Guangzhou Aier Eye Hospital (W.-Z.L.), Jinan University, Guanghzou, China; School of Stomatology and Ophthalmology (W.-Z.L., X.L., Z.Y.), Xianning Medical College, Hubei University of Science and Technology, Xianing, China; SoC Design Center (H.T.), University of Electronic Science and Technology of China, Chengdu, China; School of Electronic Science and Engineering (H.T.), University of Electronic Science and Technology of China, Chengdu, China; Aier School of Ophthalmology (L.-B.W., Z.C., Y.Z., Z.Y.), Central South University, Changsha, China; Information Center (W.D., M.W., F.T.), Aier Eye Hospital Group, Changsha, China; School of Information and Software Engineering (W.-J.W.), University of Electronic Science and Technology of China, Chengdu, China; School of Computer Science and Engineering (Y.T.), University of Electronic Science and Technology of China, Chengdu, China; Hunan Province Optometry Engineering and Technology Research Center (W.-Z.L., L.-B.W., Z.C., X.L., Z.Y.), Changsha, China; and Hunan Province International Cooperation Base for Optometry Science and Technology (W.-Z.L., L.-B.W., Z.C., X.L., Z.Y.), Changsha, China.
Eye Contact Lens. 2024 Jul 1;50(7):297-304. doi: 10.1097/ICL.0000000000001091. Epub 2024 May 2.
To explore the potential of artificial intelligence (AI) to assist prescription determination for orthokeratology (OK) lenses.
Artificial intelligence algorithm development followed by a real-world trial. A total of 11,502 OK lenses fitting records collected from seven clinical environments covering major brands. Records were randomly divided in a three-way data split. Cross-validation was used to identify the most accurate algorithm, followed by an evaluation using an independent test data set. An online AI-assisted system was implemented and assessed in a real-world trial involving four junior and three senior clinicians.
The primary outcome measure was the algorithm's accuracy (ACC). The ACC of the best performance of algorithms to predict the targeted reduction amplitude, lens diameter, and alignment curve of the prescription was 0.80, 0.82, and 0.83, respectively. With the assistance of the AI system, the number of trials required to determine the final prescription significantly decreased for six of the seven participating clinicians (all P <0.01). This reduction was more significant among junior clinicians compared with consultants (0.76±0.60 vs. 0.32±0.60, P <0.001). Junior clinicians achieved clinical outcomes comparable to their seniors, as 93.96% (140/149) and 94.44% (119/126), respectively, of the eyes fitted achieved unaided visual acuity no worse than 0.8 ( P =0.864).
AI can improve prescription efficiency and reduce discrepancies in clinical outcomes among clinicians with differing levels of experience. Embedment of AI in practice should ultimately help lessen the medical burden and improve service quality for myopia boom emerging worldwide.
探索人工智能（AI）在角膜塑形术（OK）镜片处方确定方面的应用潜力。
采用人工智能算法开发，结合真实世界试验。从覆盖主要品牌的七个临床环境中收集了 11502 例 OK 镜片拟合记录，将记录随机分为三部分。采用交叉验证确定最准确的算法，然后使用独立测试数据集进行评估。实施了一个在线 AI 辅助系统，并在涉及四名初级和三名高级临床医生的真实世界试验中进行了评估。
主要结局指标为算法的准确性（ACC）。预测处方目标降低幅度、镜片直径和配适曲线的算法最佳性能的 ACC 分别为 0.80、0.82 和 0.83。在 AI 系统的辅助下，七位参与临床医生中有六位（均 P <0.01）确定最终处方所需的试戴次数显著减少。与顾问相比，初级临床医生的减少更为显著（0.76±0.60 与 0.32±0.60，P <0.001）。初级临床医生的临床结果与他们的高级临床医生相当，因为 93.96%（140/149）和 94.44%（119/126）的配镜眼的裸眼视力均不低于 0.8（P =0.864）。
AI 可以提高处方效率，减少经验水平不同的临床医生之间的临床结果差异。将 AI 嵌入实践中，最终有助于减轻全球近视热潮带来的医疗负担，提高服务质量。
