Zhengyun Zhao

Zhengyun Zhao

Auto-generated profile, based on publicly available information

Zhengyun Zhao

Department of Statistics and Data Science, Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
3 January 2022 in Journal of Biomedical Informatics
Verified
Journal Article
Closed access
ZYZheng Yuan
Zheng Yuan
ZZZhengyun Zhao
Zhengyun Zhao
HSHaixia Sun
Haixia Sun
JLJiao Li
Jiao Li
FWFei Wang
Fei Wang
SYSheng Yu
Sheng Yu

18 December 2023 in Scientific Data
Verified
Journal Article
Open access
PDF file
ZZZhengyun Zhao
Zhengyun Zhao
QJQiao Jin
Qiao Jin
FCFangyuan Chen
Fangyuan Chen
TPTuorui Peng
Tuorui Peng
SYSheng Yu
Sheng Yu
Retrieval-based Clinical Decision Support (ReCDS) can aid clinical workflow by providing relevant literature and similar patients for a given patient. However, the development of ReCDS systems has been severely obstructed by the lack of diverse patient collections and publicly available large-scale patient-level annotation datasets. In this paper, we collect a novel dataset of patient summaries and relations called PMC-Patients to benchmark two ReCDS tasks: Patient-to-Article Retrieval (ReCDS-PAR) and Patient-to-Patient Retrieval (ReCDS-PPR). Specifically, we extract patient summaries from PubMed Central articles using simple heuristics and utilize the PubMed citation graph to define patient-article relevance and patient-patient similarity. PMC-Patients contains 167k patient summaries with 3.1 M patient-article relevance annotations and 293k patient-patient similarity annotations, which is the largest-scale resource for ReCDS and also one of the largest patient collections. Human evaluation and analysis show that PMC-Patients is a diverse dataset with high-quality annotations. We also implement and evaluate several ReCDS systems on the PMC-Patients benchmarks to show its challenges and conduct several case studies to show the clinical utility of PMC-Patients.

26 October 2023
Verified
Conference Paper
Open access
ZYZheng Yuan
Zheng Yuan
QJQiao Jin
Qiao Jin
CTChuanqi Tan
Chuanqi Tan
ZZZhengyun Zhao
Zhengyun Zhao
HYHongyi Yuan
Hongyi Yuan
SHSongfang Huang
Songfang Huang
Vision-and-language multi-modal pretraining and fine-tuning have shown great success in visual question answering (VQA). Compared to general domain VQA, the performance of biomedical VQA suffers from limited data. In this paper, we propose a retrieval-augmented pretrain-and-finetune paradigm named RAMM for biomedical VQA to overcome the data limitation issue. Specifically, we collect a new biomedical dataset named PMCPM which offers patient-based image-text pairs containing diverse patient situations from PubMed. Then, we pretrain the biomedical multi-modal model to learn visual and textual representation for image-text pairs and align these representations with image-text contrastive objective (ITC). Finally, we propose a retrieval-augmented method to better use the limited data. We propose to retrieve similar image-text pairs based on ITC from pretraining datasets and introduce a novel retrieval-attention module to fuse the representation of the image and the question with the retrieved images and texts. Experiments demonstrate that our retrieval-augmented pretrain-and-finetune paradigm obtains state-of-the-art performance on Med-VQA2019, Med-VQA2021, VQARAD, and SLAKE datasets. Further analysis shows that the proposed RAMM and PMCPM can enhance biomedical VQA performance compared with previous resources and methods. The pre-trained models and codes are published at https://github.com/GanjinZero/RAMM.

23 May 2024 in Journal of the American Medical Informatics Association
Verified
Journal Article
Closed access
PDF file
HYHuaiyuan Ying
Huaiyuan Ying
ZZZhengyun Zhao
Zhengyun Zhao
YZYang Zhao
Yang Zhao
SZSihang Zeng
Sihang Zeng
SYSheng Yu
Sheng Yu
Objectives: Biomedical Knowledge Graphs play a pivotal role in various biomedical research domains. Concurrently, term clustering emerges as a crucial step in constructing these knowledge graphs, aiming to identify synonymous terms. Due to a lack of knowledge, previous contrastive learning models trained with Unified Medical Language System (UMLS) synonyms struggle at clustering difficult terms and do not generalize well beyond UMLS terms. In this work, we leverage the world knowledge from large language models (LLMs) and propose Contrastive Learning for Representing Terms via Explanations (CoRTEx) to enhance term representation and significantly improves term clustering. Materials and Methods: The model training involves generating explanations for a cleaned subset of UMLS terms using ChatGPT. We employ contrastive learning, considering term and explanation embeddings simultaneously, and progressively introduce hard negative samples. Additionally, a ChatGPT-assisted BIRCH algorithm is designed for efficient clustering of a new ontology. Results: We established a clustering test set and a hard negative test set, where our model consistently achieves the highest F1 score. With CoRTEx embeddings and the modified BIRCH algorithm, we grouped 35 580 932 terms from the Biomedical Informatics Ontology System (BIOS) into 22 104 559 clusters with O(N) queries to ChatGPT. Case studies highlight the model’s efficacy in handling challenging samples, aided by information from explanations. Conclusion: By aligning terms to their explanations, CoRTEx demonstrates superior accuracy over benchmark models and robustness beyond its training set, and it is suitable for clustering terms for large-scale biomedical ontologies.

26 February 2026 in The Lancet Digital Health
Verified
Journal Article
Open access
HCHaichao Chen
Haichao Chen
ZZZhengyun Zhao
Zhengyun Zhao
SZSongchi Zhou
Songchi Zhou
SHShikai Hu
Shikai Hu
JWJinyuan Wang
Jinyuan Wang
TWTien Yin Wong
Tien Yin Wong
Rare diseases pose a substantial clinical and public health burden, with timely and accurate diagnoses remaining a formidable challenge in many countries and settings. Large language models (LLMs) have the potential to enhance the screening and diagnosis of rare diseases. However, existing evaluations of such capacities of LLMs are insufficient due to the low sample sizes, poor coverage of different rare diseases, and weak real-world clinical relevance. To address these issues, we developed an automated data collection pipeline, RareArena, to curate a comprehensive rare disease dataset from PubMed Central case reports. Two tasks were considered: rare disease screening (RDS), which involved rare disease recognition before confirmatory diagnostic tests; and rare disease confirmation (RDC), which required diagnosis with complete information. The constructed RDS task comprised 49 760 cases of 4597 rare diseases, whereas the RDC task comprised 22 901 cases of 3522 rare diseases. Human evaluations by two physicians across three dimensions-leakage, fidelity, and complexity-validated the high quality of our dataset. We systematically benchmarked ten state-of-the-art LLMs of varying sizes (GPT-4o, Llama3·1-70B, Llama3·1-8B, Qwen2·5-72B, Qwen2·5-7B, Gemma2-9B, Phi3-7B, Llama3-70B-UltraMedical, Llama3-8B-UltraMedical, and MedLlama-7B) and found that GPT-4o achieved the best performance in both the tasks (RDS: 33·1% top-1 recall, 56·9% top-5 recall; RDC: 64·2% top-1 recall, 85·9% top-5 recall). Additionally, GPT-4o performed better on genetically inherited diseases than on non-genetically inherited diseases in both the tasks, with its highest performance observed in systemic or rheumatologic diseases (RDS: 48·5% top-1 recall, 76·5% top-5 recall; RDC: 76·0% top-1 recall, 93·5% top-5 recall). To our knowledge, our dataset represents the largest rare disease diagnostic benchmark to date, featuring broad and deep disease coverage and reflecting clinically relevant scenarios. RareArena highlights the potential of LLMs in rare disease screening and diagnosis, providing a foundation for improved care for individuals with rare diseases around the world.

18 September 2021
Verified
Conference Paper
Closed access
SYShangqin Yang
Shangqin Yang
ZZZhengyun Zhao
Zhengyun Zhao
QYQingpeng Yang
Qingpeng Yang
JWJun Wang
Jun Wang
The sewer system plays an import role in our life, it is applied to collect and dispose domestic wastewater and rainwater. Regular inspection is necessary for the normal operation of the pipeline. Existing pipeline defect detection technologies are mostly based on manual inspection or supervised defect detection, which are time-consuming and laborious. In this paper, we propose a new weakly supervised attention guided image enhancement network for sewer pipeline defect detection. And, we establish a sewer pipelines dataset of 15 classes for weakly supervised learning. In our network, we use resnet-50 to generate the feature maps and attention maps of the images. Then the image enhancement module is designed to supplement details of the object. Finally, the original image and enhanced image will be used as input image onto training. The trained network can locate a variety of pipeline defects with highlight. Experimental result shows that our model performs better than other weakly supervised models on the particular pipe dataset.