Mitigating bias in machine learning for medicine

Vokinger, Kerstin Noëlle; Feuerriegel, Stefan; Kesselheim, Aaron S.

doi:10.1038/s43856-021-00028-w

Cited by 123 publications

(98 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sociotechnical perspective on AF overcomes assumptions present in the literature and offers a framework for identifying sources of algorithmic bias. To date, sources of bias were either related to the ML workflow (Feuerriegel et al, 2020;Vokinger, Feuerriegel, & Kesselheim, 2021;von Zahn, Feuerriegel, & Kuehl, 2021) or ascribed to social biases (Mohamed et al, 2020;Wong, 2020). We will now address sources of bias identified in the literature (see Appendix A) and classify them according to the components of a sociotechnical system or the interrelationships between them.…”

Section: Directions For Sociotechnical Research Into Algorithmic Fair...mentioning

confidence: 99%

A sociotechnical view of algorithmic fairness

Dolata

Feuerriegel

Schwabe

2021

Information Systems Journal

Self Cite

View full text Add to dashboard Cite

Algorithmic fairness (AF) has been framed as a newly emerging technology that mitigates systemic discrimination in automated decision-making, providing opportunities to improve fairness in information systems (IS). However, based on a state-of-the-art literature review, we argue that fairness is an inherently social concept and that technologies for AF should therefore be approached through a sociotechnical lens. We advance the discourse on AF as a sociotechnical phenomenon. Our research objective is to embed AF in the sociotechnical view of IS. Specifically, we elaborate on why outcomes of a system that uses algorithmic means to assure fairness depend on mutual influences between technical and social structures. This perspective can generate new insights that integrate knowledge from both technical fields and social studies. Further, it spurs new directions for IS debates. We contribute as follows:First, we problematize fundamental assumptions in the current discourse on AF based on a systematic analysis of 310 articles. Second, we respond to these assumptions by theorizing AF as a sociotechnical construct. Third, we propose directions for IS researchers to enhance their impacts by pursuing a unique understanding of sociotechnical AF. We call for and undertake a holistic approach to AF.A sociotechnical perspective on AF can yield holistic solutions to systemic biases and discrimination.

show abstract

Section: Directions For Sociotechnical Research Into Algorithmic Fair...mentioning

confidence: 99%

A sociotechnical view of algorithmic fairness

Dolata

Feuerriegel

Schwabe

2021

Information Systems Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another limitation of ML encountered at the model-development phase is sampling bias and lack of external validation [ 207 , 208 ]. ML learning models usually derive their weights from large datasets.…”

Section: Discussionmentioning

confidence: 99%

Current and Future Applications of Artificial Intelligence in Coronary Artery Disease

et al. 2022

View full text Add to dashboard Cite

Cardiovascular diseases (CVDs) carry significant morbidity and mortality and are associated with substantial economic burden on healthcare systems around the world. Coronary artery disease, as one disease entity under the CVDs umbrella, had a prevalence of 7.2% among adults in the United States and incurred a financial burden of 360 billion US dollars in the years 2016–2017. The introduction of artificial intelligence (AI) and machine learning over the last two decades has unlocked new dimensions in the field of cardiovascular medicine. From automatic interpretations of heart rhythm disorders via smartwatches, to assisting in complex decision-making, AI has quickly expanded its realms in medicine and has demonstrated itself as a promising tool in helping clinicians guide treatment decisions. Understanding complex genetic interactions and developing clinical risk prediction models, advanced cardiac imaging, and improving mortality outcomes are just a few areas where AI has been applied in the domain of coronary artery disease. Through this review, we sought to summarize the advances in AI relating to coronary artery disease, current limitations, and future perspectives.

show abstract

“…Making use of frequency weighted evaluation metrics, such as the frequency weighted intersection over union rather than the commonly used Jaccard similarity index could assist in dealing with this challenge. Development of consensus documents for OCT based deep learning may also assist researchers reduce other biases in their work, including data distribution, dataset leakage and methodological bias, factors already shown to significantly skew results in cancer diagnoses [ 197 , 198 , 199 , 200 ]. Improving access to large scale, longitudinal and multicenter datasets that are representative of real-world scenarios coupled with consistent use of techniques including cross-validation, model regularization (to prevent overfitting or underfitting) and de-biasing through oversampling and adversarial de-biasing will help in addressing these challenges.…”

Section: Discussionmentioning

confidence: 99%

Automated Coronary Optical Coherence Tomography Feature Extraction with Application to Three-Dimensional Reconstruction

et al. 2022

View full text Add to dashboard Cite

Coronary optical coherence tomography (OCT) is an intravascular, near-infrared light-based imaging modality capable of reaching axial resolutions of 10–20 µm. This resolution allows for accurate determination of high-risk plaque features, such as thin cap fibroatheroma; however, visualization of morphological features alone still provides unreliable positive predictive capability for plaque progression or future major adverse cardiovascular events (MACE). Biomechanical simulation could assist in this prediction, but this requires extracting morphological features from intravascular imaging to construct accurate three-dimensional (3D) simulations of patients’ arteries. Extracting these features is a laborious process, often carried out manually by trained experts. To address this challenge, numerous techniques have emerged to automate these processes while simultaneously overcoming difficulties associated with OCT imaging, such as its limited penetration depth. This systematic review summarizes advances in automated segmentation techniques from the past five years (2016–2021) with a focus on their application to the 3D reconstruction of vessels and their subsequent simulation. We discuss four categories based on the feature being processed, namely: coronary lumen; artery layers; plaque characteristics and subtypes; and stents. Areas for future innovation are also discussed as well as their potential for future translation.

show abstract

Mitigating bias in machine learning for medicine

Abstract: Several sources of bias can affect the performance of machine learning systems used in medicine and potentially impact clinical care. Here, we discuss solutions to mitigate bias across the different development steps of machine learning-based systems for medical applications.

Cited by 123 publications

References 13 publications

A sociotechnical view of algorithmic fairness

A sociotechnical view of algorithmic fairness

Current and Future Applications of Artificial Intelligence in Coronary Artery Disease

Automated Coronary Optical Coherence Tomography Feature Extraction with Application to Three-Dimensional Reconstruction

Contact Info

Product

Resources

About