Xiaolan Chen

Xiaolan Chen

Auto-generated profile, based on publicly available information

Xiaolan Chen

School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
3 May 2024 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
XCXiaolan Chen
Xiaolan Chen
WZWeiyi Zhang
Weiyi Zhang
PXPusheng Xu
Pusheng Xu
ZZZiwei Zhao
Ziwei Zhao
YZYingfeng Zheng
Yingfeng Zheng
MHMingguang He
Mingguang He
Fundus fluorescein angiography (FFA) is a crucial diagnostic tool for chorioretinal diseases, but its interpretation requires significant expertise and time. Prior studies have used Artificial Intelligence (AI)-based systems to assist FFA interpretation, but these systems lack user interaction and comprehensive evaluation by ophthalmologists. Here, we used large language models (LLMs) to develop an automated interpretation pipeline for both report generation and medical question-answering (QA) for FFA images. The pipeline comprises two parts: an image-text alignment module (Bootstrapping Language-Image Pre-training) for report generation and an LLM (Llama 2) for interactive QA. The model was developed using 654,343 FFA images with 9392 reports. It was evaluated both automatically, using language-based and classification-based metrics, and manually by three experienced ophthalmologists. The automatic evaluation of the generated reports demonstrated that the system can generate coherent and comprehensible free-text reports, achieving a BERTScore of 0.70 and F1 scores ranging from 0.64 to 0.82 for detecting top-5 retinal conditions. The manual evaluation revealed acceptable accuracy (68.3%, Kappa 0.746) and completeness (62.3%, Kappa 0.739) of the generated reports. The generated free-form answers were evaluated manually, with the majority meeting the ophthalmologists’ criteria (error-free: 70.7%, complete: 84.0%, harmless: 93.7%, satisfied: 65.3%, Kappa: 0.762–0.834). This study introduces an innovative framework that combines multi-modal transformers and LLMs, enhancing ophthalmic image interpretation, and facilitating interactive communications during medical consultation.

11 December 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
XCXiaolan Chen
Xiaolan Chen
ZZZiwei Zhao
Ziwei Zhao
WZWeiyi Zhang
Weiyi Zhang
PXPusheng Xu
Pusheng Xu
YWYue Wu
Yue Wu
MHMingguang He
Mingguang He
Background: Large language models (LLMs) have the potential to enhance clinical flow and improve medical education, but they encounter challenges related to specialized knowledge in ophthalmology. Objective: This study aims to enhance ophthalmic knowledge by refining a general LLM into an ophthalmology-specialized assistant for patient inquiries and medical education. Methods: We transformed Llama2 into an ophthalmology-specialized LLM, termed EyeGPT, through the following 3 strategies: prompt engineering for role-playing, fine-tuning with publicly available data sets filtered for eye-specific terminology (83,919 samples), and retrieval-augmented generation leveraging a medical database and 14 ophthalmology textbooks. The efficacy of various EyeGPT variants was evaluated by 4 board-certified ophthalmologists through comprehensive use of 120 diverse category questions in both simple and complex question-answering scenarios. The performance of the best EyeGPT model was then compared with that of the unassisted human physician group and the EyeGPT+human group. We proposed 4 metrics for assessment: accuracy, understandability, trustworthiness, and empathy. The proportion of hallucinations was also reported. Results: The best fine-tuned model significantly outperformed the original Llama2 model at providing informed advice (mean 9.30, SD 4.42 vs mean 13.79, SD 5.70; P<.001) and mitigating hallucinations (97/120, 80.8% vs 53/120, 44.2%, P<.001). Incorporating information retrieval from reliable sources, particularly ophthalmology textbooks, further improved the model's response compared with solely the best fine-tuned model (mean 13.08, SD 5.43 vs mean 15.14, SD 4.64; P=.001) and reduced hallucinations (71/120, 59.2% vs 57/120, 47.4%, P=.02). Subgroup analysis revealed that EyeGPT showed robustness across common diseases, with consistent performance across different users and domains. Among the variants, the model integrating fine-tuning and book retrieval ranked highest, closely followed by the combination of fine-tuning and the manual database, standalone fine-tuning, and pure role-playing methods. EyeGPT demonstrated competitive capabilities in understandability and empathy when compared with human ophthalmologists. With the assistance of EyeGPT, the performance of the ophthalmologist was notably enhanced. Conclusions: We pioneered and introduced EyeGPT by refining a general domain LLM and conducted a comprehensive comparison and evaluation of different strategies to develop an ophthalmology-specific assistant. Our results highlight EyeGPT’s potential to assist ophthalmologists and patients in medical settings.

30 December 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
ZZZiwei Zhao
Ziwei Zhao
WZWeiyi Zhang
Weiyi Zhang
XCXiaolan Chen
Xiaolan Chen
FSFan Song
Fan Song
JGJames Gunasegaram
James Gunasegaram
NLNa Liu
Na Liu
Background: Large language models have shown remarkable efficacy in various medical research and clinical applications. However, their skills in medical image recognition and subsequent report generation or question answering (QA) remain limited. Objective: We aim to finetune a multimodal, transformer-based model for generating medical reports from slit lamp images and develop a QA system using Llama2. We term this entire process slit lamp–GPT. Methods: Our research used a dataset of 25,051 slit lamp images from 3409 participants, paired with their corresponding physician-created medical reports. We used these data, split into training, validation, and test sets, to finetune the Bootstrapping Language-Image Pre-training framework toward report generation. The generated text reports and human-posed questions were then input into Llama2 for subsequent QA. We evaluated performance using qualitative metrics (including BLEU [bilingual evaluation understudy], CIDEr [consensus-based image description evaluation], ROUGE-L [Recall-Oriented Understudy for Gisting Evaluation—Longest Common Subsequence], SPICE [Semantic Propositional Image Caption Evaluation], accuracy, sensitivity, specificity, precision, and F1-score) and the subjective assessments of two experienced ophthalmologists on a 1-3 scale (1 referring to high quality). Results: We identified 50 conditions related to diseases or postoperative complications through keyword matching in initial reports. The refined slit lamp–GPT model demonstrated BLEU scores (1-4) of 0.67, 0.66, 0.65, and 0.65, respectively, with a CIDEr score of 3.24, a ROUGE (Recall-Oriented Understudy for Gisting Evaluation) score of 0.61, and a Semantic Propositional Image Caption Evaluation score of 0.37. The most frequently identified conditions were cataracts (22.95%), age-related cataracts (22.03%), and conjunctival concretion (13.13%). Disease classification metrics demonstrated an overall accuracy of 0.82 and an F1-score of 0.64, with high accuracies (≥0.9) observed for intraocular lens, conjunctivitis, and chronic conjunctivitis, and high F1-scores (≥0.9) observed for cataract and age-related cataract. For both report generation and QA components, the two evaluating ophthalmologists reached substantial agreement, with κ scores between 0.71 and 0.84. In assessing 100 generated reports, they awarded scores of 1.36 for both completeness and correctness; 64% (64/100) were considered “entirely good,” and 93% (93/100) were “acceptable.” In the evaluation of 300 generated answers to questions, the scores were 1.33 for completeness, 1.14 for correctness, and 1.15 for possible harm, with 66.3% (199/300) rated as “entirely good” and 91.3% (274/300) as “acceptable.” Conclusions: This study introduces the slit lamp–GPT model for report generation and subsequent QA, highlighting the potential of large language models to assist ophthalmologists and patients.

27 August 2025 in British Journal of Ophthalmology
Verified
Journal Article
Closed access
PDF file
XCXiaolan Chen
Xiaolan Chen
RCRuoyu Chen
Ruoyu Chen
PXPusheng Xu
Pusheng Xu
XWXiaojie Wan
Xiaojie Wan
WZWeiyi Zhang
Weiyi Zhang
DSDanli Shi
Danli Shi
Ophthalmic practice involves the integration of diverse clinical data and interactive decision-making, posing challenges for traditional artificial intelligence (AI) systems. Visual question answering (VQA) addresses this by combining computer vision and natural language processing to interpret medical images through user-driven queries. Evolving from VQA, multimodal AI agents enable continuous dialogue, tool use and context-aware clinical decision support. This review explores recent developments in ophthalmic conversational AI, spanning theoretical advances and practical implementations. We highlight the transformative role of large language models (LLMs) in improving reasoning, adaptability and task execution. However, key obstacles remain, including limited multimodal datasets, absence of standardised evaluation protocols, and challenges in clinical integration. We outline these limitations and propose future research directions to support the development of robust, LLM-driven AI systems. Realising their full potential will depend on close collaboration between AI researchers and the ophthalmic community.

14 May 2025 in Asia-Pacific Journal of Ophthalmology
Verified
Journal Article
Open access
KXKezheng Xu
Kezheng Xu
XCXiaolan Chen
Xiaolan Chen
BLBowen Liu
Bowen Liu
Kai JinKai Jin
Kai Jin
MHMingguang He
Mingguang He
DSDanli Shi
Danli Shi

3 July 2025 in British Journal of Ophthalmology
Verified
Journal Article
Closed access
PDF file
PXPusheng Xu
Pusheng Xu
PCPeranut Chotcomwongse
Peranut Chotcomwongse
WZWeiyi Zhang
Weiyi Zhang
XCXiaolan Chen
Xiaolan Chen
XWXinyuan Wu
Xinyuan Wu
PRPaisan Ruamviboonsuk
Paisan Ruamviboonsuk
Purpose To develop an annotated fundus angiographic dataset, including fundus fluorescein angiography (FFA) and indocyanine green angiography (ICGA), and establish baseline methods for automatic report generation. Methods This retrospective study reviewed patients aged ≥18 years who underwent FFA or ICGA at Rajavithi Hospital, Thailand, between 1 January and 31 December 2019. A total of 55 361 de-identified images from 1691 patients (3179 eyes) were annotated by retinal specialists with detailed descriptions of the type, location, shape, size and pattern of abnormal fluorescence. Two baseline methods were developed: (1) a classification-based approach using ResNet101 with class-specific residual attention for multi-label lesion recognition and (2) a language-generation approach using the Bootstrapping Language-Image Pre-training framework, fine-tuned on angiographic images and structured reports. Model performances were evaluated using F1 score and BERTScore. Results The dataset includes 24 diagnostic conditions, with macular neovascularisation (32.5%) being the most prevalent, followed by unremarkable findings (21.8%) and dry age-related macular degeneration (10.2%). Most eyes (81.8%) underwent both FFA and ICGA. Hyperfluorescence was observed in 75.6% of cases, predominantly due to leakage, while hypofluorescence was present in 28.1%. The classification-based method achieved an average score of 7.966, demonstrating superior performance in recognising choroidal neovascularisation, hyperfluorescent and hypofluorescent areas. The language-generation method achieved a comparable average score of 7.947, excelling in impression recognition and the hyperfluorescence identification. Conclusion We present the largest annotated fundus angiographic dataset to date, along with two effective baseline methods for automatic report generation, offering a valuable foundation for advancing artificial intelligence applications in ophthalmology.