AbstractCorneAI for iOS is an artificial intelligence (AI) application to classify the condition of the cornea and cataract into nine categories: normal, infectious keratitis, non-infection keratitis, scar, tumor, deposit, acute primary angle closure, lens opacity, and bullous keratopathy. We evaluated its performance to classify multiple conditions of the cornea and cataract of various races in images published in the Cornea journal.

摘要iOS角膜是一种人工智能（AI）应用程序，可将角膜和白内障的状况分为九类：正常，感染性角膜炎，非感染性角膜炎，瘢痕，肿瘤，沉积物，急性原发性闭角，晶状体混浊和大疱性角膜病。我们评估了它在《角膜杂志》上发表的图像中对不同种族的角膜和白内障的多种情况进行分类的性能。

The positive predictive value (PPV) of the top classification with the highest predictive score was 0.75, and the PPV for the top three classifications exceeded 0.80. For individual diseases, the highest PPVs were 0.91, 0.73, 0.42, 0.72, 0.77, and 0.55 for infectious keratitis, normal, non-infection keratitis, scar, tumor, and deposit, respectively.

预测得分最高的最高分类的阳性预测值（PPV）为0.75，前三个分类的PPV超过0.80。对于个体疾病，感染性角膜炎，正常，非感染性角膜炎，瘢痕，肿瘤和沉积物的最高PPV分别为0.91、0.73、0.42、0.72、0.77和0.55。

CorneAI for iOS achieved an area under the receiver operating characteristic curve of 0.78 (95% confidence interval [CI] 0.5–1.0) for normal, 0.76 (95% CI 0.67–0.85) for infectious keratitis, 0.81 (95% CI 0.64–0.97) for non-infection keratitis, 0.55 (95% CI 0.41–0.69) for scar, 0.62 (95% CI 0.27–0.97) for tumor, and 0.71 (95% CI 0.53–0.89) for deposit.

iOS的角膜在受试者工作特征曲线下的面积正常为0.78（95%置信区间[CI]0.5-1.0），感染性角膜炎为0.76（95%CI 0.67-0.85），非感染性角膜炎为0.81（95%CI 0.64-0.97），瘢痕为0.55（95%CI 0.41-0.69），肿瘤为0.62（95%CI 0.27-0.97），沉积物为0.71（95%CI 0.53-0.89）。

CorneAI performed well in classifying various conditions of the cornea and cataract when used to diagnose journal images, including those with variable imaging conditions, ethnicities, and rare cases..

当用于诊断期刊图像时，CorneAI在对角膜和白内障的各种情况进行分类方面表现良好，包括那些具有可变成像条件，种族和罕见病例的图像。。

IntroductionThe cornea and crystalline lenses are crucial for focusing light onto the retina and maintaining optimal vision. Pathological conditions of the ocular media, such as, corneal opacity, infectious keratitis and cataracts, are the leading causes of vision impairment, affecting 75 million people worldwide (15 million with blindness (presenting visual acuity of < 3/60 in the better eye) and 60 million with moderate-to-severe vision impairment)1,2.

引言角膜和晶状体对于将光线聚焦到视网膜上并保持最佳视力至关重要。眼部介质的病理状况，如角膜混浊，感染性角膜炎和白内障，是视力障碍的主要原因，影响了全世界7500万人（1500万盲人（视力较好的眼睛视力为3/60）和6000万中度至重度视力障碍）1,2。

Corneal diseases and cataracts are considered as avoidable vision loss with early detection and timely medical intervention1,2,3. However, real-world diagnosis and treatment depend on the availability of skilled ophthalmologists. Despite recent medical progress, the number of patients with avoidable blindness due to corneal diseases and cataracts continues to increase as the global population grows and ages, owing to the limited number of experienced ophthalmologists3,4.In recent years, the integration of artificial Intelligence (AI) into healthcare has emerged as a transformative force, revolutionizing diagnostic processes and patient care5,6.

通过早期发现和及时的医疗干预，角膜疾病和白内障被认为是可避免的视力丧失1,2,3。。尽管最近取得了医学进展，但由于经验丰富的眼科医生数量有限，随着全球人口的增长和年龄的增长，由于角膜疾病和白内障而可避免失明的患者人数继续增加3,4。近年来，人工智能（AI）融入医疗保健已成为一股变革力量，彻底改变了诊断过程和患者护理5,6。

AI applications are now used in various medical fields, including ophthalmology7,8.Advancements in AI have significantly benefited ophthalmology, enabling the use of fundus images to identify retinal diseases, such as retinal detachment9, age-related macular degeneration10, diabetic retinopathy11,12, and glaucoma13,14.

AI应用现已应用于各个医学领域，包括眼科7,8。AI的进步使眼科学显着受益，使眼底图像能够识别视网膜疾病，如视网膜脱离9，年龄相关性黄斑变性10，糖尿病视网膜病变11,12和青光眼13,14。

For anterior segment diseases, studies have reported the classification of bacterial and fungal keratitis using anterior segment slit-lamp images15,16. Diagnosing corneal diseases requires a skilled ophthalmologist to examine the patient’s cornea using a slit-lamp microscope or slit-lamp imaging. Although these AI techniques have achieved promising results, their a.

对于前段疾病，研究报道了使用前段裂隙灯图像对细菌和真菌性角膜炎进行分类15,16。诊断角膜疾病需要熟练的眼科医生使用裂隙灯显微镜或裂隙灯成像检查患者的角膜。虽然这些人工智能技术取得了有希望的结果，但他们的a。

Data availability

数据可用性

The data that support the findings of this study are available on request from the corresponding author (T.Y.). The data are not publicly available due to them containing information that could compromise research participant privacy/consent.

支持本研究结果的数据可应通讯作者（T.Y.）的要求提供。这些数据不公开，因为它们包含可能损害研究参与者隐私/同意的信息。

ReferencesFlaxman, S. R. et al. Global causes of blindness and distance vision impairment 1990–2020: A systematic review and meta-analysis. Lancet Glob. Heal. 5, e1221–e1234 (2017).Article

参考文献Flaxman，S.R.等人，《1990-2020年失明和远视障碍的全球原因：系统综述和荟萃分析》。柳叶刀球。治愈。。文章

Google Scholar

谷歌学者

Pascolini, D. & Mariotti, S. P. Global estimates of visual impairment: 2010. Br. J. Ophthalmol. 96, 614–618 (2012).Article

Pascolini，D.＆Mariotti，S.P。全球视力障碍估计：2010年。Br.J.眼科。96614-618（2012）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Bourne, R. R. A. et al. Trends in prevalence of blindness and distance and near vision impairment over 30 years: An analysis for the Global Burden of Disease Study. Lancet Glob. Heal. 9, e130–e143 (2021).Article

Bourne，R.R.A.等人，《30年来失明、远距离和近视力障碍患病率的趋势：全球疾病负担研究分析》。柳叶刀球。治愈。9，e130–e143（2021）。文章

Google Scholar

谷歌学者

Gupta, N., Tandon, R., Gupta, S., Sreenivas, V. & Vashist, P. Burden of corneal blindness in India. Indian J. Commun. Med. 38, 198–206 (2013).Article

Gupta，N.，Tandon，R.，Gupta，S.，Sreenivas，V。＆Vashist，P。印度角膜失明的负担。印度J.Commun。医学38198-206（2013）。文章

Google Scholar

谷歌学者

Litjens, G. et al. A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017).Article

Litjens，G。等。医学图像分析深度学习调查。医学图像肛门。。文章

PubMed

PubMed

Google Scholar

谷歌学者

Matheny, M. E., Whicher, D. & Thadaney Israni, S. Artificial intelligence in health care: A report from the National Academy of Medicine. JAMA J. Am. Med. Assoc. 323, 509–510 (2020).Article

Matheny，M.E.，Whicher，D。和Thadaney Israni，S。医疗保健中的人工智能：来自国家医学院的报告。《美国医学会杂志》第323509-510号（2020年）。文章

Google Scholar

谷歌学者

Rashidi, P. & Bihorac, A. Artificial intelligence approaches to improve kidney care. Nat Rev Nephrol. 16, 71–72 (2020).Article

Rashidi，P。＆Bihorac，A。改善肾脏护理的人工智能方法。Nat Rev Nephrol。16，71-72（2020）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Chilamkurthy, S. et al. Deep learning algorithms for detection of critical findings in head CT scans: A retrospective study. Lancet 392, 2388–2396 (2018).Article

Chilamkurthy，S.等人。用于检测头部CT扫描中关键发现的深度学习算法：一项回顾性研究。柳叶刀3922388-2396（2018）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Li, Z. et al. Deep learning for detecting retinal detachment and discerning macular status using ultra-widefield fundus images. Commun. Biol. 3, 1–10 (2020).PubMed

Li，Z.等人。使用超宽视野眼底图像检测视网膜脱离和辨别黄斑状态的深度学习。Commun公司。生物学3，1-10（2020）。

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Burlina, P. M. et al. Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA Ophthalmol. 135, 1170–1176 (2017).Article

Burlina，P.M.等人。使用深度卷积神经网络从彩色眼底图像自动分级年龄相关性黄斑变性。JAMA眼科。1351170-1176（2017）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Gulshan, V. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA J. Am. Med. Assoc. 316, 2402–2410 (2016).Article

Gulshan，V。等人。在视网膜眼底照片中检测糖尿病视网膜病变的深度学习算法的开发和验证。《美国医学会杂志》3162402-2410（2016）。文章

Google Scholar

谷歌学者

Gargeya, R. & Leng, T. Automated identification of diabetic retinopathy using deep learning. Ophthalmology 124, 962–969 (2017).Article

Gargeya，R。＆Leng，T。使用深度学习自动识别糖尿病视网膜病变。眼科124962-969（2017）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Li, Z. et al. Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology 125, 1199–1206 (2018).Article

Li，Z.等人。基于彩色眼底照片检测青光眼视神经病变的深度学习系统的功效。眼科1251199-1206（2018）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Li, Z. et al. Deep learning for automated glaucomatous optic neuropathy detection from ultra-widefield fundus images. Br. J. Ophthalmol. 105, 1548–1554 (2021).Article

Li，Z.等人。从超宽视野眼底图像自动检测青光眼视神经病变的深度学习。Br.J.眼科。1051548-1554（2021）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Ghosh, A. K., Thammasudjarit, R., Jongkhajornpong, P., Attia, J. & Thakkinstian, A. Deep learning for discrimination between fungal keratitis and bacterial keratitis: DeepKeratitis. Cornea 41, 616–622 (2022).Article

Ghosh，A.K.，Thammasudjarit，R.，Jongkhajornpong，P.，Attia，J。＆Thakkinstian，A。区分真菌性角膜炎和细菌性角膜炎的深度学习：深度角膜炎。角膜41616-622（2022）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Hung, N. et al. Using slit-lamp images for deep learning-based identification of bacterial and fungal keratitis: Model development and validation with different convolutional neural networks. Diagnostics 11(7), 1246 (2021).Article

Hung，N.等人。使用裂隙灯图像进行基于深度学习的细菌和真菌性角膜炎识别：不同卷积神经网络的模型开发和验证。诊断11（7），1246（2021）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Gu, H. et al. Deep learning for identifying corneal diseases from ocular surface slit-lamp photographs. Sci. Rep. 10, 1–11 (2020).Article

Gu，H.等人。从眼表裂隙灯照片识别角膜疾病的深度学习。科学。代表10，1-11（2020）。文章

Google Scholar

谷歌学者

Freeman, K. et al. Algorithm based smartphone apps to assess risk of skin cancer in adults: systematic review of diagnostic accuracy studies. BMJ 368,127 (2020).Li, Z. et al. Preventing corneal blindness caused by keratitis using artificial intelligence. Nat. Commun. https://doi.org/10.1038/s41467-021-24116-6 (2021).Article .

Freeman，K.等人。基于算法的智能手机应用程序，用于评估成人皮肤癌的风险：诊断准确性研究的系统评价。BMJ 368127（2020）。Li，Z.等人。使用人工智能预防角膜炎引起的角膜失明。国家公社。https://doi.org/10.1038/s41467-021-24116-6（2021年）。文章。

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Ueno, Y., Oda, M., Yamaguchi, T., Fukuoka, H., Nejima, R., Kitaguchi, Y., Miyake, M., Akiyama, M., Miyata, K., Kashiwagi, K., Naoyuki Maeda, J. S. & Hisashi Noma Kensaku Mori, T. O. Deep learning model for extensive smartphone-based diagnosis and triage of cataracts and multiple corneal diseases.

上野，Y.，Oda，M.，山口，T.，福冈，H.，Nejima，R.，北口，Y.，宫宅，M.，秋山，M.，宫田，K.，Kashiwagi，K.，Naoyuki Maeda，J.S。和Hisashi Noma Kensaku Mori，T.O.深度学习模型，用于广泛的基于智能手机的白内障和多种角膜疾病的诊断和分类。

Br. J. Ophthalmol. Epub ahead of print. https://doi.org/10.1136/bjo-2023-324488 (2024) .Levitt, A. E. et al. Ocular inflammation in the setting of concomitant systemic autoimmune conditions in an older male population. Cornea 34, 762–767 (2015).Article .

Br.J.眼科。Epub领先于印刷。https://doi.org/10.1136/bjo-2023-324488（2024年）。Levitt，A.E.等人。老年男性伴随全身性自身免疫性疾病的眼部炎症。角膜34762-767（2015）。文章。

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Khan, T. A. et al. Bilateral immune-mediated keratolysis after immunization with SARS-CoV-2 recombinant viral vector vaccine. Cornea 40, 1629–1632 (2021).Article

Khan，T.A.等人。用SARS-CoV-2重组病毒载体疫苗免疫后的双侧免疫介导的角膜溶解。角膜401629-1632（2021）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Ide, T. et al. A spectrum of clinical manifestations of gelatinous drop-like corneal dystrophy in Japan. Am. J. Ophthalmol. 137, 1081–1084 (2004).Article

Ide，T.等人。日本凝胶状滴状角膜营养不良的一系列临床表现。美国眼科杂志。1371081-1084（2004）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Watson, S., Cabrera-Aguas, M. & Khoo, P. Common eye infections. Aust. Prescr. 41, 67–72 (2018).Article

Watson，S.，Cabrera Aguas，M。＆Khoo，P。常见眼部感染。。Prescr。41,67-72（2018）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Sharma, A. & Taniguchi, J. Review: Emerging strategies for antimicrobial drug delivery to the ocular surface: Implications for infectious keratitis. Ocul. Surf. 15, 670–679 (2017).Article

Sharma，A。＆Taniguchi，J。综述：抗菌药物输送到眼表的新兴策略：对感染性角膜炎的影响。。冲浪。15670-679（2017）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Santoni, A. et al. Management of invasive squamous cell carcinomas of the conjunctiva. Am. J. Ophthalmol. 200, 1–9 (2019).Article

Santoni，A。等人。结膜浸润性鳞状细胞癌的治疗。美国眼科杂志。200，1-9（2019）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Ahremark, J. et al. Benchmarking a machine learning model in the transformation from PyTorch to CoreML. LiU Electronic Press 33 (2022)Download referencesAcknowledgementsWe thank Editage for the English language editing.FundingThis study was supported by the Japan Agency for Medical Research and Development (Y.U., JP22hma322004).

Ahremark，J.等人。在从PyTorch到CoreML的转换中对机器学习模型进行基准测试。刘电子出版社33（2022）下载参考文献致谢我们感谢Editage的英文编辑。资助这项研究得到了日本医学研究与发展署（Y.U.，JP22hma322004）的支持。

The funders had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication.Author informationAuthors and AffiliationsDepartment of Ophthalmology, Tokyo Dental College Ichikawa General Hospital, 5-11-13, Sugano, Ichikawa, Chiba, 272-8513, JapanYosuke Taki, Osama M.

资助者在研究的设计和实施中没有任何作用；数据的收集、管理、分析和解释；稿件的准备，审查或批准；并决定提交稿件出版。作者信息作者和附属机构东京牙科学院一川总医院眼科，5-11-13，杉野，一川，千叶，272-8513，日本Osuke Taki，Osama M。

A. Ibrahim, Naohiko Aketa & Takefumi YamaguchiDepartment of Ophthalmology, Faculty of Medicine, University of Tsukuba, Tsukuba, Ibaraki, JapanYuta UenoScholarly Information Division, Information Technology Center, Nagoya University, Nagoya, Aichi, JapanMasahiro OdaGraduate School of Informatics, Nagoya University, Nagoya, Aichi, JapanMasahiro OdaDepartment of Ophthalmology, Osaka University Gradual School of Medicine, Suita, Osaka, JapanYoshiyuki KitaguchiClinical and Translational Research Center, Keio University Hospital, Shinjuku, Tokyo, JapanNaohiko AketaAuthorsYosuke TakiView author publicationsYou can also search for this author in.

A、 Ibrahim，Naohiko Aketa&Takefumi Yamaguchi筑波大学医学院眼科，筑波，茨城，日本名古屋大学信息技术中心，名古屋大学信息技术中心，爱知名古屋，日本名古屋大学信息学研究生院，名古屋，爱知名古屋，日本大阪大学渐进医学院眼科，大阪，大阪AketaAuthorYosuke TakiView作者出版物您也可以在中搜索此作者。

PubMed Google ScholarYuta UenoView author publicationsYou can also search for this author in

PubMed Google ScholarYuta UenoView作者出版物您也可以在

PubMed Google ScholarMasahiro OdaView author publicationsYou can also search for this author in

PubMed Google ScholarMasahiro OdaView作者出版物您也可以在

PubMed Google ScholarYoshiyuki KitaguchiView author publicationsYou can also search for this author in

PubMed Google ScholarYoshiyuki KitaguchiView作者出版物您也可以在

PubMed Google ScholarOsama M. A. IbrahimView author publicationsYou can also search for this author in

PubMed Google ScholarOsama M.A.IbrahimView作者出版物您也可以在

PubMed Google ScholarNaohiko AketaView author publicationsYou can also search for this author in

PubMed Google ScholarNaohiko AketaView作者出版物您也可以在

PubMed Google ScholarTakefumi YamaguchiView author publicationsYou can also search for this author in

PubMed Google ScholarTakefumi YamaguchiView作者出版物您也可以在

PubMed Google ScholarContributionsConcept and design: Y. T., Y. U., M. O., and T. Y. Acquisition of photograph: Y. T., and T. Y. Development of the network architectures: M. O. Software engineering: Y. K. Critical revision of the manuscript for important intellectual content: Y.

PubMed谷歌学术贡献概念与设计：Y.T.，Y.U.，M.O。和T.Y。照片获取：Y.T。和T.Y。网络架构的发展：M.O。软件工程：Y.K。重要知识内容手稿的关键修订：Y。

U., M. O., N. A., O. I., and Y. K. Management of this project: Y. U., and T. Y. Obtained funding: Y. U. Administrative, technical, or material support: Y. U., and T. Y.. Supervision: Y. U., and T. Y.Corresponding authorCorrespondence to.

U、 ，M.O.，N.A.，O.I。和Y.K。该项目的管理：Y.U。和T.Y。获得资金：Y.U。行政，技术或物质支持：Y.U。和T.Y。监督：Y.U。和T.Y。相应的作者。

Takefumi Yamaguchi.Ethics declarations

山口武文。道德宣言

Competing interests

相互竞争的利益

Takefumi Yamaguchi: Grants (Nortis Pharma); honoria for lectures (Alcon Japan, HOYA, Novartis Pharma, AMO Japan, Santen Pharmaceuticals, Senju Pharmaceutical, Johnson & Johnson).

山口武文：补助金（Nortis Pharma）；讲座荣誉奖（Alcon Japan，HOYA，Novartis Pharma，AMO Japan，Santen Pharmaceuticals，Senju Pharmacecal，Johnson&Johnson）。

Additional informationPublisher's noteSpringer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Supplementary InformationSupplementary Legends.Supplementary Figures.Supplementary Video 1.Supplementary Video 2.Rights and permissions

Additional informationPublisher的noteSpringer Nature在已发布地图和机构隶属关系中的管辖权主张方面保持中立。补充信息补充图例。补充数字。补充视频1。补充视频2。权利和权限

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

开放获取本文是根据知识共享署名4.0国际许可证授权的，该许可证允许以任何媒体或格式使用，共享，改编，分发和复制，只要您对原始作者和来源给予适当的信任，提供知识共享许可证的链接，并指出是否进行了更改。

The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

本文中的图像或其他第三方材料包含在文章的知识共享许可中，除非在材料的信用额度中另有说明。如果材料未包含在文章的知识共享许可中，并且您的预期用途不受法律法规的许可或超出许可用途，则您需要直接获得版权所有者的许可。

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/..

要查看此许可证的副本，请访问http://creativecommons.org/licenses/by/4.0/..

Reprints and permissionsAbout this articleCite this articleTaki, Y., Ueno, Y., Oda, M. et al. Analysis of the performance of the CorneAI for iOS in the classification of corneal diseases and cataracts based on journal photographs.

转载和许可本文引用本文Taki，Y.，Ueno，Y.，Oda，M。等人根据期刊照片分析iOS角膜在角膜疾病和白内障分类中的表现。

Sci Rep 14, 15517 (2024). https://doi.org/10.1038/s41598-024-66296-3Download citationReceived: 25 February 2024Accepted: 01 July 2024Published: 05 July 2024DOI: https://doi.org/10.1038/s41598-024-66296-3Share this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

Sci Rep 1415517（2024）。https://doi.org/10.1038/s41598-024-66296-3Download引文接收日期：2024年2月25日接受日期：2024年7月1日发布日期：2024年7月5日OI：https://doi.org/10.1038/s41598-024-66296-3Share本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供

KeywordsCorneAIArtificial intelligenceiPhoneSmartphoneCornea diseases

关键词角膜人工智能手机手机角膜疾病

Subjects

主题

Eye diseasesEye manifestations

眼部疾病表现

CommentsBy submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

评论通过提交评论，您同意遵守我们的条款和社区指南。如果您发现有虐待行为或不符合我们的条款或准则，请将其标记为不合适。