From Data to Deployment: The Collaborative Community on Ophthalmic Imaging Roadmap for Artificial Intelligence in Age-Related Macular Degeneration.
From Data to Deployment: The Collaborative Community on Ophthalmic Imaging Roadmap for Artificial Intelligence in Age-Related Macular Degeneration.
复制标题
从数据到部署：眼科成像路线图协作社区人工智能在视网膜相关黄斑变性。
DOI：
10.1016/j.ophtha.2022.01.002
复制
发表时间：
2022-05
期刊：
影响因子：
13.7
通讯作者：
Lim, Jennifer, I
中科院分区：
文献类型：
--
作者：
Dow, Eliot R.;Keenan, Tiarnan D. L.;Lad, Eleonora M.;Lee, Aaron Y.;Lee, Cecilia S.;Loewenstein, Anat;Eydelman, Malvina B.;Chew, Emily Y.;Keane, Pearse A.;Lim, Jennifer, I
全球医疗保健系统面临着为2亿老年性黄斑变性（AMD）患者提供充分护理的挑战。人工智能（AI）有可能对AMD患者的诊断和管理产生重大的积极影响。然而，开发用于临床护理的有效人工智能设备面临着许多考虑和挑战，目前缺乏FDA批准的AMD人工智能设备就证明了这一点。描述AMD的人工智能现状，包括当前数据、标准、成就和挑战。AMD人工智能眼科成像协作社区工作组的成员出席了2020年9月7日的成立会议，讨论了这一主题。随后，他们对与该专题有关的医学文献进行了全面审查。成员于2021年12月举行会议及讨论，以综合资料及达成共识。AMD强大的人工智能开发的现有基础设施包括几个大型标记的彩色眼底摄影（CFP）和光学相干断层扫描（OCT）图像数据集。然而，图像数据通常不包含开发可靠、有效和可推广的模型所需的元数据。由于对数据隐私和安全的限制，AMD模型开发的数据共享变得困难，尽管潜在的解决方案正在调查中。计算资源对于当前的应用可能是足够的，但是在许多临床眼科环境中，机器学习（ML）开发的知识可能是稀缺的。尽管存在这些挑战，研究人员已经为AMD开发了有前途的AI模型，用于筛查、诊断、预测和监测。未来的目标包括定义基准，以促进监管授权和随后的现实世界的推广。为AMD的临床护理提供FDA授权的基于AI的设备涉及许多考虑因素，包括识别适当的临床应用，获取和管理大型高质量数据集，开发AI架构，训练和验证模型，以及模型输出和临床最终用户之间的功能交互。迄今为止所做的研究工作代表了医疗设备的起点，最终将使供应商，医疗保健系统和患者受益。
Healthcare systems worldwide are challenged to provide adequate care for the 200 million individuals with age-related macular degeneration (AMD). Artificial intelligence (AI) has the potential to make a significant positive impact on the diagnosis and management of patients with AMD. However, the development of effective AI devices for clinical care faces numerous considerations and challenges, a fact evidenced by a current absence of FDA-approved AI devices for AMD. To delineate the state of AI for AMD including current data, standards, achievements, and challenges. EVIDENCE Members of the Collaborative Community on Ophthalmic Imaging working group for AI in AMD attended an inaugural meeting on September 7, 2020 to discuss the topic. Subsequently, they undertook a comprehensive review of the medical literature relevant to the topic. Members engaged in meetings and discussion through December 2021 to synthesize the information and arrive at consensus. Existing infrastructure for robust AI development for AMD includes several large, labeled datasets of color fundus photography (CFP) and optical coherence tomography (OCT) images. However, image data often does not contain meta-data necessary for the development of reliable, valid, and generalizable models. Data sharing for AMD model development is made difficult by restrictions on data privacy and security, although potential solutions are under investigation. Computing resources may be adequate for current applications, but knowledge of machine learning (ML) development may be scarce in many clinical ophthalmology settings. Despite these challenges, researchers have produced promising AI models for AMD for screening, diagnosis, prediction, and monitoring. Future goals include defining benchmarks to facilitate regulatory authorization and subsequent real-world generalization. Delivering an FDA-authorized, AI-based device for clinical care in AMD involves numerous considerations including the identification of an appropriate clinical application, acquisition and curation of a large, high-quality data set, development of the AI architecture, training and validation of the model, and functional interactions between the model output and clinical end-user. The research efforts undertaken to date represent starting points for the medical devices that will eventually benefit providers, healthcare systems, and patients.
登录
查看更多内容
影响因子：
4.2
作者：
Kashani, Amir H.;Zimmer-Galler, Ingrid E.;Shah, Syed Mahmood;Dustin, Laurie;Do, Diana V.;Eliott, Dean;Haller, Julia A.;Nguyen, Quan Dong
通讯作者：
Nguyen, Quan Dong
影响因子：
13.7
作者：
Keenan, Tiarnan D. L.;Clemons, Traci E.;Chew, Emily Y.
通讯作者：
Chew, Emily Y.
影响因子：
3.9
作者：
Ho AC;Heier JS;Holekamp NM;Garfinkel RA;Ladd B;Awh CC;Singh RP;Sanborn GE;Jacobs JH;Elman MJ;Loewenstein A;Eichenbaum DA
通讯作者：
Eichenbaum DA
影响因子：
13.7
作者：
Domalpally, Amitha;Agron, Elvira;Chew, Emily Y.
通讯作者：
Chew, Emily Y.
影响因子：
13.7
作者：
Busbee, Brandon G.;Ho, Allen C.;Lai, Phillip
通讯作者：
Lai, Phillip