JMIR Publications

ABSTRACT

Background:

COVID-19 forecasting models have been used to inform decision making around resource allocation and intervention decisions e.g., hospital beds or stay-at-home orders. State-of-the-art forecasting models often use multimodal data such as mobility or socio-demographic data to enhance COVID-19 case prediction models. Nevertheless, related work has revealed under-reporting bias in COVID-19 cases as well as sampling bias in mobility data for certain minority racial and ethnic groups, which affects the fairness of the COVID-19 predictions among racial and ethnic groups.

Objective:

To introduce a fairness correction method that works for forecasting COVID-19 cases at an aggregate geographic level.

Methods:

We use Hard and soft error parity analysis results on existing fairness frameworks and to show our proposed method DemOpts, performs better in both scenarios.

Results:

In this paper, we first show that state of the art COVID-19 deep learning models output mean prediction errors that are significantly different across racial and ethnic groups at larger geographic scales. Then, we propose a novel de-biasing method, DemOpts, to increase the fairness of deep learning based forecasting models trained on potentially biased datasets. Our results show that DemOpts can achieve better error parity than other state of the art de-biasing approaches, thus effectively reducing the differences in the mean error distributions across more racial and ethnic groups.

Conclusions:

We introduce DemOpts which reduces the error parity as compared to other approaches and generates fair forecasting model as compared to other approaches in literature.