Xuanqiao Lin

Xuanqiao Lin

Auto-generated profile, based on publicly available information

Xuanqiao Lin

Eye, Ear, Nose, and Throat Hospital of Fudan University

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2025 in Journal of Cataract & Refractive Surgery
Verified
Journal Article
Open access
XLXuanqiao Lin
Xuanqiao Lin
DMDongmei Ma
Dongmei Ma
XHXiaoyan Han
Xiaoyan Han
ZHZhixiang Hua
Zhixiang Hua
WSWenqian Shen
Wenqian Shen
Jin YangJin Yang
Jin Yang
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.

18 March 2026 in Ophthalmology Science
Verified
Journal Article
Open access
XLXuanqiao Lin
Xuanqiao Lin
YYYizhou Yang
Yizhou Yang
YRYuecheng Ren
Yuecheng Ren
LWLan Wang
Lan Wang
LCLei Cai
Lei Cai
To evaluate contemporary deep-reasoning large language models (LLMs) for early assessment of ophthalmic emergencies using sequential, workflow-mimicking information levels. Cross-sectional, vignette-based, head-to-head comparative evaluation. Thirty-four deidentified emergency ophthalmology teaching cases curated from a publicly accessible repository. Each case was reconstructed into 3 sequential information levels (level 1 [L1]: history; level 2: basic examination; level 3 [L3]: specialist examination). Six LLMs (Doubao, DeepSeek, Kimi-2, ChatGPT-5, Gemini-3, and Grok-4), operating in deep-reasoning mode, generated outputs that were independently scored by 2 ophthalmologists. Diagnoses were graded as fully correct, partially correct, or incorrect; triage category (typical vs. atypical emergency) was rated as correct or incorrect. Ancillary test recommendations were mapped to a prespecified 10-category taxonomy and classified as undertesting, exact match, or overtesting. A four-level composite outcome integrated diagnostic correctness, triage accuracy, and testing. Diagnostic correctness (fully correct, partially correct, incorrect), triage-category accuracy, ancillary test recommendation patterns, and composite outcome (ideal, safe but overtesting, potentially dangerous, intermediate). Across 612 model–case–level outputs, 46.9% of diagnoses were fully correct, 24.5% partially correct, and 28.6% incorrect. Fully correct diagnoses increased from 43.1% at L1 to 53.9% at L3 (P = 0.048). Overall triage category accuracy was 85.3% (range, 76.5%–94.1% across models; P = 0.003) and did not differ across information levels (P = 0.89). Ancillary test recommendations most commonly reflected undertesting (51.0%), followed by overtesting (27.5%) and exact matches (21.6%) (P < 0.001 across models). In generalized estimating equation pairwise comparisons, ChatGPT-5 showed higher odds of a fully correct diagnosis than DeepSeek (odds ratio [OR], 3.54; 95% confidence interval [CI], 1.49–8.43) and Gemini-3 (OR, 2.24; 95% CI, 1.31–3.83), and lower odds of potentially dangerous composite outcomes than DeepSeek (OR, 0.28; 95% CI, 0.10–0.74) and Gemini-3 (OR, 0.31; 95% CI, 0.11–0.89). Deep-reasoning LLMs demonstrated high triage category accuracy and moderate diagnostic performance for ophthalmic emergencies, with diagnostic correctness improving at higher information levels. However, ancillary testing patterns varied substantially, and ideal composite safety profiles were uncommon, supporting cautious, supervised deployment with explicit guardrails governing workup recommendations. The author has no/the authors have no proprietary or commercial interest in any materials discussed in this article.

1 February 2026 in Digital Health
Verified
Journal Article
Open access
XLXuanqiao Lin
Xuanqiao Lin
YYYizhou Yang
Yizhou Yang
SWSonglian Wang
Songlian Wang
LCLei Cai
Lei Cai
Jin YangJin Yang
Jin Yang
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.

14 June 2026 in American Journal of Ophthalmology
Verified
Journal Article
Closed access
ELEnze Liu
Enze Liu
XLXuanqiao Lin
Xuanqiao Lin
KZKaiyi Zhu
Kaiyi Zhu
JLJianming Li
Jianming Li
QXQiuling Xie
Qiuling Xie
DZDexi Zhu
Dexi Zhu

1 February 2026 in Digital Health
Verified
Journal Article
Open access
YYYizhou Yang
Yizhou Yang
YRYuecheng Ren
Yuecheng Ren
LLLuze Liu
Luze Liu
YLYue Li
Yue Li
XLXuanqiao Lin
Xuanqiao Lin
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 in Digital Health
Verified
Journal Article
Open access
LBLifang Bai
Lifang Bai
XLXuanqiao Lin
Xuanqiao Lin
XWXingyao Wang
Xingyao Wang
XZXiaohuan Zhao
Xiaohuan Zhao
YYYizhou Yang
Yizhou Yang
Jin YangJin Yang
Jin Yang
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.