arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.00976cs.LGstat.OT
收藏

超声心动图数据中子组有效性在机器学习中的应用

Subgroup Validity in Machine Learning for Echocardiogram Data

Department of Computer Science, Tufts University(计算机科学系,塔夫茨大学);Division of Cardiology, Tufts Medical Center(心内科部门,塔夫茨医疗中心)

Cynthia Feeney, Shane Williams, Benjamin S. Wessler, Michael C. Hughes

AI总结:

本文探讨了超声心动图数据集中子组有效性的问题,指出现有数据集在性别、种族和民族多样性方面的不足,并提出改进社会人口学报告和进行子组分析以验证子组有效性。

摘要:

超声心动图数据集使深度学习模型能够自动化解读心脏超声,从而扩大获得诊断有用图像准确读数的途径。然而,这些数据集中患者性别、性别、种族和民族的报告不足,且子组特定的预测性能未被评估。这些报告缺陷引发了关于子组有效性的担忧,必须在模型部署之前研究和解决。在本文中,我们表明当前的开放超声心动图数据集无法缓解子组有效性问题。我们改进了两个数据集的社会人口学报告:TMED-2和MIMIC-IV-ECHO。对六个开放数据集的分析显示,没有考虑性别多样化的患者,且许多种族和民族组的患者数量不足。我们进一步对两个已发表的主动脉狭窄检测模型在TMED-2上进行了探索性子组分析。我们发现,对于性别、种族和民族子组,缺乏子组有效性的证据。我们的发现强调,需要更多数据来证明子组有效性,改进人口学报告,并进行子组聚焦分析。

英文摘要:

Echocardiogram datasets enable training deep learning models to automate interpretation of cardiac ultrasound, thereby expanding access to accurate readings of diagnostically-useful images. However, the gender, sex, race, and ethnicity of the patients in these datasets are underreported and subgroup-specific predictive performance is unevaluated. These reporting deficiencies raise concerns about subgroup validity that must be studied and addressed before model deployment. In this paper, we show that current open echocardiogram datasets are unable to assuage subgroup validity concerns. We improve sociodemographic reporting for two datasets: TMED-2 and MIMIC-IV-ECHO. Analysis of six open datasets reveals no consideration of gender-diverse patients and insufficient patient counts for many racial and ethnic groups. We further perform an exploratory subgroup analysis of two published aortic stenosis detection models on TMED-2. We find insufficient evidence for subgroup validity for sex, racial, and ethnic subgroups. Our findings highlight that more data for underrepresented subgroups, improved demographic reporting, and subgroup-focused analyses are needed to prove subgroup validity in future work.

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。

↑