Algorithmic fairness in computational medicine

Xu, Jie; Xiao, Yunyu; Wang, Wendy Hui; Ning, Yue; Shenkman, Elizabeth; Bian, Jiang; Wang, Fei

doi:10.1016/j.ebiom.2022.104250

Cited by 74 publications

(61 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But more importantly, these results may have profound implications in the context discussed earlier, that there is a real risk that ML models may amplify health disparities. 9 , 10 , 11 Since it seems straightforward (given the very high accuracy) to extract features related to racial information from medical scans, any spurious correlations between race and clinical outcome present in the data could be picked up by a model that is trained for clinical diagnosis. Assuming that features predictive of race are easier to extract than features associated with pathology, there are concerns that the model may learn ‘shortcuts’ that could manifest an undesirable association in the model between the patient's race and the prediction of disease.…”

Section: Introductionmentioning

confidence: 99%

Algorithmic encoding of protected characteristics in chest X-ray disease detection models

Glocker¹,

Jones²,

Bernhardt³

et al. 2023

eBioMedicine

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Algorithmic encoding of protected characteristics in chest X-ray disease detection models

Glocker¹,

Jones²,

Bernhardt³

et al. 2023

eBioMedicine

View full text Add to dashboard Cite

“…On a different note, Abdul et al [1] featured emerging trends for explainable, accountable, and intelligible systems within the CHI community, also discussing notions of fairness. Closer to our work, Mhasawade et al [94] discussed ML fairness in the domain of public and population health, and Xu et al [144] explored algorithmic fairness in computational medicine, which only covers a subset of the broad, interdisciplinary UbiComp research domains.…”

Section: Related Workmentioning

confidence: 96%

Beyond Accuracy: A Critical Review of Fairness in Machine Learning for Mobile and Wearable Computing

Yfantidou¹,

Constantinides²,

Spathis³

et al. 2023

Preprint

View full text Add to dashboard Cite

The field of mobile, wearable, and ubiquitous computing (UbiComp) is undergoing a revolutionary integration of machine learning. Devices can now diagnose diseases, predict heart irregularities, and unlock the full potential of human cognition. However, the underlying algorithms are not immune to biases with respect to sensitive attributes (e.g., gender, race), leading to discriminatory outcomes. The research communities of HCI and AI-Ethics have recently started to explore ways of reporting information about datasets to surface and, eventually, counter those biases. The goal of this work is to explore the extent to which the UbiComp community has adopted such ways of reporting and highlight potential shortcomings. Through a systematic review of papers published in the Proceedings of the ACM Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) journal over the past 5 years (2018-2022), we found that progress on algorithmic fairness within the UbiComp community lags behind. Our findings show that only a small portion (5%) of published papers adheres to modern fairness reporting, while the overwhelming majority thereof focuses on accuracy or error metrics. In light of these findings, our work provides practical guidelines for the design and development of ubiquitous technologies that not only strive for accuracy but also for fairness. CCS Concepts: • Human-centered computing → Ubiquitous and mobile computing; • Applied computing → Consumer health; • Computing methodologies → Artificial intelligence; • Social and professional topics → Codes of ethics.

show abstract

“…In the context of current issues in healthcare, Chen et al 16 summarized the fairness in machine learning and its intersectional eld, outlining how algorithmic biases arise in existing clinical work ows and the healthcare disparities that result from these issues. Although research 1,16,17,18 shows that AI algorithms can be biased against speci c populations or groups in various situations, there is a gap in understanding fairness in audio sentiment analysis.…”

Section: Introductionmentioning

confidence: 99%

Investigating Fairness in Machine Learning-based Audio Sentiment Analysis using Spectrograms and Bag-of-visual-words

Luitel

Liu

Anwar

2023

Preprint

View full text Add to dashboard Cite

Audio sentiment analysis is a growing area of research, however fairness in audio sentiment analysis is hardly investigated. We found research on machine learning tools’ reliability and fairness in various demographic groups. However, fairness in audio sentiment analysis regarding gender is still an uninvestigated field. In this research, we used 442 audio files of happiness and sadness -- representing equal samples of male and female subjects -- and generated spectrograms for each file. Then we used bag-of-visual-words method for feature extraction and Random Forest, Support Vector Machines and K-nearest Neighbors classifiers to investigate whether the machine learning models for audio sentiment analysis are fair among the two genders. We found the need for gender-specific models for audio sentiment analysis instead of a gender-agnostic general-model. Our results provided three pieces of evidence to back up our claim that the gender-agnostic model is bias in terms of accuracy of the audio sentiment analysis task. Furthermore, we discovered that a gender-specific model trained with female audio samples does not perform well against male audio files and vice versa. The best accuracy for female-model is 76% and male-model is 74%, which is significantly better than the gender-agnostic model’s accuracy of 66%.

show abstract

Algorithmic fairness in computational medicine

Cited by 74 publications

References 76 publications

Algorithmic encoding of protected characteristics in chest X-ray disease detection models

Algorithmic encoding of protected characteristics in chest X-ray disease detection models

Beyond Accuracy: A Critical Review of Fairness in Machine Learning for Mobile and Wearable Computing

Investigating Fairness in Machine Learning-based Audio Sentiment Analysis using Spectrograms and Bag-of-visual-words

Contact Info

Product

Resources

About