Xuanqiao Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xuanqiao Lin has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Jin Yang
Department of Ophthalmology, Eye, Ear, Nose, and Throat Hospital of Fudan University, Shanghai, People’s Republic of China
4 shared publications - Lei Cai
Department of Ophthalmology, Eye, Ear, Nose, and Throat Hospital of Fudan University, Shanghai, People's Republic of China
3 shared publications Yizhou Yang
Department of Ophthalmology, Eye, Ear, Nose, and Throat Hospital of Fudan University, Shanghai, People's Republic of China
3 shared publicationsYuecheng Ren
Department of Ophthalmology, Jiaxing Hospital of Traditional Chinese Medicine, Jiaxing, China
2 shared publicationsAijun Wang
Department of Ophthalmology, Shanghai Bright Eye Hospital
1 shared publication- Dexi Zhu
National Clinical Research Center for Ocular Diseases, Eye Hospital, Wenzhou Medical University, Wenzhou, China.; National Engineering Research Center of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, China.; State Key Laboratory of Ophthalmology, Optometry and Visual Science, Eye Hospital, Wenzhou Medical University, Wenzhou, China.
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 18 March 2026
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (5) , 101158
Comparative Evaluation of Deep-Reasoning Large Language Models for Ophthalmic Emergencies
- 18 March 2026
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (5) , 101158
Top Cited PapersOpen AccessComparative Evaluation of Deep-Reasoning Large Language Models for Ophthalmic Emergencies
- Open Access
- 1 February 2026
- Published by SAGE Publications in Digital Health
- Vol. 12
Agreement and repeatability of general-purpose large language model recommendations for pediatric IOL power and target refraction
Purpose: To evaluate the agreement, repeatability, and decision patterns of general-purpose large language models (LLMs) for intraocular lens (IOL) planning in children with congenital cataract. Methods: This retrospective comparative evaluation included 51 eyes from 37 children who underwent primary IOL implantation. ChatGPT 5.6 Sol, Gemini 3.0 Pro, DeepSeek V4, and Doubao Expert Mode were evaluated using standardized preoperative case information. The first independent response was used for primary performance analyses, and three independent runs were used to assess repeatability. Model-generated target refraction and recommended IOL power were compared with the documented institutional target refraction and implanted IOL power. Results: Target-refraction and IOL-power recommendations differed significantly among models (both P<0.001). Mean absolute target error ranged from 0.63 to 0.93 D, with 25.5%–54.9% of recommendations within ±0.50 D of the institutional target. Mean absolute IOL-power error ranged from 2.53 to 4.92 D; 5.9%–31.4% of recommendations were within ±1.00 D of the implanted power. Exact repeatability ranged from 45.1%–98.0% for target refraction and 0%–33.3% for IOL power. Across all models, target refraction became less hyperopic with increasing age, and recommended IOL power decreased with increasing axial length. Conclusions: General-purpose LLMs captured broad pediatric refractive-planning patterns but showed model-specific differences, variable agreement with institutional clinical planning, and lower stability in final IOL-power recommendations. In this unconstrained setting, current general-purpose LLMs are not sufficiently reliable for independent pediatric IOL planning and may be better positioned as adjunctive tools alongside validated calculation methods and specialist judgment.
- 1 February 2026
- Published by SAGE Publications in Digital Health
- Vol. 12
Open AccessAgreement and repeatability of general-purpose large language model recommendations for pediatric IOL power and target refraction
Purpose: To evaluate the agreement, repeatability, and decision patterns of general-purpose large language models (LLMs) for intraocular lens (IOL) planning in children with congenital cataract. Methods: This retrospective comparative evaluation included 51 eyes from 37 children who underwent primary IOL implantation. ChatGPT 5.6 Sol, Gemini 3.0 Pro, DeepSeek V4, and Doubao Expert Mode were evaluated using standardized preoperative case information. The first independent response was used for primary performance analyses, and three independent runs were used to assess repeatability. Model-generated target refraction and recommended IOL power were compared with the documented institutional target refraction and implanted IOL power. Results: Target-refraction and IOL-power recommendations differed significantly among models (both P<0.001). Mean absolute target error ranged from 0.63 to 0.93 D, with 25.5%–54.9% of recommendations within ±0.50 D of the institutional target. Mean absolute IOL-power error ranged from 2.53 to 4.92 D; 5.9%–31.4% of recommendations were within ±1.00 D of the implanted power. Exact repeatability ranged from 45.1%–98.0% for target refraction and 0%–33.3% for IOL power. Across all models, target refraction became less hyperopic with increasing age, and recommended IOL power decreased with increasing axial length. Conclusions: General-purpose LLMs captured broad pediatric refractive-planning patterns but showed model-specific differences, variable agreement with institutional clinical planning, and lower stability in final IOL-power recommendations. In this unconstrained setting, current general-purpose LLMs are not sufficiently reliable for independent pediatric IOL planning and may be better positioned as adjunctive tools alongside validated calculation methods and specialist judgment.
- Open Access
- 1 February 2026
- Published by SAGE Publications in Digital Health
- Vol. 12
Ophthalmic health communication in the video-based social media era: A narrative review of information quality, engagement dynamics, and professional education
With the rapid ascent of video-based social media, platforms like TikTok and YouTube have become primary sources of ophthalmic health information, shaping both patient perceptions and professional development. This narrative review synthesizes evidence from 76 empirical studies to evaluate the quality and reliability of ophthalmic video content. We identify a persistent engagement paradox, where algorithm-driven metrics such as view counts and shares often favor simplified, emotionally resonant, or visually striking narratives over medically accurate and balanced counseling. Clinician-produced content generally showed higher clinical integrity in the included studies, but it often received lower engagement than peer-led experiential narratives. Beyond patient-facing education, we explore the emerging role of video platforms as professional-facing education for residents, highlighting the risks of survivor bias in unedited or curated operative footage. Furthermore, the visual-centric nature of ophthalmology introduces unique ethical challenges, particularly regarding the anonymization of recognizable facial features and the permanence of digital consent. As Generative AI introduces new risks of sophisticated deepfake misinformation, this review emphasizes the urgent need for multi-modal assessment tools and active professional stewardship to ensure the integrity of digital eye care.
- 1 February 2026
- Published by SAGE Publications in Digital Health
- Vol. 12
Open AccessOphthalmic health communication in the video-based social media era: A narrative review of information quality, engagement dynamics, and professional education
With the rapid ascent of video-based social media, platforms like TikTok and YouTube have become primary sources of ophthalmic health information, shaping both patient perceptions and professional development. This narrative review synthesizes evidence from 76 empirical studies to evaluate the quality and reliability of ophthalmic video content. We identify a persistent engagement paradox, where algorithm-driven metrics such as view counts and shares often favor simplified, emotionally resonant, or visually striking narratives over medically accurate and balanced counseling. Clinician-produced content generally showed higher clinical integrity in the included studies, but it often received lower engagement than peer-led experiential narratives. Beyond patient-facing education, we explore the emerging role of video platforms as professional-facing education for residents, highlighting the risks of survivor bias in unedited or curated operative footage. Furthermore, the visual-centric nature of ophthalmology introduces unique ethical challenges, particularly regarding the anonymization of recognizable facial features and the permanence of digital consent. As Generative AI introduces new risks of sophisticated deepfake misinformation, this review emphasizes the urgent need for multi-modal assessment tools and active professional stewardship to ensure the integrity of digital eye care.
- Open Access
- 1 February 2026
- Published by SAGE Publications in Digital Health
- Vol. 12
Comparison of three large language models in recognizing ophthalmological examination and supporting preoperative toric IOL planning
Purpose: To evaluate the performance of three large language models (LLMs) in automated recognition of IOLMaster 700 reports and preoperative toric intraocular lens (IOL) planning. Methods: The retrospective study analyzed preoperative examination reports of patients who underwent cataract surgery with toric IOL implantation. Three models (ChatGPT-5, ChatGPT-5 Thinking and DeepSeek Thinking) were instructed to extract key biometric parameters, evaluate a patient’s suitability for toric IOL implantation, and generate a plan. Model performance was evaluated based on structured-data recognition, refractive prediction outcomes and thinking times. Results: Fifty-four eyes of 54 patients were analyzed. ChatGPT-5 Thinking model consistently achieved the highest agreement with clinical reference for all extracted parameters, and demonstrated more reliable extraction of axis information. ChatGPT-5 showed intermediate performance, while DeepSeek Thinking was the least consistent in axis-dependent fields but performed adequately for basic biometry. Refractive and axis prediction errors were smallest with ChatGPT-5 Thinking, yielding the largest proportion of cases within prespecified clinical thresholds and the highest concordance with the calculator-based reference plan. Analysis of thinking times showed that longer processing did not necessarily correlate with better accuracy. Conclusions: Advanced LLMs show promise for automated interpretation of ophthalmic biometry reports and calculator-based toric IOL planning workflows. These findings support the feasibility of LLM-assisted workflow automation, with ChatGPT-5 Thinking providing the most favorable balance of accuracy and efficiency in this setting.
- 1 February 2026
- Published by SAGE Publications in Digital Health
- Vol. 12
Open AccessComparison of three large language models in recognizing ophthalmological examination and supporting preoperative toric IOL planning
Purpose: To evaluate the performance of three large language models (LLMs) in automated recognition of IOLMaster 700 reports and preoperative toric intraocular lens (IOL) planning. Methods: The retrospective study analyzed preoperative examination reports of patients who underwent cataract surgery with toric IOL implantation. Three models (ChatGPT-5, ChatGPT-5 Thinking and DeepSeek Thinking) were instructed to extract key biometric parameters, evaluate a patient’s suitability for toric IOL implantation, and generate a plan. Model performance was evaluated based on structured-data recognition, refractive prediction outcomes and thinking times. Results: Fifty-four eyes of 54 patients were analyzed. ChatGPT-5 Thinking model consistently achieved the highest agreement with clinical reference for all extracted parameters, and demonstrated more reliable extraction of axis information. ChatGPT-5 showed intermediate performance, while DeepSeek Thinking was the least consistent in axis-dependent fields but performed adequately for basic biometry. Refractive and axis prediction errors were smallest with ChatGPT-5 Thinking, yielding the largest proportion of cases within prespecified clinical thresholds and the highest concordance with the calculator-based reference plan. Analysis of thinking times showed that longer processing did not necessarily correlate with better accuracy. Conclusions: Advanced LLMs show promise for automated interpretation of ophthalmic biometry reports and calculator-based toric IOL planning workflows. These findings support the feasibility of LLM-assisted workflow automation, with ChatGPT-5 Thinking providing the most favorable balance of accuracy and efficiency in this setting.
- Open Access
- 1 January 2025
- Published by Wolters Kluwer Health in Journal of Cataract & Refractive Surgery
- Vol. 51 (1) , 31-39
Rotational stability of plate-haptic toric intraocular lenses implantation with a capsular tension ring: prospective randomized paired-eye study
Purpose: To compare the rotational stability and visual outcomes of plate-haptic toric intraocular lenses (IOLs) with and without a capsular tension ring (CTR) in paired eyes. Setting: Eye and Ears, Nose, and Throat Hospital of Fudan University, Shanghai, China. Design: Prospective, randomized, paired-eye study. Methods: Patients with bilateral cataracts and coexisting regular corneal astigmatism were enrolled. The 2 eyes of each patient were randomly assigned to the CTR or non-CTR (NCTR) group. Both eyes of each patient were subjected to phacoemulsification and toric IOL implantation. CTRs were implanted into the eyes of the CTR group. All patients were followed up for 12 months; uncorrected distance visual acuity (UDVA), residual astigmatism (RAS), and rotational degree of the toric IOL were recorded. Results: 186 eyes of 93 patients were eligible for analysis. At each visit, UDVA improved significantly postoperatively in all eyes (P < .001). The mean rotational degree and RAS were significantly smaller in the CTR group at the 2-week visit (P < .05). The toric IOLs achieved rotational stability at 1 week postoperatively in the CTR group while at 2 weeks postoperatively in the NCTR group. In the subgroup analyses, CTR coimplantation significantly reduced the 2-week IOL rotation in eyes meeting specific ocular measurements. Conclusions: CTR coimplantation could increase the rotational stability of plate-haptic toric IOLs, by reducing the amount of IOL rotation in the early postoperative period and accelerating the stabilization of IOLs in the capsular bag.
- 1 January 2025
- Published by Wolters Kluwer Health in Journal of Cataract & Refractive Surgery
- Vol. 51 (1) , 31-39
Open AccessRotational stability of plate-haptic toric intraocular lenses implantation with a capsular tension ring: prospective randomized paired-eye study
Purpose: To compare the rotational stability and visual outcomes of plate-haptic toric intraocular lenses (IOLs) with and without a capsular tension ring (CTR) in paired eyes. Setting: Eye and Ears, Nose, and Throat Hospital of Fudan University, Shanghai, China. Design: Prospective, randomized, paired-eye study. Methods: Patients with bilateral cataracts and coexisting regular corneal astigmatism were enrolled. The 2 eyes of each patient were randomly assigned to the CTR or non-CTR (NCTR) group. Both eyes of each patient were subjected to phacoemulsification and toric IOL implantation. CTRs were implanted into the eyes of the CTR group. All patients were followed up for 12 months; uncorrected distance visual acuity (UDVA), residual astigmatism (RAS), and rotational degree of the toric IOL were recorded. Results: 186 eyes of 93 patients were eligible for analysis. At each visit, UDVA improved significantly postoperatively in all eyes (P < .001). The mean rotational degree and RAS were significantly smaller in the CTR group at the 2-week visit (P < .05). The toric IOLs achieved rotational stability at 1 week postoperatively in the CTR group while at 2 weeks postoperatively in the NCTR group. In the subgroup analyses, CTR coimplantation significantly reduced the 2-week IOL rotation in eyes meeting specific ocular measurements. Conclusions: CTR coimplantation could increase the rotational stability of plate-haptic toric IOLs, by reducing the amount of IOL rotation in the early postoperative period and accelerating the stabilization of IOLs in the capsular bag.