ABSTRACT
The goal of the diagnostic prediction task is to predict what disease patients are likely to have at their next visit, based on their historical electronic medical records. Existing studies mainly conduct the prediction task by separately using discrete medical codes or clinical notes. However, few existing studies fuse multi-modal features from medical codes and clinical notes together for diagnostic prediction. Practically, using multiple modes of EHRs data can obtain more complete patient representation to improve the predictive performance of the model. Therefore, we proposed a Multi-modal intermediate Fusion Model (MFM) to predict patient diagnosis based on diagnostic codes and clinical notes. Specifically, MFM is mainly based on recurrent neural network to model data in different modes to extract effective features. Then, an intermediate fusion module is used to not only extract the global context information of data in each mode, but also capture the correlation between data in different modes. Finally, a multi-modal fusion matrix is generated for diagnosis prediction. Experimental results on a real dataset show that the proposed method improves the prediction performance compared with the baseline methods.
- Shukla S N, Marlin B M. Integrating Physiological Time Series and Clinical Notes with Deep Learning for Improved ICU Mortality Prediction[J]. arXiv preprint arXiv:2003.11059, 2020.Google Scholar
- Niu K, Lu Y, Peng X, Fusion of Sequential Visits and Medical Ontology for Mortality Prediction[J]. Journal of Biomedical Informatics, 2022: 104012.Google Scholar
- Peng X, Long G, Shen T, Mimo: Mutual integration of patient journey and medical ontology for healthcare representation learning[J]. arXiv preprint arXiv:2107.09288, 2021.Google Scholar
- Pei S, Niu K, Peng X, Readmission Prediction with Knowledge Graph Attention and RNN-Based Ordinary Differential Equations[C]//International Conference on Knowledge Science, Engineering and Management. Springer, Cham, 2021: 559-570.Google Scholar
- Peng X, Long G, Shen T, Sequential Diagnosis Prediction with Transformer and Ontological Representation[C]//2021 IEEE International Conference on Data Mining (ICDM). IEEE, 2021: 489-498.Google Scholar
- Lipton Z C, Kale D C, Elkan C, Learning to diagnose with LSTM recurrent neural networks[J]. arXiv preprint arXiv:1511.03677, 2015.Google Scholar
- Yu R, Zheng Y, Zhang R, Using a multi-task recurrent neural network with attention mechanisms to predict hospital mortality of patients[J]. IEEE journal of biomedical and health informatics, 2019, 24(2): 486-492.Google Scholar
- Feng Y, Min X, Chen N, Patient outcome prediction via convolutional neural networks based on multi-granularity medical concept embedding[C]//2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2017: 770-777.Google Scholar
- Ma F, Wang Y, Xiao H, Incorporating medical code descriptions for diagnosis prediction in healthcare[J]. BMC medical informatics and decision making, 2019, 19(6): 1-13.Google Scholar
- Mullenbach J, Wiegreffe S, Duke J, Explainable prediction of medical codes from clinical text[J]. arXiv preprint arXiv:1802.05695, 2018.Google Scholar
- Qiao Z, Wu X, Ge S, Mnn: multimodal attentional neural networks for diagnosis prediction[J]. Extraction, 2019, 1: A1.Google Scholar
- Hao Y, Usama M, Yang J, Recurrent convolutional neural network based multimodal disease risk prediction[J]. Future Generation Computer Systems, 2019, 92: 76-83.Google ScholarDigital Library
- Su L, Hu C, Li G, MSAF: Multimodal Split Attention Fusion[J]. arXiv preprint arXiv:2012.07175, 2020.Google Scholar
- Choi E, Bahadori M T, Searles E, Multi-layer representation learning for medical concepts[C]//proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 2016: 1495-1504.Google Scholar
- Choi E, Bahadori M T, Schuetz A, RETAIN: Interpretable predictive model in healthcare using reverse time attention mechanism. 2016[J]. CoRR: abs/1608.05745.Google Scholar
- Ma F, Chitta R, Zhou J, Dipole: Diagnosis prediction in healthcare via attention-based bidirectional recurrent neural networks[C]//Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining. 2017: 1903-1911.Google Scholar
- Usama M, Ahmad B, Xiao W, Self-attention based recurrent convolutional neural network for disease prediction using healthcare data[J]. Computer methods and programs in biomedicine, 2020, 190: 105191.Google Scholar
- Hosseini A, Davis T, Sarrafzadeh M. Hierarchical target-attentive diagnosis prediction in heterogeneous information networks[C]//2019 International Conference on Data Mining Workshops (ICDMW). IEEE, 2019: 949-957.Google Scholar
Recommendations
MHM: Multi-modal Clinical Data based Hierarchical Multi-label Diagnosis Prediction
SIGIR '20: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information RetrievalDiagnosis prediction aims to forecast diseases that a patient might have in his next hospital visit, which is critical in Clinical Decision Supporting System (CDSS). Existing approaches mainly formulate diagnosis prediction as a multi-label ...
Fusion of sequential visits and medical ontology for mortality prediction
Graphical abstractDisplay Omitted
Highlights- To predict mortality with fusion of sequential visits and medical ontology.
- To ...
AbstractThe goal of mortality prediction task is to predict the future death risk of patients according to their previous Electronic Healthcare Records (EHR). The main challenge of mortality prediction is how to design an accurate and robust ...
Multi-modal deep learning model for auxiliary diagnosis of Alzheimer’s disease
AbstractAlzheimer’s disease (AD) is one of the most difficult to cure diseases. Alzheimer’s disease seriously affects the normal lives of the elderly and their families. The mild cognitive impairment (MCI) is a transitional state between the ...
Comments