Method and system for measuring, predicting, and optimizing human cognitive performance

A system adapted to be worn by a user for providing an alertness level to the user where the alertness level is representative of an ability for the user to perform cognitive functions, the system comprising:

• a user interface having a display and a receiving means for receiving input from the user;
• a motion detection sensor configured to detect movement,
• at least one memory configured to store an alertness model and data associated with the user;
• and
• a processor in electrical communication with said user interface, said motion detection sensor, and said at least one memory;
• said processor configured to
• receive a signal from said motion detection sensor to monitor a level of activity of the user,
• convert the signal from said motion detection sensor into sleep-wake data representing whether the user is asleep or awake based on the level of activity,
• store the sleep-wake data obtained from the signal in said at least one memory,
• when caffeine consumption is received from said receiving means, store the caffeine consumption in said at least one memory as a caffeine consumption data,
• determine an alertness level for the user with the alertness model based on the stored sleep-wake data and the stored caffeine consumption data,
• display the alertness level on said display to the user enabling the user to act on the displayed alertness level to address any fatigue and/or impairment as represented by the displayed alertness level by adjusting a sleep schedule and/or caffeine consumption,
• during an individualization of the alertness model to the user, perform multiple response time tests with said processor and said user interface where the response time test is performed by
• displaying a visual cue on said display,
• receiving a user response to the visual cue through said receiving means,
• calculating a response time, and
• repeating said displaying, receiving and calculating a plurality of times to determine a tested alertness level;
• determine an offset between the model-determined alertness level and the tested alertness level;
• adjust at least one parameter weight in the alertness model based on the determined offset to individualize the alertness model for a sleep-loss phenotype of the user;
• and
• wherein the alertness model includes
• a homeostatic component having a sleep debt lower asymptote that varies based on a sleep debt for the user and a sleep debt upper asymptote, the homeostatic component increases exponentially with time awake and decreases exponentially with sleep time to a basal value, the homeostatic component uses the sleep-wake data;
• a circadian component with an adjustable circadian amplitude;
• and
• a caffeine component that provides a multiplicative impact on a sum of the homeostatic component and the circadian component, the caffeine component uses caffeine consumption data present in said at least one memory at distinct dosage times to provide an exponential decay of the caffeine consumption over time, the caffeine component is equal to 1 prior to a first time of distinct caffeine consumption data.