Diagnosing and remediating harmful data shifts for the responsible deployment of clinical AI models

Harmful data shifts occur when the distribution of data used to train a clinical AI system differs significantly from the distribution of data encountered during deployment, leading to erroneous predictions and potential harm to patients. We evaluated the impact of data shifts on an early warning system (EWS) for in-hospital mortality that uses electronic health record (EHR) data from patients admitted to a general internal medicine service. We found model performance to differ across subgroups of clinical diagnoses, sex and age. To explore the robustness of the model, we evaluated potentially harmful data shifts across demographics, hospital types, seasons, times of hospital admission, and whether the patient was admitted from an acute care institution or nursing home, without relying on model performance. Interestingly, we found that models trained on community hospitals experience harmful data shifts when evaluated on academic hospitals, whereas the models trained on academic hospitals transfer well to the community hospitals. To improve model performance across hospital sites we employed transfer learning, a strategy that stores knowledge gained from learning one domain and applies it to a different but related domain. We found hospital type-specific models that leverage transfer learning, perform better than models that use all available hospitals. Furthermore, we monitored data shifts over time and identified model deterioration during the COVID-19 pandemic. Typically machine learning models remain locked after deployment, however, this can lead to model deterioration due to data shifts that occur over time. We used continual learning, the process of learning from a continual stream of data in a sequential manner, to mitigate data shifts over time and improve model performance. Overall, our study is a crucial step towards the deployment of clinical AI models, by providing strategies and workflows to ensure the safety and efficacy of these models in real-world settings.