Search Articles

View query in Help articles search

Search Results (1 to 1 of 1 Results)

Download search results: CSV END BibTex RIS


Improving the Prognostic Evaluation Precision of Hospital Outcomes for Heart Failure Using Admission Notes and Clinical Tabular Data: Multimodal Deep Learning Model

Improving the Prognostic Evaluation Precision of Hospital Outcomes for Heart Failure Using Admission Notes and Clinical Tabular Data: Multimodal Deep Learning Model

First, we acquired patients’ admission notes and tabular data, and these two single modalities were separately embedded to obtain the feature and status representation. The categorical and continuous variables in tabular data were characterized separately. Next, a feature-fusing DL network was applied to integrate the two modalities and achieved the model development. Then, a fully connected DL network was used to predict the in-hospital outcome, our primary outcome of interest.

Zhenyue Gao, Xiaoli Liu, Yu Kang, Pan Hu, Xiu Zhang, Wei Yan, Muyang Yan, Pengming Yu, Qing Zhang, Wendong Xiao, Zhengbo Zhang

J Med Internet Res 2024;26:e54363