Natural language processing (NLP) is the embodiment of computer intelligence in acquiring knowledge, understanding, processing and expressing consciously and actively. It is the scientific key to promote the informatization of medical practice and research. This paper reviews the development history and research basis of NLP, and focuses on the current application of NLP and Large Language models in biomedicine and traditional Chinese medicine (TCM), including the intelligent reading, information extraction and feedback of medical texts and ancient books of TCM, as well as the construction of medical knowledge graph and question-answering system. NLP is the technical support to explore the treasure house of TCM, which is of great practical significance to further promote the development of efficient and high-quality core values of TCM and to improve the service capacity.
The inverse problem of electrical impedance tomography (EIT) is seriously ill-posed, which restricts the clinical application of EIT. Regularization is an important numerical method to improve the stability of the EIT inverse problem as well as the resolution of the imaging. This paper proposes a self-diagnosis regularization method based on Tikhonov regularization and diagonal weight regularization method (DWRM). Firstly, the ill-posedness of the inverse problem is analyzed by sensitivity. Then, the performance of the self-diagnosis regularization is analyzed through the singular value theory. Finally, some simulated experiments including simulations and flume experiment are carried out and verify that the self-diagnosis regularization has better image quality and anti-noise ability than those of traditional regularization methods. The self-diagnosis regularization method weakens the ill-posedness of inverse problem of EIT and can prompt the practical application of EIT.
The prominent feature and form of clinical diagnosis and treatment of traditional Chinese medicine is individualization, which has generated difficulty for clinical evaluation and has restricted the production of high-level evidence for traditional Chinese medicine for a long time. Based on the complexity and dynamics of individualized information under the characteristics of time and space, this paper references the theory of space-time of system science to analyze the individualized data of diagnosis and treatment of traditional Chinese medicine and summarizes the concept of the long time course for clinical evaluation. Based on the concept of the long time course, this paper starts with the origin of clinical evaluation, which is the construction of clinical problem elements named PICO, introduces dynamic evaluation factors, explores the construction of individualized dynamic evaluation method of traditional Chinese medicine, and provides demonstration and examples for the design and implementation of individualized clinical research in future.
It is crucial to select outcomes in clinical trials. Appropriate outcomes can improve value and significance of trials and reduce the cost of investment. This paper describes how to develop core outcome sets and core outcome measurement instrument sets with the theory of mixed methods research, so as to standardize the choice of outcomes and outcome measurement instruments in clinical trials.
This paper introduces the development and changes of clinical practice guidelines based on the enlightenment of the Reporting Items for Practice Guidelines in Health Care (RIGHT), and provides policy recommendations.
Master protocol is a great transformation of clinical trials with complete research network, reasonable design and innovative statistical analysis methods. It is a highly efficient new model of clinical trials which could obtain more medical information with less clinical resources. Clinical researches in the field of oncology using master protocol have already made delightful achievements. This paper introduces the design of clinical trials on angina pectoris of coronary heart disease, myocardial infarction and heart failure for instance and discusses the application of master protocol to clinical researches of Traditional Chinese Medicine combined with the differentiation of syndromes and treatments. We expect to provide new ideas and methods for the design of master protocol on diseases with similary syndrome pattern series of Traditional Chinese Medicine.
Core outcome set (COS) is an agreed and minimal set of outcomes that should be measured and reported in all clinical trials in specific areas of health or healthcare, which can reduce the heterogeneity of outcomes in similar clinical trials, so that much more trials can merge in systematic reviews. Meanwhile, using COS may be easy to identify potential selective reporting bias in clinical trials. The research of COS has been developed for more than 30 years in western countries. At present there are much more researchers focusing on this area in China. However the status and progress of COS remain unclear. This paper reviewed the quantity of COS, the disease distributions of COS, the geographical locations involved in the development of COS, as well as the methodological progress of COS, so as to clarify the general situation of COS.
The Core Outcome Measures in Effectiveness Trials (COMET) Working Group has published a series of research and reporting guidelines related to core outcome sets since it was established. This article introduces and interprets the Core Outcome Set-STAndardised Protocol Items: the COS-STAP Statement which is developed by the COMET and published in February 2019. It will then be compared with Core Outcome Set-STAndards for Reporting (COS-STAR) and Core Outcome Set-STAndards for Development (COS-STAD), which have been introduced to China. The significance of these guidelines for the development of core outcomes in the field of traditional Chinese medicine is discussed, so as tp draw researchers' attention to this area.
背景 随机对照临床试验的报告质量欠佳。当今，提高研究透明度至关重要，不充分的报告影响了对试验结果的可靠性和有效性的评估。临床试验报告的统一标准（Consolidated Standards of Reporting Trials，CONSORT）2010 声明是为提升随机对照临床试验的报告质量而制定的，但其最初关注的是两组平行对照试验。多臂试验常采用多个平行组设计方案，将试验者以相同概率随机分配至其中一个治疗组，比较多种干预措施的效应，但以三组或者更多的组别为常见。多臂试验的报告质量差异很大，使得对结果的判断和解释变得困难。尽管 CONSORT 2010 声明的大部分内容同样适用于多臂试验，但其中一些要素需要修改，并且在某些情况下还有额外的问题需要澄清。 目的 推出 CONSORT 2010 声明的多臂试验报告扩展版，以便于此类试验的报告。 设计 2014 年 CONSORT 工作组会议后，成立了一个包括所有作者的指南撰写工作组。工作组在 2014 年至 2018 年间，每两个月进行会面或电话会议，并通过电子邮件进行交流，讨论并制定了修订清单及其相关文本。草稿随后发给了包含 36 人的 CONSORT 工作组及另外 5 名在临床试验领域的知名专家，以供他们审阅。14 人提供了详细的反馈意见，工作组经过详细考虑，形成了扩展版的最终修订版。 结果 CONSORT 声明多臂试验扩展版，扩展了 CONSORT 2010 清单中的 10 个条目，并提供了良好的报告示例及对每个扩展条目重要性的详尽解释。核心要点是对多臂试验的明确定义，并要求清楚地报告涉及所有治疗组的目的和研究假设。应明确主要治疗方案的比较，并且作者应完整、透明地报告由各组得出的计划内和非计划内的比较。如果对多重性进行了统计校正，则应描述所使用的理由和方法。 结论和相关影响 CONSORT 2010 声明扩展版为多臂平行随机对照临床试验报告提供了具体指导，并有助于在此类试验报告中提供更高的透明度和准确性。
Since the concept of core outcome set (COS) was introduced into clinical trials of traditional Chinese medicine (TCM), researchers have paid much more attention to develop COS for specific diseases. Although researchers believe that the characteristics of TCM, such as syndromes, should be considered in the COS of TCM, it was insufficiently addressed. In addition, the naming of TCM syndromes has not been standardized, and the classification and diagnostic criteria for specific diseases have been inconsistent. Thus, it is difficult to include TCM syndromes in the COS. Different diseases may show similar TCM syndromes which makes research difficult. Based on previous studies, this paper provided methods of developing core TCM syndromes set according to the model of combination of disease and syndrome and the model of syndrome dominating disease to provide references for future researches.