Aims To investigate rule-based and deep learning (DL)-based methods for the automatically generating natural language diagnostic reports for macular diseases. Methods This diagnostic study collected the ophthalmic images of 2261 eyes from 1303 patients. Colour fundus photographs and optical coherence tomography images were obtained. Eyes without retinal diseases as well as eyes diagnosed with four macular diseases were included. For each eye, a diagnostic report was written with a format consisting of lesion descriptions, diagnoses and recommendations. Subsequently, a rule-based natural language processing (NLP) and a DL-based NLP system were developed to automatically generate a diagnostic report. To assess the effectiveness of these models, two junior ophthalmologists wrote diagnostic reports for the collected images independently. A questionnaire was designed and judged by two retina specialists to grade each report’s readability, correctness of diagnosis, lesion description and recommendations. Results The rule-based NLP reports achieved higher grades over junior ophthalmologists in correctness of diagnosis (9.13±1.52 vs 9.03±1.42 points) and recommendations (8.55±2.74 vs 8.50±2.53 points). Furthermore, the DL-based NLP reports got slightly lower grades to those of junior ophthalmologists in lesion description (8.82±1.84 vs 9.12±1.20 points, p<0.05), correctness of diagnosis (8.72±2.36 vs 9.08±1.55 points, p<0.05) and recommendations (8.81±2.52 vs 9.15±1.65 points, p<0.05). For readability, the DL-based reports performed better than junior ophthalmologists, with scores of 9.98±0.17 vs 9.94±0.25 points (p=0.094). Conclusions The multimodal AI system, coupled with the NLP algorithm, has demonstrated competence in generating reports for four macular diseases compared with junior ophthalmologists. Data sharing not applicable as no datasets generated and/or analysed for this study.

中文翻译：

---

通过自然语言处理算法生成黄斑疾病的诊断报告

目的 研究基于规则和基于深度学习（DL）的黄斑疾病自然语言诊断报告的自动生成方法。方法 本诊断研究收集了 1303 例患者 2261 只眼睛的眼科图像。获得彩色眼底照片和光学相干断层扫描图像。包括没有视网膜疾病的眼睛以及被诊断患有四种黄斑疾病的眼睛。对于每只眼睛，都以由病变描述、诊断和建议组成的格式编写诊断报告。随后，开发了基于规则的自然语言处理（NLP）和基于 DL 的 NLP 系统，以自动生成诊断报告。为了评估这些模型的有效性，两名初级眼科医生独立撰写了收集到的图像的诊断报告。由两名视网膜专家设计并评判一份问卷，对每份报告的可读性、诊断的正确性、病变描述和建议进行评分。结果 基于规则的 NLP 报告在诊断正确性（9.13±1.52 vs 9.03±1.42 分）和推荐性（8.55±2.74 vs 8.50±2.53 分）方面均高于初级眼科医生。 此外，基于 DL 的 NLP 报告在病变描述（8.82±1.84 vs 9.12±1.20 分，p<0.05）、诊断正确性（8.72±2.36 vs 9.08±1.55分，p<0.05）和推荐（8.81±2.52 vs 9.15±1.65分，p<0.05）的评分略低于初级眼科医生。在可读性方面，基于DL的报告表现优于初级眼科医生，得分为9.98±0.17 vs 9.94±0.25分（p=0.094）。结论 与初级眼科医生相比，多模态人工智能系统与NLP算法相结合，在生成4种黄斑疾病的报告方面表现出能力。数据共享不适用，因为没有为本研究生成和/或分析数据集。