XWXintong Wu

Xintong Wu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xintong Wu has a total of 18 co-authors. Here are the top co-authors by number of shared publications:

  • Jing Yuan

    Department of Neurology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100006, China

    2 shared publications
  • Shengkang Huang

    Chinese Academy of Medical Sciences and Peking Union Medical College

    2 shared publications
  • Wei Zhao

    Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100037, China

    2 shared publications
  • Xiaoyuan Gao

    2 shared publications
  • Xu-Yao Zhang

    State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China

    2 shared publications
  • Yang Wang

    Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China

    2 shared publications

Latest Publications

  • Open Access

    Automated Brief Hospital Course Summarization in Cardiac Surgery Using a Lightweight Large Language Model–Based Framework: Development and Evaluation Study on the Medical Information Mart for Intensive Care-IV

    by Xiaoyuan Gao, Yang Wang, Zixing Wang, Jing Yuan, Shengkang Huang, Xu-Yao Zhang, Zhaohong Sun, Yun Xing, Yiyang Liu, Xintong Wu, et al.

    Background: Physician documentation requirements are a known contributor to clinician burnout, with the manual creation of brief hospital course (BHC) summaries being particularly time-consuming. Automating BHC summarization may mitigate this workload and reduce documentation errors. However, current natural language processing (NLP) methods are often limited to single-document inputs, and large language models (LLMs) face privacy and deployment challenges. Furthermore, existing methods often require manual information extraction and struggle to maintain temporal accuracy. Objective: We developed and evaluated LiteMedDoc, a lightweight, locally deployable LLM-based framework to automatically generate BHC summaries without model fine-tuning. Our objective was to determine whether clinically useful clinical summaries could be generated under strict privacy and resource constraints, making automated summarization feasible in real-world hospital environments. Methods: LiteMedDoc is a modular pipeline built upon an 8-billion-parameter open-source LLM (Llama 3.1). It features 3 specialized modules: a static dynamic information hierarchy module to condense multisource inputs and structure clinical events chronologically; a similar document retrieval-augmented generation module that retrieves contextually relevant prior case summaries; and a self-adaptive feedback optimization module used offline for prompt optimization. All processing was performed locally without any model fine-tuning. We evaluated the framework on a retrospective cohort of 4538 coronary artery bypass grafting (CABG) surgery cases from the Medical Information Mart for Intensive Care (MIMIC)-IV database. A held-out test set of 403 cases was used to generate BHC summaries. The model-generated summaries were compared to reference BHCs using 8 standard NLP metrics covering lexical overlap (BLEU-4 [Bilingual Evaluation Understudy-4 gram] and ROUGE [Recall-Oriented Understudy for Gisting Evaluation]), semantic similarity (BERTScore and METEOR [Metric for Evaluation of Translation With Explicit Ordering]), and clinical relevance (AlignScore [Alignment Score] and MEDCON [Medical Concept Overlap]). Additionally, 15 cardiac surgeons conducted a clinical evaluation of a sample of model-generated summaries, rating them on completeness, correctness, readability, conciseness, and global quality using a 5-point Likert scale. Results: Without any model training, LiteMedDoc achieved strong performance across individual automated metrics, nearly matching a fine-tuned model and exceeding a 70-billion-parameter model on all metrics. Additionally, in a within-database cross-domain evaluation on lobectomy cases, the framework maintained encouraging performance after prompt adaptation and outperformed both the base model and the CABG-fine-tuned model. Surgeons rated the AI-generated summaries above the prespecified acceptability threshold across all domains (mean scores ≥3.0), specifically praising their structure and conciseness. Conclusions: By integrating 3 specialized modules, the proposed framework offers a practical, locally deployable solution for clinician-in-the-loop BHC draft generation under privacy and resource constraints, and holds promise for improving documentation efficiency and enhancing information continuity during care transitions.

  • Open Access

    Automated Brief Hospital Course Summarization in Cardiac Surgery Using a Lightweight Large Language Model–Based Framework: Development and Evaluation Study on the Medical Information Mart for Intensive Care-IV (Preprint)

    by Xiaoyuan Gao, Yang Wang, Zixing Wang, Jing Yuan, Shengkang Huang, Xu-Yao Zhang, Zhaohong Sun, Yun Xing, Yiyang Liu, Xintong Wu, et al.

    BACKGROUND Physician documentation requirements are a known contributor to clinician burnout, with the manual creation of brief hospital course (BHC) summaries being particularly time-consuming. Automating BHC summarization may mitigate this workload and reduce documentation errors. However, current natural language processing (NLP) methods are often limited to single-document inputs, and large language models (LLMs) face privacy and deployment challenges. Furthermore, existing methods often require manual information extraction and struggle to maintain temporal accuracy. OBJECTIVE We developed and evaluated LiteMedDoc, a lightweight, locally deployable LLM-based framework to automatically generate BHC summaries without model fine-tuning. Our objective was to determine whether clinically useful clinical summaries could be generated under strict privacy and resource constraints, making automated summarization feasible in real-world hospital environments. METHODS LiteMedDoc is a modular pipeline built upon an 8-billion-parameter open-source LLM (Llama 3.1). It features 3 specialized modules: a static dynamic information hierarchy module to condense multisource inputs and structure clinical events chronologically; a similar document retrieval-augmented generation module that retrieves contextually relevant prior case summaries; and a self-adaptive feedback optimization module used offline for prompt optimization. All processing was performed locally without any model fine-tuning. We evaluated the framework on a retrospective cohort of 4538 coronary artery bypass grafting (CABG) surgery cases from the Medical Information Mart for Intensive Care (MIMIC)-IV database. A held-out test set of 403 cases was used to generate BHC summaries. The model-generated summaries were compared to reference BHCs using 8 standard NLP metrics covering lexical overlap (BLEU-4 [Bilingual Evaluation Understudy-4 gram] and ROUGE [Recall-Oriented Understudy for Gisting Evaluation]), semantic similarity (BERTScore and METEOR [Metric for Evaluation of Translation With Explicit Ordering]), and clinical relevance (AlignScore [Alignment Score] and MEDCON [Medical Concept Overlap]). Additionally, 15 cardiac surgeons conducted a clinical evaluation of a sample of model-generated summaries, rating them on completeness, correctness, readability, conciseness, and global quality using a 5-point Likert scale. RESULTS Without any model training, LiteMedDoc achieved strong performance across individual automated metrics, nearly matching a fine-tuned model and exceeding a 70-billion-parameter model on all metrics. Additionally, in a within-database cross-domain evaluation on lobectomy cases, the framework maintained encouraging performance after prompt adaptation and outperformed both the base model and the CABG-fine-tuned model. Surgeons rated the AI-generated summaries above the prespecified acceptability threshold across all domains (mean scores ≥3.0), specifically praising their structure and conciseness. CONCLUSIONS By integrating 3 specialized modules, the proposed framework offers a practical, locally deployable solution for clinician-in-the-loop BHC draft generation under privacy and resource constraints, and holds promise for improving documentation efficiency and enhancing information continuity during care transitions.

  • Open Access

    Open Curvature Scale Space Matching for Coronary Artery Identification in X-Ray Angiographic Images

    by Ruoxiu Xiao, Jiayu Wang, Xiaoyu Guo, Cheng Chen, Kangneng Zhou, Xintong Wu, Ping Liang, Jian Yang

    Identification of the coronary artery in sequence angiograms is an important issue in the analysis and treatment of coronary angiography data, due to the ambiguities in the coronary vessels resulting from cardiac motion and the differences in the projection angles in angiograms. In this paper, we propose a novel coronary artery identification method based on curvature scale space image matching. First, points on the centerline of each coronary artery branch are convolved with Gaussian kernel functions of different scales to obtain the corresponding curvature scale space (CSS) image during the curve evolution. Then, a CSS image matching method for open curves, which uses a combination of open feature vectors and closed feature vectors, is proposed. Finally, curve matching transitivity is used to solve the problem of the inability to recognize the coronary artery when the difference in the imaging angles is too large. The experimental results demonstrate that the proposed method can recognize every coronary artery in different views, even when the difference in the imaging angles is 29.8°.