Academic Journal
(Predictable) performance bias in unsupervised anomaly detectionResearch in context
| العنوان: | (Predictable) performance bias in unsupervised anomaly detectionResearch in context |
|---|---|
| المؤلفون: | Felix Meissen, Svenja Breuer, Moritz Knolle, Alena Buyx, Ruth Müller, Georgios Kaissis, Benedikt Wiestler, Daniel Rückert |
| المصدر: | EBioMedicine, Vol 101, Iss , Pp 105002- (2024) |
| بيانات النشر: | Elsevier, 2024. |
| سنة النشر: | 2024 |
| المجموعة: | LCC:Medicine LCC:Medicine (General) |
| مصطلحات موضوعية: | Artificial intelligence, Machine learning, Algorithmic bias, Subgroup disparities, Anomaly detection, Medicine, Medicine (General), R5-920 |
| الوصف: | Summary: Background: With the ever-increasing amount of medical imaging data, the demand for algorithms to assist clinicians has amplified. Unsupervised anomaly detection (UAD) models promise to aid in the crucial first step of disease detection. While previous studies have thoroughly explored fairness in supervised models in healthcare, for UAD, this has so far been unexplored. Methods: In this study, we evaluated how dataset composition regarding subgroups manifests in disparate performance of UAD models along multiple protected variables on three large-scale publicly available chest X-ray datasets. Our experiments were validated using two state-of-the-art UAD models for medical images. Finally, we introduced subgroup-AUROC (sAUROC), which aids in quantifying fairness in machine learning. Findings: Our experiments revealed empirical “fairness laws” (similar to “scaling laws” for Transformers) for training-dataset composition: Linear relationships between anomaly detection performance within a subpopulation and its representation in the training data. Our study further revealed performance disparities, even in the case of balanced training data, and compound effects that exacerbate the drop in performance for subjects associated with multiple adversely affected groups. Interpretation: Our study quantified the disparate performance of UAD models against certain demographic subgroups. Importantly, we showed that this unfairness cannot be mitigated by balanced representation alone. Instead, the representation of some subgroups seems harder to learn by UAD models than that of others. The empirical “fairness laws” discovered in our study make disparate performance in UAD models easier to estimate and aid in determining the most desirable dataset composition. Funding: European Research Council Deep4MI. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2352-3964 |
| Relation: | http://www.sciencedirect.com/science/article/pii/S2352396424000379; https://doaj.org/toc/2352-3964 |
| DOI: | 10.1016/j.ebiom.2024.105002 |
| URL الوصول: | https://doaj.org/article/d62efed5f9a843a4a8bf244eda853221 |
| رقم الانضمام: | edsdoj.62efed5f9a843a4a8bf244eda853221 |
| قاعدة البيانات: | Directory of Open Access Journals |
Full Text Finder | تدمد: | 23523964 |
|---|---|
| DOI: | 10.1016/j.ebiom.2024.105002 |