Abstract: This disclosure provides techniques for efficiently identifying epileptiform discharges in brain scan data. Brain scan data from an epileptic patient is segmented into multiple windows. Features of the data are identified for each window and provided to a machine learning (ML) model trained on labeled brain scan data. The ML model ranks the windows according to the likelihood each contains an epileptiform discharge. The highest-ranked window is shown to a technician trained in interpreting brain scans. The technician provides feedback regarding whether the window contains an epileptiform discharge or not. The ML model is updated by an online learning process based on feedback from the technician. The remaining windows are re-ranked, and the next highest-ranked window is shown to the technician. This process repeats and the ML model improves based on the technician feedback. This greatly reduces the amount of technician time spent reviewing brain scan data.

Abstract: This disclosure provides techniques for efficiently identifying epileptiform discharges in brain scan data. Brain scan data from an epileptic patient is segmented into multiple windows. Features of the data are identified for each window and provided to a machine learning (ML) model trained on labeled brain scan data. The ML model ranks the windows according to the likelihood each contains an epileptiform discharge. The highest-ranked window is shown to a technician trained in interpreting brain scans. The technician provides feedback regarding whether the window contains an epileptiform discharge or not. The ML model is updated by an online learning process based on feedback from the technician. The remaining windows are re-ranked, and the next highest-ranked window is shown to the technician. This process repeats and the ML model improves based on the technician feedback. This greatly reduces the amount of technician time spent reviewing brain scan data.

Abstract: In addition to an original prompt that is manually provided by a user, contextual information is sent to a generative AI to elicit a higher quality response. Sensors collect audio, video, physiological, cognitive, environmental, and digital data from the user. Machine-learning models evaluate the sensor data to infer the emotional state of the user. The emotional state is used to augment the original prompt with contextual information. The augmented prompt is fed into the generative AI to make it context-aware. Accordingly, the generative AI can automatically pick up on non-verbal cues that the user did not manually articulate in the original prompt. Just as a human-to-human conversation involves a combination of verbal and non-verbal communications, the present concepts enable the generative AI to also leverage non-verbal communication when interacting with human users.

Abstract: Biosensing measurements (e.g., heart rate, pupil size, cognitive load, stress level, etc.) are communicated in the context of events that occurred concurrently with the biosensing measurements. The biosensing measurements and the contextual events can be presented in real-time or as historical summaries. Such presentations allow users to easily gain useful insights into which specific events triggered which specific physiological responses in users. Therefore, the present concepts more effectively communicate insights that can be used to change user behavior, modify workflow, design improved products or services, enhance user satisfaction and wellbeing, increase productivity and revenue, and eliminate negative impacts on user's emotions and mental state.

Abstract: The present concepts include a neuroergonomic service that processes multimodal physiological, digital, and/or environmental inputs from a user and predicts cognitive states of the user. Thus, the neuroergonomic service provides personalized feedback to the user about her current mental and physiological wellbeing to enable modulation of mood, stress, attention, and other cognitive measures for improved productivity and satisfaction. The neuroergonomic service utilizes machine learning models that are trained offline using sensor inputs taken from participants in a controlled environment that purposefully induce an array of cognitive states upon the participants.