We propose a subject-aware contrastive learning deep fusion neural network framework for effectively classifying subjects confidence levels in the perception of visual stimuli. The framework, called WaveFusion, is composed of lightweight convolutional neural networks for per-lead time-frequency analysis and an attention network for integrating the lightweight modalities for final prediction. To facilitate the training of WaveFusion, we incorporate a subject-aware contrastive learning approach by taking advantage of the heterogeneity within a multi-subject electroencephalogram dataset to boost representation learning and classification accuracy. The WaveFusion framework demonstrates high accuracy in classifying confidence levels by achieving a classification accuracy of 95.7% while also identifying influential brain regions.

The ability to deliver drugs with precise dosages at specific time points can significantly improve disease treatment while reducing side effects. Drug encapsulation for gradual delivery has opened the doors for a superior treatment regimen. To expand on this ability, programming bioelectronic devices to deliver small molecules enables ad-hoc personalized therapeutic profiles that are more complex than gradual release. Here, a wearable bioelectronic device with an integrated electrophoretic ion pump that affords on-demand drug delivery with precise dose control is introduced. Delivery of fluoxetine to wounds in mice result in a 27.2% decrease in the macrophage ratio (M1/M2) and a 39.9% increase in re-epithelialization, indicating a shorter inflammatory phase and faster overall healing. Programmable drug delivery using wearable bioelectronics in wounds introduces a broadly applicable strategy for the long-term delivery of a prescribed treatment regimen with minimal external intervention.

Electrical signaling plays a crucial role in the cellular response to tissue injury in wound healing and an external electric field (EF) may expedite the healing process. Here, we have developed a standalone, wearable, and programmable electronic device to administer a well-controlled exogenous EF, aiming to accelerate wound healing in an in vivo mouse model to provide pre-clinical evidence. We monitored the healing process by assessing the re-epithelization rate and the ratio of M1/M2 macrophage phenotypes through histology staining. Following three days of treatment, the M1/M2 macrophage ratio decreased by 30.6% and the re-epithelization in the EF-treated wounds trended towards a non-statically significant 24.2% increase compared to the control. These findings provide point towards the effectiveness of the device in shortening the inflammatory phase by promoting reparative macrophages over inflammatory macrophages, and in speeding up re-epithelialization. Our wearable device supports the rationale for the application of programmed EFs for wound management in vivo and provides an exciting basis for further development of our technology based on the modulation of macrophages and inflammation to better wound healing.