Xin Sun

Xin Sun

Auto-generated profile, based on publicly available information

Xin Sun

Clinical Research and Innovation Unit, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, 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
28 June 2024 in JMIR Medical Informatics
Verified
Journal Article
Open access
ZXZhongzhou Xiao
Zhongzhou Xiao
LLLU LU
LU LU
XPXinwei Peng
Xinwei Peng
JPJiali Pang
Jiali Pang
JDJinru Ding
Jinru Ding
SZShaoting Zhang
Shaoting Zhang
Background: Large language models (LLMs) have achieved great progress in natural language processing tasks and demonstrated the potential for use in clinical applications. Despite their capabilities, LLMs in the medical domain are prone to generating hallucinations (not fully reliable responses). Hallucinations in LLMs’ responses create substantial risks, potentially threatening patients’ physical safety. Thus, to perceive and prevent this safety risk, it is essential to evaluate LLMs in the medical domain and build a systematic evaluation. Objective: We developed a comprehensive evaluation system, MedGPTEval, composed of criteria, medical data sets in Chinese, and publicly available benchmarks. Methods: First, a set of evaluation criteria was designed based on a comprehensive literature review. Second, existing candidate criteria were optimized by using a Delphi method with 5 experts in medicine and engineering. Third, 3 clinical experts designed medical data sets to interact with LLMs. Finally, benchmarking experiments were conducted on the data sets. The responses generated by chatbots based on LLMs were recorded for blind evaluations by 5 licensed medical experts. The evaluation criteria that were obtained covered medical professional capabilities, social comprehensive capabilities, contextual capabilities, and computational robustness, with 16 detailed indicators. The medical data sets include 27 medical dialogues and 7 case reports in Chinese. Three chatbots were evaluated: ChatGPT by OpenAI; ERNIE Bot by Baidu, Inc; and Doctor PuJiang (Dr PJ) by Shanghai Artificial Intelligence Laboratory. Results: Dr PJ outperformed ChatGPT and ERNIE Bot in the multiple-turn medical dialogues and case report scenarios. Dr PJ also outperformed ChatGPT in the semantic consistency rate and complete error rate category, indicating better robustness. However, Dr PJ had slightly lower scores in medical professional capabilities compared with ChatGPT in the multiple-turn dialogue scenario. Conclusions: MedGPTEval provides comprehensive criteria to evaluate chatbots by LLMs in the medical domain, open-source data sets, and benchmarks assessing 3 LLMs. Experimental results demonstrate that Dr PJ outperforms ChatGPT and ERNIE Bot in social and professional contexts. Therefore, such an assessment system can be easily adopted by researchers in this community to augment an open-source data set.

30 October 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
LYLingrui Yang
Lingrui Yang
JPJiali Pang
Jiali Pang
SZSong Zuo
Song Zuo
JXJian Xu
Jian Xu
WJWei Jin
Wei Jin
XSXin Sun
Xin Sun
Background: Although new technologies have increased the efficiency and convenience of medical care, patients still struggle to identify specialized outpatient departments in Chinese tertiary hospitals due to a lack of medical knowledge. Objective: The objective of our study was to develop a precise and subdividable outpatient triage system to improve the experiences and convenience of patient care. Methods: We collected 395,790 electronic medical records (EMRs) and 500 medical dialogue groups. The EMRs were divided into 3 data sets to design and train the triage model (n=387,876, 98%) and test (n=3957, 1%) and validate (n=3957, 1%) it. The triage system was altered based on the current BERT (Bidirectional Encoder Representations from Transformers) framework and evaluated by recommendation accuracies in Xinhua Hospital using the cancellation rates in 2021 and 2022, from October 29 to December 5. Finally, a prospective observational study containing 306 samples was conducted to compare the system’s performance with that of triage nurses, which was evaluated by calculating precision, accuracy, recall of the top 3 recommended departments (recall@3), and time consumption. Results: With 3957 (1%) records each, the testing and validation data sets achieved an accuracy of 0.8945 and 0.8941, respectively. Implemented in Xinhua Hospital, our triage system could accurately recommend 79 subspecialty departments and reduce the number of registration cancellations from 16,037 (3.83%) of the total 418,714 to 15,338 (3.53%) of the total 434200 (P<.05). In comparison to the triage system, the performance of the triage nurses was more accurate (0.9803 vs 0.9153) and precise (0.9213 vs 0.9049) since the system could identify subspecialty departments, whereas triage nurses or even general physicians can only recommend main departments. In addition, our triage system significantly outperformed triage nurses in recall@3 (0.6230 vs 0.5266; P<.001) and time consumption (10.11 vs 14.33 seconds; P<.001). Conclusions: The triage system demonstrates high accuracy in outpatient triage of all departments and excels in subspecialty department recommendations, which could decrease the cancellation rate and time consumption. It also improves the efficiency and convenience of clinical care to fulfill better the usage of medical resources, expand hospital effectiveness, and improve patient satisfaction in Chinese tertiary hospitals.

24 December 2024 in The Lancet Digital Health
Verified
Journal Article
Open access
JSJing Sun
Jing Sun
TFTienan Feng
Tienan Feng
BWBo Wang
Bo Wang
FLFen Li
Fen Li
BHBo Han
Bo Han
KSKun Sun
Kun Sun
Perimembranous ventricular septal defect (PMVSD) is a prevalent congenital heart disease, presenting challenges in predicting spontaneous closure, which is crucial for therapeutic decisions. Existing models mainly rely on structured echocardiographic parameters or restricted data. This study introduces an artificial intelligence (AI)-based model, which uses natural language processing (NLP) and machine learning with the aim of improving spontaneous closure predictability in PMVSD. We did a multicentre, retrospective analysis using data from 29 142 PMVSD patients across six tertiary centres in China from May, 2004, to September, 2022, for training (70%) and validation (30%; dataset 1, 27 269 patients), and from September, 2001, to December, 2009 for testing (dataset 2, 1873 patients). NLP extracted structured data from echocardiography reports and medical records, which were used to develop machine learning models. Models were evaluated for spontaneous closure occurrence and timing by use of area under the receiver operating characteristic curve (AUC), decision curve analysis, and calibration index. Spontaneous closure occurred in 3520 patients (12·1%) at a median of 31 months (IQR 16-56). Eleven NLP-derived predictors, identified via least absolute shrinkage and selection operator, highlighted the importance of defect morphology and patient age. The random survival forest algorithm, selected for its superior concordance indexes, showed excellent predictive performance with validation set AUCs (95% CI) of 0·95 (0·94-0·96) for 1-year and 3-year predictions, and 0·95 (0·95-0·96) for 5-year predictions; testing set AUCs were 0·95 (0·94-0·97) for 1-year predictions, 0·97 (0·96-0·98) for 3-year predictions, and 0·98 (0·97-0·99) for 5-year predictions. The model showed high clinical utility through decision curve analysis, calibration, and risk stratification, maintaining consistent accuracy across centres and subgroups. This AI-based model for predicting spontaneous closure in PMVSD patients represents a substantial advancement, potentially improving patient management, reducing risks of delayed or inappropriate treatment, and enhancing clinical outcomes. National Natural Science Foundation of China, Shanghai Municipal Hospital Clinical Technology Project, Shanghai Municipal Health Commission, and Clinical Research Unit of XinHua Hospital.

27 January 2026 in Journal of Medical Internet Research
Verified
Journal Article
Open access
CSChao Sun
Chao Sun
GCGuangyu Chen
Guangyu Chen
CSCuicui Shi
Cuicui Shi
HCHaixia Cao
Haixia Cao
RYRuixu Yang
Ruixu Yang
JFJian-Gao Fan
Jian-Gao Fan
Background: For patients with metabolic dysfunction–associated fatty liver disease (MAFLD), weight loss is advised but challenging in practice. In China, there is a pronounced shortage of tailored digital lifestyle interventions for this population. Objective: This study aimed to assess the effects of a WeChat mini-program-delivered lifestyle intervention on weight loss and hepatic steatosis among individuals with MAFLD who were overweight or obese. Methods: Adults who are overweight or obese and have clinically diagnosed MAFLD with transient elastography examination were enrolled in this prospective randomized controlled trial. Patients were randomly assigned to receive either WeChat mini-program management (intervention group) or standard care (control group) at a 1:1 ratio. The intervention was structured around the development and implementation of personalized diet and exercise plans, supplemented by guided exercise video courses and reinforced through continuous monitoring and informational support. Body weight and clinical parameters were assessed at baseline and then at 6 months. Results: A total of 89 patients met the inclusion criteria and were randomly assigned to the intervention group (n=45) or control group (n=44). Among the 89 patients with MAFLD, 60% (27/45) of them achieved a eight loss of ≥5%, and 24.4% (11/45) of them had a weight loss of ≥10% in the intervention group, which was greater than those in the control group (27/45 vs 7/44; relative risk [RR] 3.771, 95% CI 1.836‐7.748; P <.001; 11/45 vs 3/44, RR 3.585, 95% CI 1.072‐11.988; P =.02). Importantly, patients receiving the intervention were significantly more likely to achieve a ≥10% reduction or normalization of controlled attenuation parameter (CAP) than those in the control group (26/45 vs 14/44; RR 1.816, 95% CI 1.102‐2.992; P =.01). After adjusting for key baseline covariates, multivariate analysis confirmed the intervention’s positive effect on achieving a weight loss of ≥5% (OR [odds ratio] 8.380, 95% CI 2.886‐24.331; P <.001) of ≥10% (OR 4.612, 95% CI 1.138‐18.686; P =.03), as well as on CAP reduction of ≥10 % or normalization (OR 2.853, 95% CI 1.092‐7.456; P =.03). In parallel, the intervention group presented greater reductions in liver enzymes (alanine aminotransferase, aspartate aminotransferase, and γ-glutamyl transpeptidase) and metabolic parameters (fasting insulin, h emoglobin A 1c , and triglyceride) than the control group (all P <.05). According to the fibrosis assessment, only the FibroScan-aspartate aminotransferase score decreased more in the intervention group than in the control group (median difference −0.06, 95% CI −0.13 to −0.01; P =.02), as compared to other non-invasive indicators. Conclusions: Readily scalable in primary care and varied-resource settings, our WeChat mini-program-based intervention extends beyond weight loss to reduce hepatic steatosis and improve metabolic parameters, thereby addressing the critical gap in targeted MAFLD management in China with a low-cost model for high-burden populations. Nevertheless, larger future studies are needed to confirm these findings with greater precision and assess long-term sustainability.

19 September 2025
Verified
Book Chapter
Open access
PDF file
LYLingrui Yang
Lingrui Yang
YZYize Zhao
Yize Zhao
YTYajiao Tan
Yajiao Tan
SZSong Zuo
Song Zuo
XSXin Sun
Xin Sun
In this chapter, children’s proactive health is explored within the framework of telemedicine and telehealth, utilizing new technologies such as artificial intelligence (AI)/Large Language Models (LLMs), Internet of Things (IoT), 5G, augmented reality (AR)/virtual reality (VR), and big data to create a full-cycle health management system for children. Proactive health starts at home, with roots in lifestyle medicine and early childhood comprehensive development. In addition to creating the Children’s Proactive Health Index, the Xinhua Hospital project team constructed a child health portrait based on the Index, where wearables with Internet of Things capabilities continuously track parameters like nutrition, sleep patterns, and physical activity. Dynamic health profiles are produced using real-time data, allowing for timely risk alarms, individualized prevention, and early anomaly identification. Caregivers can use Intelligent Digital General Practitioner—guided home-based treatments to address health issues. These interventions offer personalized guidance for child care, diseases and lifestyle changes. Internet hospitals fulfill the essential approach for telemedicine. An effective intelligent triage system refers caregivers to the right medical specialists, either in person or online, for cases that need professional attention. Online consultations that can assist with smart pre-consultation, facilitate diagnosis, incorporate digital therapies provide prescription administration, and permit remote follow-ups, may guarantee smooth continuity of healthcare services for the patient. Bridging the gap between prevention and treatment, in an integrated approach, creates a new paradigm for the management and intervention of children’s health by optimizing pediatric health outcomes through proactive, technology-driven care.

18 April 2025 in JMIR Preprints
Verified
Preprint
Open access
CSChao Sun
Chao Sun
GCGuangyu Chen
Guangyu Chen
CSCuicui Shi
Cuicui Shi
HCHaixia Cao
Haixia Cao
RYRuixu Yang
Ruixu Yang
JFJian-Gao Fan
Jian-Gao Fan
BACKGROUND Weight loss is the standard recommendation for patients with metabolic dysfunction-associated fatty liver disease (MAFLD), but its successful implementation is difficult in practice. Digital lifestyle interventions may provide an efficient and scalable solution to enhance patient self-management. OBJECTIVE This study aimed to assess the effects of a WeChat mini-program-delivered lifestyle intervention on weight loss and hepatic steatosis among overweight or obese individuals with MAFLD METHODS Overweight or obese adults with clinically diagnosed MAFLD with transient elastography examination were enrolled in this prospective randomized controlled trial. Patients were randomly assigned to receive either WeChat mini-program management (intervention group) or standard care (control group) at a 1:1 ratio. Body weight and clinical parameters were assessed at baseline and then at 6 months. RESULTS Among the 89 included MAFLD patients, 60.0% achieved ≥5% weight loss, and 24.4% had ≥10% weight loss in the intervention group, which were greater than those in the control group (P <0.05). Importantly, patients receiving the intervention were significantly more likely to achieve a ≥10% controlled attenuation parameter (CAP)reduction or CAP normalization than those in the control group were (57.8% vs. 31.8%, P <0.05). In parallel, the intervention group presented greater reductions in liver enzymes (ALT, AST, and GGT) and metabolic parameters (fasting insulin, HbA1c, TG, and HDL-C) than the control group (P <0.05). According to the fibrosis assessment, only the FibroScan-aspartate aminotransferase (FAST) score decreased more in the intervention group than in the control group (P 0.05). CONCLUSIONS Digital lifestyle coaching via a WeChat mini-program demonstrates efficacy in enhancing weight reduction, improving hepatic steatosis, and ameliorating metabolic disorders, offering novel perspectives regarding the practicality and therapeutic value of digital tools in managing MAFLD through behavioral interventions. CLINICALTRIAL Chinese Clinical Trial Registry ChiCTR2500100197; https://www.chictr.org.cn/