PubMed · 2022 · 35 citations · 15 references
ComputingBiomedical InformaticsHealth InformaticsClinical Decision SupportClinical InformaticsElectronic Health RecordsClinical Natural Language ProcessingDeep LearningElectronic Health Record AnalyticsPredictive Health ModelingElectronic Health Record Feature ExtractionFeature Engineering For Healthcare DataFine-tuningIn-hospital MortalityMultimodal Electronic Health Record IntegrationNarrative Clinical NotesPredictionPretraining
Deep-learning-based clinical decision support using structured electronic health records (EHR) has been an active research area for predicting risks of mortality and diseases. Meanwhile, large amounts of narrative clinical notes provide complementary information, but are often not integrated into predictive models. In this paper, we provide a novel multimodal transformer to fuse clinical notes and structured EHR data for better prediction of in-hospital mortality. To improve interpretability, we propose an integrated gradients (IG) method to select important words in clinical notes and discover the critical structured EHR features with Shapley values. These important words and clinical features are visualized to assist with interpretation of the prediction outcomes. We also investigate the significance of domain adaptive pretraining and task adaptive fine-tuning on the Clinical BERT, which is used to learn the representations of clinical notes. Experiments demonstrated that our model outperforms other methods (AUCPR: 0.538, AUCROC: 0.877, F1:0.490).
15
MIMIC-III, a freely accessible critical care database
Alistair E. W. Johnson, Tom Pollard, Lu Shen et al. · Scientific Data · 2016 · 8.1K citations · Full text
Integrating Multimodal Information in Large Pretrained Transformers
Wasifur Rahman, Md. Kamrul Hasan, Sangwu Lee et al. · 2020 · 604 citations · Full text
BEHRT: Transformer for Electronic Health Records
Yikuan Li, Shishir Rao, José Roberto Ayala Solares et al. · Scientific Reports · 2020 · 528 citations · Full text