Yaolong Chen’s research while affiliated with Lanzhou University and other places

Aim This study aimed to develop and evaluate an automated large language model (LLM)‐based system for assessing the quality of medical imaging guidelines and consensus (GACS) in different languages, focusing on enhancing evaluation efficiency, consistency, and reducing manual workload. Method We developed the QPC‐HASE‐GuidelineEval algorithm, which integrates a Four‐Quadrant Questions Classification Strategy and Hybrid Search Enhancement. The model was validated on 45 medical imaging guidelines (36 in Chinese and 9 in English) published in 2021 and 2022. Key evaluation metrics included consistency with expert assessments, hybrid search paragraph matching accuracy, information completeness, comparisons of different paragraph matching approaches, and cost‐time efficiency. Results The algorithm demonstrated an average accuracy of 77%, excelling in simpler tasks but showing lower accuracy (29%–40%) in complex evaluations, such as explanations and visual aids. The average accuracy rates of the English and Chinese versions of the GACS were 74% and 76%, respectively (p = 0.37). Hybrid search demonstrated superior performance with paragraph matching accuracy (4.42) and information completeness (4.42), significantly outperforming keyword‐based search (1.05/1.05) and sparse‐dense retrieval (4.26/3.63). The algorithm significantly reduced evaluation time to 8 min and 30 s per guideline and reduced costs to approximately 0.5 USD per guideline, offering a considerable advantage over traditional manual methods. Conclusion The QPC‐HASE‐GuidelineEval algorithm, powered by LLMs, showed strong potential for improving the efficiency, scalability, and multi‐language capability of guideline evaluations, though further enhancements are needed to handle more complex tasks that require deeper interpretation.

After the concept of living guidelines was proposed, the British Association of Dermatologists began to use this methodology and published two living guidelines related to Behçets and alopecia areata. We read these two guidelines with great interest, especially the methodological section; however, we found that there is still room for improvement in several aspects of transparency in their development.

Introduction: We define clinical practice guideline (CPGs) implementability as the characteristics of the guideline that reflect the extent to which it is likely to be adopted in clinical practice. Our objectives were to create a comprehensive and evidence-informed framework of guideline implementability (CFGI). Methods: A mixed-methods approach was used. Based on a systematic literature review of six databases as the foundation, the initial version of the CFGI was created, followed by external consultations to gather feedback and natural language processing tool-assisted classificationto refine the framework. To get external validation of the CFGI from expert feedback at an international conference Results: 15 studies related to guideline implementability were identified from the systematic literature review. The first version of CFGI was compiled, including 6 domains. Feedback on the first version was received from 16 stakeholders, including clinicians, nurses, medical managers, and guideline methodologists, combined with natural language processing tool-assisted classification. The final version of the CFGI is comprised of 6 core domains, containing 21 constructs: (1) Scope and purpose; (2) Clarity and consistency of recommendations; (3) Development and evidence base; (4) Structure and Contents; (5) Development team and transparency; and (6) Implementation environment and tools. Twenty-nine experts participated in the external validation, and the results showed that CFGI had good rationality, importance, clarity, feasibility, and necessity. Conclusions : The development of the CFGI provides a systematic theoretical basis for the development and implementation of future CPGs, which will help to enhance the implementability of guidelines and facilitate their promotion and application in different medical settings. Future research can further validate and apply the CFGI, explore its effectiveness and feasibility in actual operation.

Rheumatoid arthritis (RA) is an autoimmune disease with destructive arthritis as its main clinical manifestation, which is a major cause of disability. It is very important to formulate and update a guideline for the diagnosis and treatment of RA that adhere to international guideline development standards and can be applied to clinical practice in China. This guideline is endorsed and developed by the National Clinical Research Center for Dermatologic and Immunologic Diseases, collaborated with Rheumatologists Branch of Chinese Medical Doctor Association, Rheumatology Rehabilitation Branch of Chinese Association of Rehabilitation Medicine, Rheumatology Branch of Chinese Research Hospital Association, and Rheumatology Branch of Beijing Association of Holistic Integrative Medicine, based on grading of recommendations assessment, development and evaluation (GRADE) and reporting items for practice guidelines in healthcare (RIGHT). Evidence-based recommendation were developed for 10 clinical scenario that are most relevant to Chinese rheumatologists, aiming to improve and standardize the diagnosis and treatment of RA in China, which may finally improve the quality of life and prognosis of patients.

Background: Bacteraemia and sepsis have traditionally required continued intravenous (IV) antibiotics. Objectives: To evaluate if early transition to oral antibiotics is noninferior to continued IV antibiotic therapy in treating patients with bacteraemia and sepsis. Data sources: MEDLINE, Embase, Web of Science, the Cochrane library, and Wanfang databases from inception to July 13, 2024, along with clinical trial registries and Google.com. Study eligibility criteria: Randomised controlled trials (RCTs) and cohort studies. Participants: Patients with bacteraemia and sepsis. Interventions: Early transition to oral antibiotics versus continued IV antibiotics. Early oral switch was defined as 5-9 days for uncomplicated Staphylococcus aureus bacteraemia, <4 weeks for complicated Staphylococcus aureus bacteraemia, 3-7 days for uncomplicated Streptococcus bacteraemia, and 3-5 days for uncomplicated Enterobacterales bacteraemia. Assessment of risk of bias: Cochrane risk of bias tool and Newcastle-Ottawa Scale. Methods of data synthesis: Random-effects models were used to pool the data. The primary outcome was treatment failure. The non-inferiority margin for treatment failure was 10%. The GRADE approach was used to rate the certainty of the evidence. Results: In total, 38 studies (6 RCTs, 10 adjusted cohorts, and 22 unadjusted cohorts) involving 11,566 patients were included. A primary analysis of 6 RCTs and 10 adjusted cohorts comprised 7,102 patients. High-certainty evidence from six RCTs showed that early transition to oral antibiotics was noninferior to continued IV therapy for treatment failure (n=529; OR 0.89; 95% CI: 0.54 to 1.48). Low-certainty evidence from five adjusted cohorts also found no significant difference in treatment failure between the two groups (n=929; OR 0.60; 95% CI: 0.29 to 1.72). Moderate-certainty evidence showed that oral switch therapy significantly reduced hospital stay (n=2,041; mean difference: -5.19 days; 95% CI: -8.16 to -2.22). Conclusions: Early transition to oral antibiotics was noninferior to continued IV antibiotic treatment for bacteraemia and sepsis.

Introduction Clinical practice guidelines are essential tools for standardizing medical practices and improving healthcare quality. However, current guideline implementation is unsatisfactory. Barriers to guideline implementation include external environmental factors (e.g., medical personnel, medical institutions, local policies) and intrinsic characteristics (e.g., context, format, language etc.), with the latter being addressable by optimizing the guidelines themselves. This study aims to develop an appraisal tool to promote effective guideline implementation. Existing guideline implementability appraisal tools lack a clear theoretical basis, evidence of reliability and validity, and/or empirically-based guidance for effective implementation, all of which will be addressed in this study. Methods and analysis The research is divided into four phases: (1) Generating a theoretical framework for guideline implementability (i.e., scoping review and concept analysis method); (2) Conducting a factorial experiment (i.e., guideline users simulate the use of different guideline versions to examine the relationship between constructs in the framework and implementability), and removing constructs with weak relationships to form the final implementability theoretical framework; (3) Generating dimensions and items for the guideline implementability appraisal tool based on the constructs in the theoretical framework, conducting comprehensive reliability and validity testing, usability testing, and iterative optimization according to the COSMIN guidelines; (4) Integrating the validated tool with the STAR guideline rating system for guideline appraisal and feedback to promote guideline implementability. Strengths and limitations (1) Our research will follow a standardized and rigorous process for developing measurement scales, ensuring that the resulting evaluation scale for the implementability of CPGs is theoretically grounded, internally consistent between theory and practice, and reliable and valid. (2) The theoretical framework developed in our study will strengthen the validity and rationality of constructs in the real world. (3) In the confirmatory factor analysis, this study will determine the dimensions and items’ weight through factor loadings, allowing for the quantification of the implementability of CPGs and providing users of the guidelines with objective evaluative results. In addition, the clinical practice guideline implementability evaluation tool developed in this study can assist guideline developers in enhancing implementability before, during, and after guideline formulation.

Background Traditional medicine (TM) plays a significant role in healthcare either as part of the primary healthcare system or as an adjunct to conventional medicine. This study aimed to map systematic reviews (SRs) of TM modalities across health conditions and identify gaps in the research literature to facilitate priority setting in future TM research. Methods We searched 17 databases from January 2018 to December 2022. Reviewers in pairs independently performed the database search, screened each record for inclusion, extracted data, and performed quality assessments using the AMSTAR 2 - A Measurement Tool to Assess systematic Reviews. To be included in this evidence map, the studies had to be SRs of clinical studies that evaluated the effectiveness of a TM modalities. The included SRs were analyzed according to TM modality, ICD-11 disease classification, and health outcomes, and visualized using graphical plots. Results We retrieved 241,509 records. After excluding duplicate records, 181,616 titles and abstracts were screened and 20,856 records were selected for full-text assessment, of which 18,137 records were further excluded. The final 2719 included SRs were primarily in adults (2591) with only 128 SRs in the pediatric population. The most commonly evaluated health conditions were diseases of the digestive system, circulatory system, and genitourinary system, with herbal medicine (n = 1867) and acupuncture (n = 471) being the most investigated TM modalities in treating these illnesses. Based on AMSTAR 2 criteria, the methodology quality of the included SRs is considerably low. Conclusion This evidence map provides a comprehensive overview of the extent and nature of the available research onTM modalities across health conditions. It provides an initial step towards characterizing the global evidence base and outlining gaps in the existing evidence. We regard this study as laying the basis for future research of TM modalities. Registration The protocol of this map is registered in PROSPERO (CRD42023416355).

The development of intensive care medicine is inseparable from the diversified monitoring data. Intensive care medicine has been closely integrated with data since its birth. Critical care research requires an integrative approach that embraces the complexity of critical illness and the computational technology and algorithms that can make it possible. Considering the need of standardization of application of big data in intensive care, Intensive Care Medicine Branch of China Health Information and Health Care Big Data Society, Standard Committee has convened expert group, secretary group and the external audit expert group to formulate Chinese Experts’ Consensus on the Application of Intensive Care Big Data (2022). This consensus makes 29 recommendations on the following five parts: Concept of intensive care big data, Important scientific issues, Standards and principles of database, Methodology in solving big data problems, Clinical application and safety consideration of intensive care big data. The consensus group believes this consensus is the starting step of application big data in the field of intensive care. More explorations and big data based retrospective research should be carried out in order to enhance safety and reliability of big data based models of critical care field.