Subjects: Library Science,Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract: [Purpose/significance] To evaluate the important academic contribution of the book in perfecting and developing the discipline system of "five metrics". [Method/process] This paper analyzed the core value of the book in the improvement and new development of the discipline system of "five metrics" from four aspects of Altmetrics theory, tool, method and application. [Result/conclusion] Published as a series of research books on metrology, the book demonstrates the close relationship between Altmetrics and "five metrics", and has special academic value and application significance for promoting the future application and development of Altmetrics.
Subjects: Library Science,Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract: [Purpose/significance] To explore the influence of open peer review (OPR) on the citation and social attention of journal papers. [Method/process] By using the descriptive statistical analysis and paired sample nonparametric test, we analyzed the difference in the journals' age, age since being indexed by SCI database, nationality, publication cycle, open access, transparency level of peer review, citation and Altmetrics between OPR journals and the non-OPR journals. We also explored the influence of the general characteristics on the citation and Altmetrics of the OPR journal papers. We tested the relationship between the citation and Altmetrics of OPR journals. [Result/conclusion] OPR journal papers have significant advantages in citation and Altmetrics. Country has significant influence on citation, and publication cycle has significant influence on citation and Altmetrics. The citation of OPR journal papers is significantly positively correlated with the Altmetrics.
Subjects: Library Science,Information Science >> Information Science submitted time 2017-11-08 Cooperative journals: 《数据分析与知识发现》
Abstract:【目的】利用SEER 数据库, 找出对非小细胞肺癌患者预后生存的影响因素并预测患者预后生存状态, 指导肿瘤预后评价。【方法】采用单因素统计学方法及Logistic 回归分析初步筛选预后相关因素, 利用贝叶斯网络方法构建患者术后生存预测模型, 并与其他三种常见的机器学习分类算法所建模型效能做比较。【结果】最终纳入模型的预后变量共5 项, 包括年龄、肿瘤大小、组织学分级、肿瘤分期和受累淋巴结比率。贝叶斯网络所建模型对非小细胞肺癌患者生存状况预测准确率达到72.87%。【局限】SEER 数据库内纳入的预后因素有限, 一定程度影响预测效果。【结论】贝叶斯网络可探寻变量间的关系并构建肺癌患者最优预后模型, 辅助医生判断患者预后情况及治疗效果, 优于决策树、支持向量机及人工神经网络三种模式。
Subjects: Library Science,Information Science >> Information Science submitted time 2017-11-08 Cooperative journals: 《数据分析与知识发现》
Abstract:【目的】利用SEER 数据库, 找出对非小细胞肺癌患者预后生存的影响因素并预测患者预后生存状态, 指导肿瘤预后评价。【方法】采用单因素统计学方法及Logistic 回归分析初步筛选预后相关因素, 利用贝叶斯网络方法构建患者术后生存预测模型, 并与其他三种常见的机器学习分类算法所建模型效能做比较。【结果】最终纳入模型的预后变量共5 项, 包括年龄、肿瘤大小、组织学分级、肿瘤分期和受累淋巴结比率。贝叶斯网络所建模型对非小细胞肺癌患者生存状况预测准确率达到72.87%。【局限】SEER 数据库内纳入的预后因素有限, 一定程度影响预测效果。【结论】贝叶斯网络可探寻变量间的关系并构建肺癌患者最优预后模型, 辅助医生判断患者预后情况及治疗效果, 优于决策树、支持向量机及人工神经网络三种模式。
Subjects: Library Science,Information Science >> Information Science submitted time 2017-11-08 Cooperative journals: 《数据分析与知识发现》
Abstract:【目的】建立结合多种特征的条件随机场模型, 探索从大型生物医学文本中同时自动提取化学物质和疾病实体的方法。【方法】结合命名实体识别特征, 包括词法特征、领域知识特征、词典匹配特征和无监督学习特征等, 比较不同特征对命名实体识别的效果, 并优化模型。【结果】CRF 模型纳入词法特征、词典匹配特征、无监督学习特征和部分领域知识特征, 化学物质识别准确率97.33%、召回率80.76%、F 值8.27%, 疾病实体识别准确率为84.20%、召回率为81.96%、F值为83.07%。【局限】同时识别化学物质和疾病实体可能存在互相干扰, 删除的部分领域特征可能含有有用信息。【结论】本研究可为生物医学命名实体识别的特征选择提供参考, 同时仍需优化特征以获得更好的识别效果。
Subjects: Library Science,Information Science >> Information Science submitted time 2017-10-11 Cooperative journals: 《数据分析与知识发现》
Abstract: [Objective] This study developed a disease prediction model based on the support vector machine, using electronic medical records of the severe acute pancreatitis patients. [Methods] We first adjusted the kernel type and parameter values of the support vector machine method to get an optimized prediction model. Then, we combined it with univariable and multivariable logistic regression analysis methods to select features’ variable. Finally, we proposed a simplified early warning model for the severe acute pancreatitis. [Results] The new model’s prediction accuracy rate is 70.37%. Variables used by this model include: white blood cell count, serum calcium, serum lipase, systolic blood pressure, diastolic blood pressure and pleural effusion. [Limitations] Because of the small sample size, we only used this support vector machine method to develop the new disease prediction model. In the future, we will try to establish a larger examination system for the clinical trial. [Conclusions] Support vector machine can help us develop an optimal disease prediction model. A new system based on this model could support our clinical decision makings.