Comparing Radiomics features of tumour and healthy liver tissue in a limited CT dataset: A machine learning study

IntroductionLiver cancer lesions on Computed Tomography (CT) withholds a great amount of data, which is not visible to the radiologists and radiographer. Radiomics features can be extracted from the lesions and used to train Machine Learning (ML) algorithms to predict between tumour and liver tissue. The purpose of this study was to investigate and classify Radiomics features extracted from liver tumours and normal liver tissue in a limited CT dataset.MethodsThe Liver Tumour Segmentation Benchmark (LiTS) dataset consisting of 131 CT scans of the liver with segmentations of tumour tissue and healthy liver was used to extract Radiomic features. Extracted Radiomic features included size, shape, and location extracted with morphological and statistical techniques according to the International Symposium on Biomedical Imaging manual. Relevant features was selected with chi2 correlation and principal component analysis (PCA) with tumour and healthy liver tissue as outcome according to a consensus between three experienced radiologists. Logistic regression, random forest and support vector machine was used to train and validate the dataset with a 10-fold cross-validation method and the Grid Search as hyper-parameter tuning. Performance was evaluated with sensitivity, specificity and accuracy.ResultsThe performance of the ML algorithms achieved sensitivities, specificities and accuracy ranging from 96.30% (95% CI: 81.03%–99.91%) to 100.00% (95% CI: 86.77%–100.00%), 91.30% (95% CI: 71.96%–98.93%) to 100.00% (95% CI: 83.89%–100.00%)and 94.00% (95% CI: 83.45%–98.75%) to 100.00% (95% CI: 92.45%–100.00%), respectively.ConclusionML algorithms classifies Radiomics features extracted from healthy liver and tumour tissue with perfect accuracy. The Radiomics signature allows for a prognostic biomarker for hepatic tumour screening on liver CT.Implications for practiceDifferentiation between tumour and liver tissue with Radiomics ML algorithms have the potential to increase the diagnostic accuracy, assist in the decision-making of supplementary multiphasic enhanced medical imaging, as well as for developing novel prognostic biomarkers for liver cancer patients.     

益气活血法联合西药治疗肺纤维化疗效及安全性Meta分析＊

目的 系统评价益气活血法联合西药治疗特发性肺纤维化（idiopathic pulmonary fibrosis，IPF）的疗效及安全性。方法 系统检索中国知网、维普网、万方数据库、EMbase、PubMed、Cochrane Library图书馆等数据库，检索时限从数据库建库至2021年1月，纳入益气活血法联合西药治疗特发性肺纤维化的随机对照试验（randomized controlled trial，RCT），由2名研究人员独立筛选并交叉核对纳入结果，提取有效数据后，应用RevMan 5.3软件进行Meta分析。结果 纳入16项随机对照试验共计1160例IPF患者。分析结果显示益气活血法联合西药组可提高临床总有效率（OR= 3.71，95% CI ［2.68，5.14］，P<0.00001）；改善患者肺功能：用力肺活量（MD=0.31，95% CI ［0.23，0.38］，P<0.00001）（MD=3.59，95% CI ［1.51，5.66］，P=0.0007），一氧化碳弥散量（MD=2.54，95% CI ［1.83，3.25］，P<0.00001）；提高生活质量，降低圣乔治评分：呼吸困难（MD=-12.70，95% CI ［-21.07，-4.32］，P=0.003），活动能力（MD=-8.38，95% CI ［-13.66，-3.10］，P=0.002），疾病影响（MD=-13.87，95% CI ［-22.53，-5.22］，P=0.002）；并可降低患者中医症状积分：喘息（MD=-0.66，95% CI ［-0.84，-0.49］，P<0.00001），咳嗽（MD=-0.71，95% CI ［-1.04，-0.37］，P<0.0001）；有效提高动脉血氧分压（MD=5.92，95% CI ［4.61，7.22］，P<0.00001）；且不增加不良事件发生率（OR=0.55，95% CI ［0.27，1.14］，P=0.11）。结论 益气活血法联合西药治疗IPF可提高临床治疗有效率，改善患者生活质量，且不增加临床不良事件（便秘、嗜睡、口干、恶心呕吐、皮肤瘙痒、腹泻等）发生率。但本研究纳入文献质量参差不齐，仍需更多大样本、高质量、多中心的RCT试验验证结论。     

基于CiteSpace可视化分析代谢组学在中医药领域的研究现状及趋势＊

目的 应用可视化方法分析代谢组学在中医药领域的现状及趋势。方法 检索中国知网数据库（CNKI）和Web of Science 核心合集数据库2021年3月15日之前收录的中医药领域代谢组学研究的相关文献，应用CiteSpace软件对纳入的文献进行关键词、作者、研究机构等内容进行可视化分析。结果 共纳入中文文献247篇，英文文献350篇。文献数量在波动中迅速上升。中、英文文献作者合作网络显示，张爱华是中医药领域代谢组学研究发文量最多的作者，并形成了核心研究团队。发文机构显示，中国医学科学院是该领域的重要研究机构，机构间合作紧密。中、英文文献关键词分析显示，研究内容主要集中在核磁共振、代谢标记物、冠心病、质谱技术、代谢通路等相关领域。结论 中医药领域代谢组学研究的热点主要为中医药治疗代谢性疾病的机制研究。研究趋势为卵泡代谢组学研究及中药有效成分的研究。     

Comprehensive interrogation of gene lists from genome-scale cancer screens with oncoEnrichR

Genome-scale screening experiments in cancer produce long lists of candidate genes that require extensive interpretation for biological insight and prioritization for follow-up studies. Interrogation of gene lists frequently represents a significant and time-consuming undertaking, in which experimental biologists typically combine results from a variety of bioinformatics resources in an attempt to portray and understand cancer relevance. As a means to simplify and strengthen the support for this endeavor, we have developed oncoEnrichR, a flexible bioinformatics tool that allows cancer researchers to comprehensively interrogate a given gene list along multiple facets of cancer relevance. oncoEnrichR differs from general gene set analysis frameworks through the integration of an extensive set of prior knowledge specifically relevant for cancer, including ranked gene-tumor type associations, literature-supported proto-oncogene and tumor suppressor gene annotations, target druggability data, regulatory interactions, synthetic lethality predictions, as well as prognostic associations, gene aberrations and co-expression patterns across tumor types. The software produces a structured and user-friendly analysis report as its main output, where versions of all underlying data resources are explicitly logged, the latter being a critical component for reproducible science. We demonstrate the usefulness of oncoEnrichR through interrogation of two candidate lists from proteomic and CRISPR screens. oncoEnrichR is freely available as a web-based service hosted by the Galaxy platform ( https://oncotools.elixir.no ), and can also be accessed as a stand-alone R package ( https://github.com/sigven/oncoEnrichR ).     

Glycaemic control for patients with severe acute brain injury: Protocol for a systematic review

Background

Hyperglycaemia is common in patients with acute brain injury admitted to an intensive care unit (ICU). Many studies have found associations between development of hyperglycaemia and increased mortality in hospitalised patients. However, the optimal target for blood glucose control is unknown. We want to conduct a systematic review with meta-analysis and trial sequential analysis to explore the beneficial and harmful effects of restrictive versus liberal glucose control on patient outcomes in adults with severe acute brain injury.

Methods

We will systematically search medical databases including CENTRAL, Embase, MEDLINE and trial registries. We will search the following websites for ongoing or unpublished trials: http://www.controlled-trials.com/ , http://www.clinicaltrials.gov/ , www.eudraCT.com , http://centerwatch.com/ , The Cochrane Library's CENTRAL, PubMed, EMBASE, Science Citation Index Expanded and CINAHL. Two authors will independently review and select trials and extract data. We will include randomised trials comparing levels of glucose control in our analyses and observational studies will be included to address potential harms. The primary outcomes are defined as all-cause mortality, functional outcome and health-related quality of life. Secondary outcomes include serious adverse events including hypoglycaemia, length of ICU stay and duration of mechanical ventilation, and explorative outcomes including intracranial pressure and infection. Trial Sequential Analysis will be used to investigate the risk of type I error due to repetitive testing and to further explore imprecision. Quality of trials will be evaluated using the Cochrane Risk of Bias tool, and quality of evidence will be assessed using the Grading of Recommendations, Assessment, Development and Evaluations (GRADE) approach.

Discussion

The results of the systematic review will be disseminated through peer-reviewed publication. With the review, we hope to inform future randomised clinical trials and improve clinical practice.     

补充与替代疗法治疗肠易激综合征的研究进展

肠易激综合征是临床常见的功能性胃肠病之一。由于多数患者的症状经过一线药物治疗后仍不能得到较好改善，许多患者为获得更好的治疗效果，转向选择补充与替代疗法进行治疗。然而，由于研究质量和数量的限制，大部分治疗肠易激综合征的补充与替代疗法并未被相关共识和指南所推荐。本文从补充与替代疗法的分类入手，从天然产品、身心治疗、传统医药3个方面就目前国内外常用的补充与替代疗法治疗肠易激综合征的研究进行概述，以期为临床工作者和患者更好地了解和应用提供帮助。     

基于CiteSpace的结直肠癌患者生命质量研究

目的：通过中英文文献了解结直肠癌患者生命质量研究现状及发展趋势。方法：运用CiteSpace对中国知网（CNKI）、万方数据知识服务平台、中国生物医学文献数据库、Web of Science核心数据集、PubMed、Cochrane Library中收录的关于结直肠癌患者生命质量研究的中英文文献进行可视化分析。结果：检索得到中文文献1 285篇，英文文献871篇，中英文文献发文量均呈上升趋势，相关研究关注的重点主要是结直肠癌患者造口、抑郁、免疫、肠道功能、化疗及化疗药物，但机构之间、学者之间合作程度及研究类型等方面存在一定差异。结论：中文文献相关研究起步晚、发展快，但在研究质量与研究深度等方面与英文文献相比还有一定差距；国内学者之间、机构之间应加强合作，关心患者肠道功能、心理状况，提高患者体力活动水平，开展更多高质量研究。     

A fully automated sex estimation for proximal femur X-ray images through deep learning detection and classification

PurposeTo develop a fully automated deep learning pipeline using digital radiographs to detect the proximal femur region for accurate automated sex estimation.MethodRadiograph predictive features from 2122 Chinese Han clinical pelvic with ages ranging from 18 to 26 years were collected retrospectively to train and test the sex prediction model using deep machine learning’s convolutional neural networks (CNN). Model performance was assessed using a Chinese Han population with 361 samples and a white population with 50 samples. The average accuracy of the sex estimation of the two test datasets was determined.ResultsFor the Chinese Han population test dataset, the sex estimation accuracy was 94.6% (males: 93.9% and females: 94.7%). For the white population samples, the accuracy of sex estimation was 82.9% (males: 80.9% and females: 88.6%). The accuracy of CNN tested in the Chinese population was significantly higher than that tested in the White population (p < 0.001)ConclusionsThe model based on convolutional neural networks has an accuracy similar to that of current state-of-the-art mathematical functions using manually extracted features for the Chinese Han population samples, proving to be a reliable choice for the human sex estimation.     

从环境隐喻的角度看外感病的因机证治＊

外感病是感受六淫、疫毒等外界因素引起的疾病，现代医学认为其主要致病因素为细菌或病毒。在以肉身体验为主要认知手段的古代，中医学家不可能发现细菌或病毒的存在，因而中医学家往往以天人相应的整体观来把握认知外感病。由于外感病的发病与传播受到外界气候环境和社会环境的影响，尤与人体的内环境密切相关。有鉴于此，本文从“环境隐喻”的立场出发，对外感病发病的因机证治进行分析。外界的气候环境和社会环境容易被人们感受，而对于古代无法观察人体的内环境，作者借助《论语·季氏将伐颛臾》中“祸起萧墙”的故事，对人体内环境为何与外感病的发病关系密切作以阐释，并通过人参败毒散、达原饮等方证的案例式说明，揭示清理人体内外环境而达治疗外感病的机理。     

中药治疗哮喘-慢阻肺重叠的Meta分析＊

目的 系统评价中药治疗哮喘-慢阻肺（ACO）的疗效与安全性。方法 全面检索PubMed、Cochrane Library、Web of Science、中国知网、万方、维普、中国医学文献数据库，纳入有关中医药治疗ACO的随机对照试验（RCT），运用Cochrane手册对纳入研究的方法学质量进行评估，采用Review Manager 5.3进行Meta分析。结果 共纳入32项RCT，包括2688例ACO患者，其中试验组1361例，对照组1327例。Meta分析结果显示，中医药可以显著改善ACO患者的中医证候疗效［RR=1.19，95% CI（1.13，1.25），P<0.00001］、CAT评分［MD=-3.62，95% CI（-4.37，-2.87），P<0.00001］、ACT评分［MD=3.42，95% CI（2.23，4.62），P<0.00001］，、中医证候总积分［MD=-3.61，95% CI（-4.83，-2.39），P<0.00001］、FEV₁［MD=0.59，95% CI（0.08，1.10），P=0.02］、FEV₁%［MD=8.61，95% CI（5.20，12.1），P<0.00001］、FEV₁/FVC［MD=6.52，95% CI（4.24，8.80），P<0.00001］、6 min步行实验［MD=41.18，95% CI（22.15，60.21），P<0.0001］、急性发作次数［MD=-2.46，95% CI（-3.62，-1.13），P<0.0001］。所有研究均未报道严重不良反应。结论 中药治疗ACO，可以显著提高临床疗效，改善患者的肺功能且具有较好安全性，但是需要更高质量、多样本、多中心的随机对照试验进一步确认。