Bioengineering 2026, 13(7), 794; https://doi.org/10.3390/bioengineering13070794 - 10 Jul 2026
Abstract
Acute respiratory distress syndrome (ARDS) is associated with mortality rates up to 46% and remains challenging to diagnose early due to overlapping clinical presentations. We propose a dual-system framework for multimodal ARDS diagnosis that integrates a Mamba-Bi-LSTM primary discrimination system with a TreeSHAP-based
[...] Read more.
Acute respiratory distress syndrome (ARDS) is associated with mortality rates up to 46% and remains challenging to diagnose early due to overlapping clinical presentations. We propose a dual-system framework for multimodal ARDS diagnosis that integrates a Mamba-Bi-LSTM primary discrimination system with a TreeSHAP-based verification system whose attribution outputs iteratively refine the primary system’s feature selection gate. The primary system processes heterogeneous clinical inputs—ventilator parameters, blood gas indices, chest imaging, and EEG signals—through a selective state-space Mamba module and bidirectional LSTM layers. The verification system applies TreeSHAP attribution to independently cross-validate primary outputs, provide clinically interpretable evidence, and supply
(This article belongs to the Special Issue Deep Learning for Medical Applications: Challenges and Opportunities)
►
Show Figures
Figure 1
