Multimodal spatiotemporal graph neural networks for improved prediction of 30-day all-cause hospital readmission

  title={Multimodal spatiotemporal graph neural networks for improved prediction of 30-day all-cause hospital readmission},
  author={Siyi Tang and Amara Tariq and Jared A. Dunnmon and Umesh Sharma and Praneetha Elugunti and Daniel L. Rubin and Bhavik N. Patel and Imon Banerjee},
Measures to predict 30-day readmission are considered an important quality factor for hospitals as accurate predictions can reduce the overall cost of care by identifying high risk patients before they are discharged. While recent deep learning-based studies have shown promising empirical results on readmission prediction, several limitations exist that may hinder widespread clinical utility, such as: (a) only patients with certain conditions are considered, (b) existing approaches do not… 

Figures and Tables from this paper


Predicting Hospital Readmission via Cost-Sensitive Deep Learning
It is found that early prediction of readmission is possible and when compared with state-of-the-art existing methods used by hospitals, the methods perform significantly better.
Predicting 30-day hospital readmissions using artificial neural networks with medical code embedding
It is shown that unsupervised Global Vector for Word Representations embedding representations of administrative claims data combined with artificial neural network classification models significantly improves prediction of 30-day readmission, suggesting that prediction models that incorporate new methods classify hospitals differently than traditional regression-based approaches and that their role in assessing hospital performance warrants further investigation.
DeepNote-GNN: predicting hospital readmission using clinical notes and patient network
A novel hybrid deep learning model that integrates clinical notes information and patient network topological structure to improve 30-day hospital readmission prediction is proposed, and it is demonstrated that DeepNote-GNN achieves superior results compared to the state-of-the-art baselines on the 30- days readmission task.
Neural networks versus Logistic regression for 30 days all-cause readmission prediction
It is concluded that data from patient timelines improve 30 day readmission prediction, that a logistic regression with LASSO has equal performance to the best neural network model and that the use of administrative data result in competitive performance compared to published approaches based on richer clinical datasets.
How Good Is Machine Learning in Predicting All-Cause 30-Day Hospital Readmission? Evidence From Administrative Data.
Scalable and accurate deep learning with electronic health records
A representation of patients’ entire raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format is proposed, and it is demonstrated that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization.
Combining structured and unstructured data for predictive models: a deep learning approach
This research proposed 2 general-purpose multi-modal neural network architectures to enhance patient representation learning by combining sequential unstructured notes with structured data to improve the performance of prediction models and reduce errors.