Interpretable Deep Learning System for Identifying Critical Patients Through the Prediction of Triage Level, Hospitalization, and Length of Stay: Prospective Study.
Yu-Ting LinYuan-Xiang DengChu-Lin TsaiChien-Hua HuangLi-Chen FuPublished in: JMIR medical informatics (2024)
Our system improved the prediction of 3 different medical outcomes when compared with other machine learning methods. With the pretrained vital sign encoder and repretrained mask language modeling MacBERT encoder, our multimodality model can provide a deeper insight into the characteristics of electronic health records. Additionally, by providing interpretability, we believe that the proposed system can assist nursing staff and physicians in taking appropriate medical decisions.
Keyphrases
- electronic health record
- machine learning
- healthcare
- deep learning
- end stage renal disease
- emergency department
- ejection fraction
- newly diagnosed
- primary care
- artificial intelligence
- mental health
- autism spectrum disorder
- prognostic factors
- peritoneal dialysis
- clinical decision support
- convolutional neural network
- type diabetes
- adverse drug
- patient reported outcomes
- insulin resistance
- long term care