PTSD-MDNN : Fusion tardive de réseaux de neurones profonds multimodaux pour la détection du trouble de stress post-traumatique
This work addresses the need for objective and quicker PTSD diagnosis, potentially benefiting teleconsultation, patient journey optimization, and human-robot interaction, but appears incremental as it merges existing unimodal networks.
The authors tackled the problem of diagnosing post-traumatic stress disorder (PTSD) by proposing PTSD-MDNN, a model that fuses multimodal deep neural networks using video and audio inputs, resulting in a low detection error rate.
In order to provide a more objective and quicker way to diagnose post-traumatic stress disorder (PTSD), we present PTSD-MDNN which merges two unimodal convolutional neural networks and which gives low detection error rate. By taking only videos and audios as inputs, the model could be used in the configuration of teleconsultation sessions, in the optimization of patient journeys or for human-robot interaction.