 2022, 38(18): 2367-2372.
[12]	AN Wei, LIANG Haoyue, KONG Xiaodong.. Progress on Raman spectroscopy for differential diagnosis of renal diseases [J]. The Journal of Practical Medicine, 2022, 38(16): 2094-2099.
[13]	LI Yingna, DONG Lan, LIU Wanshan, QUAN Linfei, HE Feng.. Pathogenesis of early diabetic nephropathy：A bioinformatics analysis [J]. The Journal of Practical Medicine, 2022, 38(14): 1736-1742.
[14]	LUO Gang, PAN Si⁃lin, QIAO Sibo, PANG Shanchen, CHEN Taotao, SUN Lingyu, DONG Yukun.. Deep learning technology for automatic recognition of fetal echocardiography images [J]. The Journal of Practical Medicine, 2022, 38(14): 1830-1833.
[15]	YANG Lei, TANG Can.. CAD machine diagnosis system in ultrasonic diagnosis of breast cancer [J]. The Journal of Practical Medicine, 2022, 38(1): 106-110.

Application value of artificial intelligence⁃basedretinal microvascular analysis in diagnosis of diabetes complications

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 6

References 25

Related Articles 15

Recommended Articles

Metrics

Comments