Background: Early recognition of mild cognitive impairment (MCI) and subtle changes to cognitive abilities that precede an MCI diagnosis has the potential to improve the efficacy of therapeutic treatment programs.Objective: The work addresses mobile games' potential as empirical assessment tools for cognitive processes within the domains of attention, recognition, recall, and memory applied to game strategy. Methods: Two games have been developed with this objective. WarCAT is based on a familiar card game, War, and "Lock Picking" is a search for an optimal score, akin to finding the combination that opens a lock. Both games provide players with immediate feedback but engage different algorithms and heuristics to solve the respective problems at hand. Conclusions:By collecting player data on large scales to allow for baseline establishment of cognitive abilities across demographic (age) profiles, longitudinal performance of individuals and of groups can be established, and from there, the potential exists to employ machine learning methods to detect subtle changes in an individual's cognitive processes over time.

Background: Early recognition of mild cognitive impairment (MCI) and subtle changes to cognitive abilities that precede an MCI diagnosis has the potential to improve the efficacy of therapeutic treatment programs. Objective: The work addresses mobile games' potential as empirical assessment tools for cognitive processes within the domains of attention, recognition, recall, and memory applied to game strategy. Methods: Two games have been developed with this objective. WarCAT is based on a familiar card game, War, and "Lock Picking" is a search for an optimal score, akin to finding the combination that opens a lock. Both games provide players with immediate feedback but engage different algorithms and heuristics to solve the respective problems at hand. Conclusions: By collecting player data on large scales to allow for baseline establishment of cognitive abilities across demographic (age) profiles, longitudinal performance of individuals and of groups can be established, and from there, the potential exists to employ machine learning methods to detect subtle changes in an individual's cognitive processes over time.

This perspective paper presents a simple serious game on a mobile platform (Smartphone game). The game has the integrated capability to track a person's play by storing player metadata on start time, end time, and moves within the game. These data can be analyzed to infer cognitive processes of strategy learning, retention, and recall over a brief period of time for potential future applications in pre-symptomatic assessment of Mild Cognitive Impairment. Through Machine Learning, the data are demonstrated to be of utility in providing a "cognitive fingerprint" of play. The Machine Learning methods used to classify play use synthetic data generated by robots (bots), ranging from bots playing perfectly to bots playing with various degrees of impairment. The findings include guidance on the volume of data required, as well as the features deemed effective for Machine Learning classification of various degrees of bot impairment. The work illustrates several significant considerations when applying Machine Learning to simple serious games and the data they can generate.