Multimodal Deep Learning for ARDS Detection
Preprint
Abstract
Objective Poor outcomes in acute respiratory distress syndrome (ARDS) can be alleviated with tools that support early diagnosis. Current machine learning methods for detecting ARDS do not take full advantage of the multimodality of ARDS pathophysiology. We developed a multimodal deep learning model that uses imaging data, continuously collected ventilation data, and tabular data derived from a patient’s electronic health record (EHR) to make ARDS predictions. Materials and Methods A chest radiograph (x-ray), at least two hours of ventilator waveform (VWD) data within the first 24 hours of intubation, and EHR-derived tabular data were used from 220 patients admitted to the ICU to train a deep learning model. The model uses pretrained encoders for the x-rays and ventilation data and trains a feature extractor on tabular data. Encoded features for a patient are combined to make a single ARDS prediction. Ablation studies for each modality assessed their effect on the model’s predictive capability. Results The trimodal model achieved an area under the receiver operator curve (AUROC) of 0.86 with a 95% confidence interval of 0.01. This was a statistically significant improvement (pDiscussion and Conclusion Our results demonstrate the potential utility of using deep learning to address complex conditions with heterogeneous data. More work is needed to determine the additive effect of modalities on ARDS detection. Our framework can serve as a blueprint for building performant multimodal deep learning models for conditions with small, heterogeneous datasets.Keywords
This publication has 31 references indexed in Scilit:
- Development and validation of deep learning ECG-based prediction of myocardial infarction in emergency department patientsScientific Reports, 2022
- Combining chest X-rays and electronic health record (EHR) data using machine learning to diagnose acute respiratory failureJournal of the American Medical Informatics Association, 2022
- Predicting neurological outcome in comatose patients after cardiac arrest with multiscale deep neural networksResuscitation, 2021
- SciPy 1.0: fundamental algorithms for scientific computing in PythonNature Methods, 2020
- Outcome Prediction in Postanoxic Coma With Deep Learning*Critical Care Medicine, 2019
- Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural networkNature Medicine, 2019
- Deep Residual Learning for Image Recognition2016
- Subphenotypes in acute respiratory distress syndrome: latent class analysis of data from two randomised controlled trialsThe Lancet Respiratory Medicine, 2014
- Acute Respiratory Distress SyndromeJAMA, 2012
- Screening of ARDS patients using standardized ventilator settings: influence on enrollment in a clinical trialIntensive Care Medicine, 2004