Fairer AI in ophthalmology via implicit fairness learning for mitigating sexism and ageism

Abstract

The transformative role of artificial intelligence (AI) in various fields highlights the need for it to be both accurate and fair. Biased medical AI systems pose significant potential risks to achieving fair and equitable healthcare. Here, we show an implicit fairness learning approach to build a fairer ophthalmology AI (called FairerOPTH) that mitigates sex (biological attribute) and age biases in AI diagnosis of eye diseases. Specifically, FairerOPTH incorporates the causal relationship between fundus features and eye diseases, which is relatively independent of sensitive attributes such as race, sex, and age. We demonstrate on a large and diverse collected dataset that FairerOPTH significantly outperforms several state-of-the-art approaches in terms of diagnostic accuracy and fairness for 38 eye diseases in ultra-widefield imaging and 16 eye diseases in narrow-angle imaging. This work demonstrates the significant potential of implicit fairness learning in promoting equitable treatment for patients regardless of their sex or age.

Fig. 1. Characteristics of the datasets.

a Fundus images including both ultra-widefield (UWF) and narrow-angle (NAF) images, play a foundation role in the diagnosis of various ocular diseases by modern clinical systems. UWF imaging, an advanced method, covers up to 200° eccentricities in a single capture, while NAF imaging, which is more common, has an angle of view of 30–60°. b Statistics of the OculoScope and MixNAF datasets. The label density $\rho =\frac{1}{N}{\sum }_{i=1}^K∣y_i∣$ quantitatively shows that a single fundus map contains multiple diseases and pathological signs on average, where y_i is the number of the i-th disease, N represents the total number of images, and K represents the number of disease types. c The sample distribution of 38 diseases in OculoScope is extremely unbalanced. d The sample distribution of 16 diseases on MixNAF is also extremely unbalanced. e Visual representation of fundus features in fundus images. Source data are provided as a Source Data file.

Fig. 2. Mitigating ageism of AI in ophthalmology.

a Sample distribution of patient age (in 10-year intervals) for the OculoScope test set. The unbalanced sample distribution of patient age may cause AI to favor the patients in the age group that contains more samples in the screening dataset, which will lead to the problem of AI ageism. In this study, we show that implicit fairness learning based on the relationship between ophthalmic diseases and fundus features can not only mitigate the unfairness that arises due to different sensitive attributes but also improve the screening accuracy for multiple diseases. b FairerOPTH is developed and validated with the OculoScope dataset, which contains data from 8405 patients with ages ranging from 0 to 90. Within each age division, FairerOPTH has obvious advantages in four fairness metrics (ΔA (average screening disparity), ΔM (max screening disparity), DPM (demographic disparity metric), and EOM (equality of opportunity metric)) compared with the baseline model. The smaller ΔA and ΔM are, the better. c Details of the fairness metric ΔD (screening quality disparity) for 38 diseases. d Details of PQD (predictive quality disparity) for 38 diseases. Source data are provided as a Source Data file.

Fig. 3. Mitigating sexism of AI in ophthalmology.

a Proportion of male and female patients included in the OculoScope test set. b Comparison of fairness metrics (ΔA (average screening disparity), ΔM (max screening disparity), DPM (demographic disparity metric), and EOM (equality of opportunity metric)) and screening accuracy (mAP) between the baseline and our FairerOPTH. c Details of the fairness metric ΔD (screening quality disparity) for 38 diseases. d Details of PQD (predictive quality disparity) for 38 diseases. Source data are provided as a Source Data file.

Fig. 4. Screening performance of the FairerOPTH on the OculoScope dataset.

a The FairerOPTH consists of two branches, pathology and disease classification that predict 67 fundus features and 38 ophthalmic diseases, respectively. Such design of the two branches aims to enhance the disease representation in the disease classification branch, resulting in higher screening accuracy. b Comparison of FairerOPTH with the baseline model and state-of-the-art multi-label classification methods using mAP, specificity, sensitivity, and AUC (area under the curve) evaluation metrics. c, d ROC (Receiver Operating Characteristics) curves for 38 diseases of baseline model and FairerOPTH. Source data are provided as a Source Data file.

Fig. 5. Screening performance of the FairerOPTH on the MixNAF dataset.

a The FairerOPTH predicts 20 fundus features and 16 ophthalmic diseases from input NAF images. b Comparison of FairerOPTH with the baseline model and state-of-the-art multi-label classification methods using mAP, specificity, sensitivity, and AUC (area under the curve) evaluation metrics. c ROC (Receiver Operating Characteristics) curves for 16 diseases of baseline model and FairerOPTH. Source data are provided as a Source Data file.