TY - GEN
T1 - Bias Reducing Multitask Learning on Mental Health Prediction
AU - Zanna, Khadija
AU - Sridhar, Kusha
AU - Yu, Han
AU - Sano, Akane
N1 - Funding Information:
This work was supported by NSF #1840167 and #2047296.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - There has been an increase in research in developing machine learning models for mental health detection or prediction in recent years due to increased mental health issues in society. Effective use of mental health prediction or detection models can help mental health practitioners re-define mental illnesses more objectively than currently done, and identify illnesses at an earlier stage when interventions may be more effective. However, there is still a lack of standard in evaluating bias in such machine learning models in the field, which leads to challenges in providing reliable predictions and in addressing disparities. This lack of standards persists due to factors such as technical difficulties, complexities of high dimensional clinical health data, etc., which are especially true for physiological signals. This along with prior evidence of relations between some physiological signals with certain demographic identities restates the importance of exploring bias in mental health prediction models that utilize physiological signals. In this work, we aim to perform a fairness analysis and implement a multi-task learning based bias mitigation method on anxiety prediction models using ECG data. Our method is based on the idea of epistemic uncertainty and its relationship with model weights and feature space representation. Our analysis showed that our anxiety prediction base model introduced some bias with regards to age, income, ethnicity, and whether a participant is born in the U.S. or not, and our bias mitigation method performed better at reducing the bias in the model, when compared to the reweighting mitigation technique. Our analysis on feature importance also helped identify relationships between heart rate variability and multiple demographic groupings.
AB - There has been an increase in research in developing machine learning models for mental health detection or prediction in recent years due to increased mental health issues in society. Effective use of mental health prediction or detection models can help mental health practitioners re-define mental illnesses more objectively than currently done, and identify illnesses at an earlier stage when interventions may be more effective. However, there is still a lack of standard in evaluating bias in such machine learning models in the field, which leads to challenges in providing reliable predictions and in addressing disparities. This lack of standards persists due to factors such as technical difficulties, complexities of high dimensional clinical health data, etc., which are especially true for physiological signals. This along with prior evidence of relations between some physiological signals with certain demographic identities restates the importance of exploring bias in mental health prediction models that utilize physiological signals. In this work, we aim to perform a fairness analysis and implement a multi-task learning based bias mitigation method on anxiety prediction models using ECG data. Our method is based on the idea of epistemic uncertainty and its relationship with model weights and feature space representation. Our analysis showed that our anxiety prediction base model introduced some bias with regards to age, income, ethnicity, and whether a participant is born in the U.S. or not, and our bias mitigation method performed better at reducing the bias in the model, when compared to the reweighting mitigation technique. Our analysis on feature importance also helped identify relationships between heart rate variability and multiple demographic groupings.
KW - Monte-Carlo dropout
KW - bias
KW - epistemic uncertainty
KW - fairness metric
KW - multi-task learning
KW - protected label
UR - http://www.scopus.com/inward/record.url?scp=85143756585&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85143756585&partnerID=8YFLogxK
U2 - 10.1109/ACII55700.2022.9953850
DO - 10.1109/ACII55700.2022.9953850
M3 - Conference contribution
AN - SCOPUS:85143756585
T3 - 2022 10th International Conference on Affective Computing and Intelligent Interaction, ACII 2022
BT - 2022 10th International Conference on Affective Computing and Intelligent Interaction, ACII 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Affective Computing and Intelligent Interaction, ACII 2022
Y2 - 18 October 2022 through 21 October 2022
ER -