Publications
1.
Domain generalization for enhanced predictions of hospital readmission on unseen domains among patients with diabetes Journal Article
In: Artificial Intelligence in Medicine, vol. 158, pp. 103010, 2024.
@article{nokey,
title = {Domain generalization for enhanced predictions of hospital readmission on unseen domains among patients with diabetes},
author = {Ameen Abdel Hai and Mark G. Weiner and Alice Livshits and Jeremiah R. Brown and Anuradha Paranjape and Wenke Hwang and Lester H. Kirchner and Nestoras Mathioudakis and Esra Karslioglu French and Zoran Obradovic and Daniel J. Rubin},
doi = {10.1016/j.artmed.2024.103010},
year = {2024},
date = {2024-11-10},
urldate = {2024-11-10},
journal = {Artificial Intelligence in Medicine},
volume = {158},
pages = {103010},
abstract = {A prediction model to assess the risk of hospital readmission can be valuable to identify patients who may benefit from extra care. Developing hospital-specific readmission risk prediction models using local data is not feasible for many institutions. Models developed on data from one hospital may not generalize well to another hospital. There is a lack of an end-to-end adaptable readmission model that can generalize to unseen test domains. We propose an early readmission risk domain generalization network, ERR-DGN, for cross-domain knowledge transfer. ERR-DGN internalizes the shared patterns and characteristics that are consistent across source domains, enabling it to adapt to a new domain. It transforms source datasets to a common embedding space while capturing relevant temporal long-term dependencies of sequential data. Domain generalization is then applied on domain-specific fully connected linear layers. The model is optimized by a loss function that integrates distribution discrepancy loss to match the mean embeddings of multiple source distributions with the task-specific loss. A model was developed using electronic health record (EHR) data of 201,688 patients with diabetes across urban, suburban, rural, and mixed hospital systems to enhance 30-day readmission predictions among patients with diabetes on 67,066 unseen patients at a rural hospital. We also explored how model performance varied by the number of sites and over time. The proposed method outperformed the baseline models, yielding a 6 % increase in F1-score (0.79 ± 0.006 vs. 0.73 ± 0.007). Model performance peaked with the inclusion of three sites. Performance of the model was relatively stable for 3 years then declined at 4 years. ERR-DGN may be a proficient tool for learning data from multiple sites and subsequently applying a hospitalization readmission prediction model to a new site. Including a relatively small number of varied sites may be sufficient to ac},
keywords = {deep learning, diabetes mellitus, domain generalization},
pubstate = {published},
tppubtype = {article}
}
A prediction model to assess the risk of hospital readmission can be valuable to identify patients who may benefit from extra care. Developing hospital-specific readmission risk prediction models using local data is not feasible for many institutions. Models developed on data from one hospital may not generalize well to another hospital. There is a lack of an end-to-end adaptable readmission model that can generalize to unseen test domains. We propose an early readmission risk domain generalization network, ERR-DGN, for cross-domain knowledge transfer. ERR-DGN internalizes the shared patterns and characteristics that are consistent across source domains, enabling it to adapt to a new domain. It transforms source datasets to a common embedding space while capturing relevant temporal long-term dependencies of sequential data. Domain generalization is then applied on domain-specific fully connected linear layers. The model is optimized by a loss function that integrates distribution discrepancy loss to match the mean embeddings of multiple source distributions with the task-specific loss. A model was developed using electronic health record (EHR) data of 201,688 patients with diabetes across urban, suburban, rural, and mixed hospital systems to enhance 30-day readmission predictions among patients with diabetes on 67,066 unseen patients at a rural hospital. We also explored how model performance varied by the number of sites and over time. The proposed method outperformed the baseline models, yielding a 6 % increase in F1-score (0.79 ± 0.006 vs. 0.73 ± 0.007). Model performance peaked with the inclusion of three sites. Performance of the model was relatively stable for 3 years then declined at 4 years. ERR-DGN may be a proficient tool for learning data from multiple sites and subsequently applying a hospitalization readmission prediction model to a new site. Including a relatively small number of varied sites may be sufficient to ac