Zeming Li

Zeming Li

Auto-generated profile, based on publicly available information

Zeming Li

Department of Computer Science, Hong Kong Baptist University, Hong Kong, China (Hong Kong)

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
26 September 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
XLXufei Luo
Xufei Luo
ZLZeming Li
Zeming Li
ZYZhenhua Yang
Zhenhua Yang
BWBingyi Wang
Bingyi Wang
YMYanfang Ma
Yanfang Ma
ZBZhaoxiang Bian
Zhaoxiang Bian
Background: Chatbots based on large language models (LLMs) have shown promise in evaluating the consistency of research. Previously, researchers used LLM to assess if randomized controlled trial (RCT) abstracts adhered to the CONSORT-Abstract guidelines. However, the consistency of artificial intelligence (AI) interventional RCTs aligning with the CONSORT-AI (Consolidated Standards of Reporting Trials-Artificial Intelligence) standards by LLMs remains unclear. Objective: The aim of this study is to identify the consistency of RCTs on AI interventions with CONSORT-AI using chatbots based on LLMs. Methods: This cross-sectional study employed 6 LLM models to assess the consistency of RCTs on AI interventions. The sample selection is based on articles published in JAMA Network Open, which included a total of 41 RCTs. All queries were submitted to LLMs through an application programming interface with a temperature setting of 0 to ensure deterministic responses. One researcher posed the questions to each model, while another independently verified the responses for validity before recording the results. The Overall Consistency Score (OCS), recall, inter-rater reliability, and consistency of contents were analyzed. Results: We found gpt-4‐0125-preview has the best average OCS on the basis of the results obtained by JAMA Network Open authors and by us (86.5%, 95% CI 82.5%‐90.5% and 81.6%, 95% CI 77.6%‐85.6%, respectively), followed by gpt-4‐1106-preview (80.3%, 95% CI 76.3%‐84.3% and 78.0%, 95% CI 74.0%‐82.0%, respectively). The model with the worst average OCS is gpt-3.5-turbo-0125 on the basis of the results obtained by JAMA Network Open authors and by us (61.9%, 95% CI 57.9%‐65.9% and 63.0%, 95% CI 59.0%‐67.0%, respectively). Among the 11 unique items of CONSORT-AI, Item 2 (“State the inclusion and exclusion criteria at the level of the input data”) received the poorest overall evaluation across the 6 models, with an average OCS of 48.8%. For other items, those with an average OCS greater than 80% across the 6 models included Items 1, 5, 8, and 9. Conclusions: GPT-4 variants demonstrate strong performance in assessing the consistency of RCTs with CONSORT-AI. Nonetheless, refining the prompts could enhance the precision and consistency of the outcomes. While AI tools like GPT-4 variants are valuable, they are not yet fully autonomous in addressing complex and nuanced tasks such as adherence to CONSORT-AI standards. Therefore, integrating AI with higher levels of human supervision and expertise will be crucial to ensuring more reliable and efficient evaluations, ultimately advancing the quality of medical research.

17 February 2025 in bioRxiv
Verified
Preprint
Open access
PDF file
ZLZeming Li
Zeming Li
XLXufei Luo
Xufei Luo
ZYZhenhua Yang
Zhenhua Yang
HZHuayu Zhang
Huayu Zhang
BWBingyi Wang
Bingyi Wang
TGthe ADVANCED working group
the ADVANCED working group
Importance Medical reporting guidelines are significant in improving the transparency, quality, and integrity of medical research, particularly in randomized clinical trials; adherence to these guidelines supports research interpretability and has direct implications for downstream applications, such as patient treatment. However, with over 600 distinct reporting guidelines, manual assessments are often time-consuming and labor-intensive. Objective To evaluate an automated reporting checklist generation tool using large language models and retrieval augmentation generation technology, called RAPID. Design, Setting, and Participants This study used large language models to design a retrieval augmentation generation architecture and collected published journal articles as training and validation sets to optimize prompts within the framework and comprehensively evaluate the performance of the framework. Medical reporting experiments were collected from 50 randomized controlled trials without the intervention of AI tools and 41 randomized controlled trials with the intervention of AI tools. Main Outcomes and Measures For effective evaluation of the performance of this tool, a classification accuracy metric (Reported/Not Reported) defined as the number of correct judgments divided by all judgments and a content consistent score metric defined as the number of contents retrieved by the tool that are the same as those retrieved by researchers divided by the total number of judgments were calculated. Results The RAPID tool uses the widely used Word document and Portable Document Format as an input file. Fifty published journal articles without the intervention of AI tools and 41 published journal articles with the intervention of AI tools were collected as CONSORT and CONSORT-AI datasets. All of the CONSORT reporting items (37) were included in the tool. RAPID achieved a high average accuracy rate of 92.11% and a content consistency score of 81.14% on the CONSORT dataset. Of the CONSORT-AI reporting items, 11 items related to the intervention of AI tools were included in the tool. RAPID achieved an average accuracy of 83.81% with a content consistency score of 72.51% on the CONSORT-AI dataset. For these two reporting guidelines, a training set of 5 articles was selected from each dataset to refine the prompts used in the tools for CONSORT and CONSORT-AI reporting checklist. The validation set of the remaining articles was used to assess the performance of the RAPID. The RAPID tool used the Word document and Portable Document Format of the articles as input files. A RAPID graphical user interface was built using JavaScript and Vue. Conclusions and Relevance The RAPID tool is designed to assist in the reporting of various types of trials. RAPID has strong scalability, which can be easily adapted to different medical reporting guidelines without transfer learning on a large dataset. RAPID may effectively save time and improve working efficiency for different user groups, for example, 1) simplifying the submission process and improving report quality by verifying manuscript completeness for medical authors; 2) facilitating evaluation of report quality for medical researchers; 3) expediting manuscript distribution for medical editors; and 4) identifying reporting deficiencies and providing deeper insights for review comments for reviewers. Question Can large language model tools automatically generate medical reporting checklists for manuscripts of different types of clinic trials? Findings An automated reporting checklist generation tool using large language models and retrieval augmentation generation technology, RAPID, was developed. RAPID was fully evaluated on all items across two separate datasets related to the Consolidated Standards of Reporting Trials (CONSORT) and CONSORT-AI reporting guidelines. In the first dataset corresponding to CONSORT, RAPID achieved an average accuracy of 92.11%, while in the second dataset associated with CONSORT - AI, it reached an average accuracy of 83.81%. Additionally, RAPID is highly scalable. It can be easily and smoothly adapted to different medical reporting guidelines without transfer learning on a large dataset. Meaning RAPID can effectively save time and improve working efficiency for different user groups such as medical authors, researchers, editors, and reviewers.

22 November 2024
Verified
Conference Paper
Open access
ZLZeming Li
Zeming Li
YXYu Xu
Yu Xu
DCDebajyoti Chowdhury
Debajyoti Chowdhury
HYHip Fung Yip
Hip Fung Yip
CWChonghao Wang
Chonghao Wang
LZLu Zhang
Lu Zhang
Predicting complex diseases using computational methods have rapidly evolved, which accelerates precision medicine, disease prevention, and so on. In past years, especially after emergence of genomics, major focus was inclined connecting genetic influence to complex diseases wherein many other essential factors such as environment, lifestyles, and so on were constantly neglected. In recent years, researchers have begun predicting disease risk scores by integrating genetic variants data and different lifestyle factors (alcohol intake, etc) and physical parameters (body mass index, age, etc). However, a potential missing link still exists there as most of those methods did not adequately address how to integrate the information from the medical history record that plays a crucial role in complex disease occurrence. In this paper, we have proposed Med-PRSIMD model that integrates genetic variants, lifestyle factors and medical history records to advance complex disease prediction. In this approach, we trained the Transformer model using causal language model pretraining task for extracting medical history records information. We have evaluated the prediction performance of our proposed Med-PRSIMD model on coronary artery disease, type 2 diabetes, and breast cancer patients' data obtained from the UK biobank. Med-PRSIMD achieved state-of-the-art performance compared to existing methods.