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
- deep learning
- healthcare
- end stage renal disease
- emergency department
- ejection fraction
- primary care
- newly diagnosed
- chronic kidney disease
- autism spectrum disorder
- artificial intelligence
- peritoneal dialysis
- mental health
- prognostic factors
- type diabetes
- quality improvement
- convolutional neural network
- weight loss
- positive airway pressure
- sleep apnea