A Study of Age and Sex Bias in Multiple Instance Learning Based Classification of Acute Myeloid Leukemia Subtypes

Sadafi, Ario; Hehr, Matthias; Navab, Nassir und Marr, Carsten (2023): A Study of Age and Sex Bias in Multiple Instance Learning Based Classification of Acute Myeloid Leukemia Subtypes. 12th Int Workshop on Clin Image-Based Procedures - Towards Holist Patient Models for Personalised Healthcare, 1st Int Workshop on Fairness of AI in Med Imaging , 2nd Int Workshop on Ethical and Philosoph Issues in Med Imaging, Vancouver, Canada, 08. - 12. Oktober 2023. Wesarg, Stefan; Puyol Antón, Esther; Baxter, John S. H.; Erdt, Marius; Drechsler, Klaus; Oyarzun Laura, Cristina; Freiman, Moti; Chen, Yufei; Rekik, Islem; Eagleson, Roy; Feragen, Aasa; King, Andrew P.; Cheplygina, Veronika; Ganz-Benjaminsen, Melani; Ferrante, Enzo; Glocker, Ben; Moyer, Daniel und Petersen, Eikel (Hrsg.): In: Clinical Image-Based Procedures, Fairness of AI in Medical Imaging, and Ethical and Philosophical Issues in Medical Imaging, Lecture Notes in Computer Science Bd. 14242 Cham: Springer. S. 256-265

Abstract

Accurate classification of Acute Myeloid Leukemia (AML) subtypes is crucial for clinical decision-making and patient care. In this study, we investigate the potential presence of age and sex bias in AML subtype classification using Multiple Instance Learning (MIL) architectures. To that end, we train multiple MIL models using different levels of sex imbalance in the training set and excluding certain age groups. To assess the sex bias, we evaluate the performance of the models on male and female test sets. For age bias, models are tested against underrepresented age groups in the training data. We find a significant effect of sex and age bias on the performance of the model for AML subtype classification. Specifically, we observe that females are more likely to be affected by sex imbalance dataset and certain age groups, such as patients with 72 to 86 years of age with the RUNX1::RUNX1T1 genetic subtype, are significantly affected by an age bias present in the training data. Ensuring inclusivity in the training data is thus essential for generating reliable and equitable outcomes in AML genetic subtype classification, ultimately benefiting diverse patient populations.

• Dokumententyp: Konferenzbeitrag (Paper)
• Fakultät: Medizin > Klinikum der LMU München > Medizinische Klinik und Poliklinik III (Onkologie) ; Medizin > Klinikum der LMU München > Kinderklinik und Kinderpoliklinik im Dr. von Haunerschen Kinderspital
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik ; 600 Technik, Medizin, angewandte Wissenschaften > 610 Medizin und Gesundheit
• ISBN: 978-3-031-45248-2 ; 978-3-031-45249-9
• ISSN: 0302-9743
• Ort: Cham
• Sprache: Englisch