提高医疗机器学习潜在偏差的认识:来自数据马拉松的经验
Harry Hochheiser1, Jesse Klug2, Thomas Mathie3
1Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, Pennsylvania, United States of America.
PLOS digital health
|July 11, 2025
概括
数据马拉松有效地识别医疗机器学习模型中的偏差,通过让跨学科团队分析来自全球开源疾病严重性得分 (GOSSIS-1) 的数据和预测. 这种方法突出了潜在的问题,如人口代表性和绩效差异.
科学领域:
- 医疗信息学 医疗信息学
- 机器学习偏见 机器学习偏见
- 医疗保健分析 医疗保健分析
背景情况:
- 医疗机器学习模型可能包含隐藏的偏见.
- 调查这些偏见对于公平的医疗保健至关重要.
- 开源工具为偏见检测提供了机会.
研究的目的:
- 挑战临床医生和信息专家确定医学机器学习中的偏见来源.
- 调查数据和预测从一个开源的疾病严重程度得分.
- 探索医疗保健算法中未被识别的偏见.
主要方法:
- 进行了为期两天的数据马拉松,以调查全球开源疾病严重性得分 (GOSSIS-1) 的偏见.
- 跨学科团队 (临床医生和计算机专家) 开发了假设,并使用了选择的分析工具.
- 团队分析了GOSSIS-1预测,人口统计,护理变量和结果之间的关系.
主要成果:
- 五个团队参与了,其中大多数使用Python进行分析.
- 确定了潜在的偏见来源包括人口代表性,群体之间的校准差异,以及医院设置中的绩效差异.
- 分析主题包括人口统计,护理背景和缺失数据影响.
结论:
- 数据马拉松是发现医疗机器学习偏差的一个有价值的方法.
- 这种方法促进了开发人员和用户对未被识别的偏见的探索.
- 跨学科合作是识别和减轻人工智能医疗工具偏见的关键.
更多相关视频
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.9K
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
587
相关概念视频
Bias
5.0K
Bias refers to any tendency that prevents a question from being considered unprejudiced. In research, bias occurs when one outcome or answer is selected or encouraged over others in sampling or testing. Bias can occur during any research phase, including study design, data collection, analysis, and publication.
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
5.0K
Bias in Epidemiological Studies
695
Biases can arise at various stages of research, from study design and data collection to analysis and interpretation. Recognizing and addressing these biases is essential to ensure the validity and reliability of epidemiological findings.Broadly speaking, biases in epidemiology fall into three main categories: selection bias, information bias, and confounding. A more detailed description of possible biases is:
695
Issues And Trends In Healthcare Delivery System
5.9K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
5.9K
Errors occurring during blood pressure monitoring
982
Blood pressure monitoring is a crucial clinical procedure in diagnosing and managing various cardiovascular conditions. Despite its significance, the accuracy of blood pressure measurements can be compromised by multiple factors, potentially leading to either falsely high or low readings. These inaccuracies are critical as they can significantly impact patient care. So, it is vital to understand these challenges deeply and adopt strategic approaches to minimize errors.
Several factors...
Several factors...
982
Improving Translational Accuracy
11.9K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.9K
Data Validation
5.3K
Data validation is an essential part of a comprehensive assessment. Validation is confirming or verifying and opening the door to gathering more assessment data as it clarifies vague or unclear data. The process of checking and verifying the collected information is called data validation. The primary purpose of data validation is to ensure data is as free from error, bias, and misinterpretation as possible.
Nursing assessment guides are generally based on holistic models rather than medical...
Nursing assessment guides are generally based on holistic models rather than medical...
5.3K
