医学科研论文中统计建模误区和一般策略

Misunderstandings and general strategies of statistical modeling in medical research papers

目的针对2018年医学科研论文中Logistic和线性回归建模情况进行总结分析,有针对性的提出一般建模策略。方法检索2018年中国知网医学科研论文,抽取部分论文进行评价,找出其写作过程中的建模缺陷并分析,给出一般建模方法。结果在中国知网数据库中,2018年共检出医学科研建模论文1319篇,随机抽取125篇进行评价,评价结果显示作者对于建模前数据清洗、建模前提、建模后模型评价等诸多问题不够重视。结论医学科研论文建模过程存在缺陷,论文写作过程需要进一步注意和加强建模逻辑性。

Objective To summarize and analyze the Logistic and linear regression modeling of medical research papers in 2018,to propose a general modeling strategy.Methods Search 2018 China Knowledge Network medical research related papers*extract some papers for evaluation,identify and analyze possible modeling defects in the paper writing process,provide the general method of modeling.Results In the China Knowledge Network database,1319 medical research papers were detected in 2018,and 125 papers were randomly selected for evaluation.Identified issues include no data cleaning before modeling,insufficient attention to modeling,and model evaluation after modeling.Conclusions There are defects in the modeling process of medical research papers,and further attention and enhancement are needed in the writing process.