Multimodal collaborative brain-computer interfaces aid human-machine team decision-making in a pandemic scenario.

Area of Science:

• Neuroscience
• Human-Computer Interaction
• Decision Science

Background:

• Effective team decision-making relies on trust and opinion integration.
• Assessing critical situations, like pandemics, demands accurate and reliable collaborative decisions.

Purpose of the Study:

• To introduce a multimodal brain-computer interface (BCI) for human-artificial agent teams.
• To improve decision accuracy in danger zone assessments during a pandemic scenario.

Main Methods:

• Simultaneous electroencephalography/functional MRI (EEG/fMRI) to identify neural markers of confidence and trust.
• Machine learning to decode neural signatures for BCI-augmented decision-making.
• Comparison of BCI-assisted teams against traditional team decision-making strategies.

Main Results:

• BCI-assisted teams achieved significantly higher decision accuracy compared to traditional teams.
• The BCI effectively captured trial-by-trial neural correlates of confidence.
• Distinct neural circuits for accuracy and confidence were identified, with the superior parietal lobule playing a key role.

Conclusions:

• Multimodal, collaborative BCIs can optimize decision-making in critical settings.
• BCIs enhance human-artificial agent team performance by leveraging neural insights into confidence and trust.
• This technology offers a pathway for augmented decision strategies in complex environments.