arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.06403stat.APcs.LGstat.ML
收藏

在临床决策中调整主观评分

Aligning Subjective Ratings in Clinical Decision Making

Fraunhofer IAIS(弗劳恩霍夫智能分析与信息系统研究所);Fraunhofer Cluster of Excellence Immune-Mediated Diseases CIMD(弗劳恩霍夫免疫介导疾病卓越集群);Fraunhofer Center for Machine Learning(弗劳恩霍夫机器学习中心);Fraunhofer IME-TMP(弗劳恩霍夫分子生物学与应用生态学研究所转化医学与药理学分部)

Annika Pick, Sebastian Ginzel, Stefan Rüping, Jil Sander, Ann Christina Foldenauer, Michaela Köhm

摘要:

除了客观指标(如实验室值)外,临床数据通常还包含专家的主观评价(如疾病严重程度评估)。虽然客观指标更加透明和稳健,但主观评价包含丰富的专家知识和直觉。在这项工作中,我们展示了成对排序方法的潜力,使主观评价与客观指标相一致,创造了一个新的分数,结合了它们的优势,有利于诊断。在一项关于有患银屑病关节炎风险的患者的病例研究中,我们说明了所得评分(1)在检测疾病存在/不存在时提高了分类准确性,(2)稀疏,(3)为后续分析提供了细致入微的严重程度评估。

英文摘要:

In addition to objective indicators (e.g. laboratory values), clinical data often contain subjective evaluations by experts (e.g. disease severity assessments). While objective indicators are more transparent and robust, the subjective evaluation contains a wealth of expert knowledge and intuition. In this work, we demonstrate the potential of pairwise ranking methods to align the subjective evaluation with objective indicators, creating a new score that combines their advantages and facilitates diagnosis. In a case study on patients at risk for developing Psoriatic Arthritis, we illustrate that the resulting score (1) increases classification accuracy when detecting disease presence/absence, (2) is sparse and (3) provides a nuanced assessment of severity for subsequent analysis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑