Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation

Authors: Wenfang Yao, Chen Liu, Kejing Yin, William Cheung, Jing Qin

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments using MIMIC datasets show that the proposed model could effectively address asynchronicity in multimodal fusion and consistently outperform existing methods.
Researcher Affiliation Academia 1School of Nursing, The Hong Kong Polytechnic University 2Department of Computer Science, Hong Kong Baptist University 3School of Software Engineering, South China University of Technology
Pseudocode No The paper describes methods in prose, but does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes The code is available at https://github.com/Chenliu-svg/DDL-CXR.
Open Datasets Yes We empirically evaluate the clinical predictive performance of DDL-CXR using MIMIC-IV [50] and MIMIC-CXR [18]4. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports.
Dataset Splits Yes The dataset is randomly split by the patient identifier with a ratio of 24:4:7 for training, validation, and testing, which avoids patient overlapping between subsets.
Hardware Specification Yes The training and validation processes are executed on a server equipped with a RTX 4090-24GB GPU card and a 16 v CPU Intel Xeon Processor.
Software Dependencies Yes The method is implemented using Py Torch 1.9.1 and Py Torch-Lightning 1.4.2.
Experiment Setup Yes The Transformer f EHR cond is designed with one layer, a model dimension d set to 128, and a maximum EHR data length of 70. The UNet model ϵθ features an input channel of 8 and an output channel of 4. [...] The model is trained for 200 epochs with a batch size of 32, and the model with the smallest composite loss on the validation set is selected for subsequent latent Chest X-ray (CXR) generation. We set the hyperparameters α to 0.2, and β to 0.5, empirically.