Artificial intelligence-based classification of cardiac autonomic neuropathy from retinal fundus images in patients with diabetes: The Silesia Diabetes Heart Study.

IF 8.5 1区医学 Q1 CARDIAC & CARDIOVASCULAR SYSTEMS Cardiovascular Diabetology Pub Date : 2024-08-10 DOI:10.1186/s12933-024-02367-z

Katarzyna Nabrdalik, Krzysztof Irlik, Yanda Meng, Hanna Kwiendacz, Julia Piaśnik, Mirela Hendel, Paweł Ignacy, Justyna Kulpa, Kamil Kegler, Mikołaj Herba, Sylwia Boczek, Effendy Bin Hashim, Zhuangzhi Gao, Janusz Gumprecht, Yalin Zheng, Gregory Y H Lip, Uazman Alam

{"title":"Artificial intelligence-based classification of cardiac autonomic neuropathy from retinal fundus images in patients with diabetes: The Silesia Diabetes Heart Study.","authors":"Katarzyna Nabrdalik, Krzysztof Irlik, Yanda Meng, Hanna Kwiendacz, Julia Piaśnik, Mirela Hendel, Paweł Ignacy, Justyna Kulpa, Kamil Kegler, Mikołaj Herba, Sylwia Boczek, Effendy Bin Hashim, Zhuangzhi Gao, Janusz Gumprecht, Yalin Zheng, Gregory Y H Lip, Uazman Alam","doi":"10.1186/s12933-024-02367-z","DOIUrl":null,"url":null,"abstract":"Background: Cardiac autonomic neuropathy (CAN) in diabetes mellitus (DM) is independently associated with cardiovascular (CV) events and CV death. Diagnosis of this complication of DM is time-consuming and not routinely performed in the clinical practice, in contrast to fundus retinal imaging which is accessible and routinely performed. Whether artificial intelligence (AI) utilizing retinal images collected through diabetic eye screening can provide an efficient diagnostic method for CAN is unknown.Methods: This was a single center, observational study in a cohort of patients with DM as a part of the Cardiovascular Disease in Patients with Diabetes: The Silesia Diabetes-Heart Project (NCT05626413). To diagnose CAN, we used standard CV autonomic reflex tests. In this analysis we implemented AI-based deep learning techniques with non-mydriatic 5-field color fundus imaging to identify patients with CAN. Two experiments have been developed utilizing Multiple Instance Learning and primarily ResNet 18 as the backbone network. Models underwent training and validation prior to testing on an unseen image set.Results: In an analysis of 2275 retinal images from 229 patients, the ResNet 18 backbone model demonstrated robust diagnostic capabilities in the binary classification of CAN, correctly identifying 93% of CAN cases and 89% of non-CAN cases within the test set. The model achieved an area under the receiver operating characteristic curve (AUCROC) of 0.87 (95% CI 0.74-0.97). For distinguishing between definite or severe stages of CAN (dsCAN), the ResNet 18 model accurately classified 78% of dsCAN cases and 93% of cases without dsCAN, with an AUCROC of 0.94 (95% CI 0.86-1.00). An alternate backbone model, ResWide 50, showed enhanced sensitivity at 89% for dsCAN, but with a marginally lower AUCROC of 0.91 (95% CI 0.73-1.00).Conclusions: AI-based algorithms utilising retinal images can differentiate with high accuracy patients with CAN. AI analysis of fundus images to detect CAN may be implemented in routine clinical practice to identify patients at the highest CV risk.Trial registration: This is a part of the Silesia Diabetes-Heart Project (Clinical-Trials.gov Identifier: NCT05626413).","PeriodicalId":9374,"journal":{"name":"Cardiovascular Diabetology","volume":null,"pages":null},"PeriodicalIF":8.5000,"publicationDate":"2024-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11316981/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cardiovascular Diabetology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12933-024-02367-z","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Cardiac autonomic neuropathy (CAN) in diabetes mellitus (DM) is independently associated with cardiovascular (CV) events and CV death. Diagnosis of this complication of DM is time-consuming and not routinely performed in the clinical practice, in contrast to fundus retinal imaging which is accessible and routinely performed. Whether artificial intelligence (AI) utilizing retinal images collected through diabetic eye screening can provide an efficient diagnostic method for CAN is unknown.

Methods: This was a single center, observational study in a cohort of patients with DM as a part of the Cardiovascular Disease in Patients with Diabetes: The Silesia Diabetes-Heart Project (NCT05626413). To diagnose CAN, we used standard CV autonomic reflex tests. In this analysis we implemented AI-based deep learning techniques with non-mydriatic 5-field color fundus imaging to identify patients with CAN. Two experiments have been developed utilizing Multiple Instance Learning and primarily ResNet 18 as the backbone network. Models underwent training and validation prior to testing on an unseen image set.

Results: In an analysis of 2275 retinal images from 229 patients, the ResNet 18 backbone model demonstrated robust diagnostic capabilities in the binary classification of CAN, correctly identifying 93% of CAN cases and 89% of non-CAN cases within the test set. The model achieved an area under the receiver operating characteristic curve (AUCROC) of 0.87 (95% CI 0.74-0.97). For distinguishing between definite or severe stages of CAN (dsCAN), the ResNet 18 model accurately classified 78% of dsCAN cases and 93% of cases without dsCAN, with an AUCROC of 0.94 (95% CI 0.86-1.00). An alternate backbone model, ResWide 50, showed enhanced sensitivity at 89% for dsCAN, but with a marginally lower AUCROC of 0.91 (95% CI 0.73-1.00).

Conclusions: AI-based algorithms utilising retinal images can differentiate with high accuracy patients with CAN. AI analysis of fundus images to detect CAN may be implemented in routine clinical practice to identify patients at the highest CV risk.

Trial registration: This is a part of the Silesia Diabetes-Heart Project (Clinical-Trials.gov Identifier: NCT05626413).

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于人工智能的糖尿病患者视网膜眼底图像的心脏自主神经病变分类：西里西亚糖尿病心脏研究

背景：糖尿病（DM）患者的心脏自主神经病变（CAN）与心血管（CV）事件和心血管死亡密切相关。诊断糖尿病的这种并发症非常耗时，而且在临床实践中也不是常规做法，相比之下，眼底视网膜成像技术既方便又是常规做法。人工智能（AI）利用糖尿病眼底筛查收集的视网膜图像是否能为CAN提供有效的诊断方法，目前还不得而知：这是一项单中心观察性研究，研究对象是糖尿病患者心血管疾病队列中的糖尿病患者：西里西亚糖尿病-心脏项目（NCT05626413）的一部分。为了诊断 CAN，我们使用了标准的 CV 自律神经反射测试。在这项分析中，我们利用基于人工智能的深度学习技术和非眼底5视野彩色眼底成像来识别CAN患者。我们开发了两个实验，利用多重实例学习（Multiple Instance Learning），主要以 ResNet 18 作为骨干网络。在对未见图像集进行测试之前，对模型进行了训练和验证：在对 229 名患者的 2275 张视网膜图像进行分析时，ResNet 18 骨干网络模型在 CAN 的二元分类中表现出了强大的诊断能力，正确识别了测试集中 93% 的 CAN 病例和 89% 的非 CAN 病例。该模型的接收者操作特征曲线下面积 (AUCROC) 为 0.87（95% CI 0.74-0.97）。在区分CAN的明确或严重阶段（dsCAN）时，ResNet 18模型准确分类了78%的dsCAN病例和93%的无dsCAN病例，AUCROC为0.94（95% CI 0.86-1.00）。另一种骨干模型 ResWide 50 对 dsCAN 的灵敏度有所提高，达到 89%，但 AUCROC 略低，为 0.91 (95% CI 0.73-1.00)：结论：利用视网膜图像的人工智能算法可以高精度地区分 CAN 患者。对眼底图像进行人工智能分析以检测CAN，可在常规临床实践中应用，以识别CV风险最高的患者：这是西里西亚糖尿病-心脏项目（Clinical-Trials.gov Identifier: NCT05626413）的一部分。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Cardiovascular Diabetology 医学-内分泌学与代谢

CiteScore

12.30

自引率

15.10%

发文量

240

审稿时长

1 months

期刊介绍： Cardiovascular Diabetology is a journal that welcomes manuscripts exploring various aspects of the relationship between diabetes, cardiovascular health, and the metabolic syndrome. We invite submissions related to clinical studies, genetic investigations, experimental research, pharmacological studies, epidemiological analyses, and molecular biology research in this field.