サブグループ学習性のある医療データセットにおける暗黙的および明示的な人種バイアスの検出,特徴付け,緩和:アルゴリズム開発および検証研究
Faris Gulamali1, Ashwin Shreekant Sawant1, Lora Liharska1
1Icahn School of Medicine at Mount Sinai, 1468 Madison Avenue, New York, NY, 10029, United States, 1 2122416500.
Journal of medical Internet research
|September 4, 2025
まとめ
新しいメトリックであるAEquityは データ収集と再表示を ガイドすることで 医療データにおけるアルゴリズムのバイアスを 効果的に軽減します このアプローチは,様々なデータセットとアルゴリズムで既存の方法を上回り,AI診断の公平性を向上させます.
科学分野:
- 医療における人工知能
- アルゴリズムの公平性
- データサイエンス
背景:
- 医療アルゴリズムの普及は 恵まれないグループに対する 偏見の持続を懸念しています
- 既存のバイアス緩和方法は,データレベルの介入に限られた努力をしてモデル修正に焦点を当てています.
- 医療データセットはバイアスになりやすいので 診断と予測アルゴリズムの性能に影響を及ぼします
研究 の 目的:
- 医療データにおけるバイアスを特定し軽減するために,学習曲線の近似を用いた新しいメトリックであるAEquityを導入します.
- アルゴリズムの公平性を向上させるために,ガイドされたデータセットの収集と再ラベリングにおける AEquityの有効性を実証する.
- 様々なデータセット,アルゴリズム,公平性メトリックで AEquity の堅実性を評価する.
主な方法:
- 偏見の検出と緩和のための学習曲線の近似に基づいたAEequityメトリックを開発しました.
- 胸部X線データセット,医療費利用データ,国家健康栄養調査 (NHANES) に AEquityを適用した.
- バランスのとれた経験的なリスクの最小化と校正のような最先端の方法に対してベンチマークされたAEクイティ.
主要な成果:
- エクイティによるデータ収集は胸部X線写真のバイアスを29%~96. 5% (AUC) 減少させた.
- 複数の公平性指標 (例えば,FNRの33. 3%減少) で,交差点の集団 (メディケイドの黒人患者) で顕著なバイアスの減少が観察されました.
- AEquityはバランスのとれた経験的リスク最小化と校正を上回り,さまざまなAIモデル (CNN,トランスフォーマーなど) で堅実なパフォーマンスを示しました. ) でした.
結論:
- 医療におけるデータレベルでのアルゴリズムのバイアスを軽減するための 堅実で効果的なツールです
- このメトリックは,さまざまなデータセット,人口集団,機械学習アーキテクチャに広く適用可能であることを示しています.
- 医療AIにおける公平性を高めるため,データ中心のアプローチを提案しています.
さらに関連する動画
07:35Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
7.6K
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
565
関連する概念動画
Stereotypes, Prejudice, and Discrimination
91.4K
Humans are very diverse and although we share many similarities, we also have many differences. The social groups we belong to help form our identities (Tajfel, 1974). These differences may be difficult for some people to reconcile, which may lead to prejudice toward people who are different. Prejudice is a negative attitude and feeling toward an individual based solely on one’s membership in a particular social group (Allport, 1954; Brown, 2010). Prejudice is common against people who...
91.4K
Bias in Epidemiological Studies
666
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:
666
Bias
4.8K
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...
4.8K
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
Blind Procedures
12.1K
Ideally, the people who observe and record the children’s behavior are unaware of who was assigned to the experimental or control group, in order to control for experimenter bias. Experimenter bias refers to the possibility that a researcher’s expectations might skew the results of the study. Remember, conducting an experiment requires a lot of planning, and the people involved in the research project have a vested interest in supporting their hypotheses. If the observers knew which...
12.1K
Surveys
15.3K
Often, psychologists develop surveys as a means of gathering data. Surveys are lists of questions to be answered by research participants, and can be delivered as paper-and-pencil questionnaires, administered electronically, or conducted verbally. Generally, the survey itself can be completed in a short time, and the ease of administering a survey makes it easy to collect data from a large number of people.
15.3K
