Understanding effects of cognitive rehabilitation under a knowledge discovery approach

• SAIMAP is an innovative combination of pre-processing, clustering, motif discovery and post-processing in a hybrid methodological frame,
• SAIMAP associates sequential patterns of a predefined set of events including high order interactions and cumulative effects.
• Effects of treatment are measured through multi-criteria improvement indicators set, referring tot a predefined set of areas.
• SAIMAP provides the possibility to understand underlying structure in Cognitive Rehabilitation Patterns
• SAIMAP analyses characteristics of different types of treatments. Length of treatment is associated with different treatment schemes
• Decision criteria to understand when long or short treatment is required can be also learned.Shorter treaments work for patients with short-term memory mild impaired; high impairment in recognition memory require longer treatment.
• SAIMAP overcomes classical machine learning approaches for this complex scenarios.SAIMAP is suitable for other research fields out of neuropsychology, provided they fit the formal structure of problem described in the paper.

Traumatic brain injury (TBI) is the leading cause of death and disability in children and young adults worldwide. Cognitive rehabilitation (CR) plans consist of a sequence of CR tasks targeting main cognitive functions. There is not enough on-field experience yet regarding which specific intervention (tasks or exercise assignment) is more appropriate to help therapists to design plans with significant effectiveness on patient improvement. The selection of specific tasks to be prescribed to the patient and the order in which they might be executed is currently decided by the therapists based on their experience.In this paper a new data mining methodology is proposed, combining several tools from Artificial Intelligence, clustering and post-processing analysis to identify regularities in the sequences of tasks in such a way that treatment profiles (classes) can be discovered. Due to the cumulative effect of rehabilitation tasks, small variations within the sequence of tasks performed by the patient do not significantly change the final outcomes in rehabilitation and makes it difficult to find discriminant rules by using the traditional machine learning inductive methods. However, by relaxing the formalization of the problem to find patterns that might include small variations, and introducing motif discovery techniques in the proposed methodology, the complexity of the neurorehabilitation phenomenon can be better captured and a global structure of successful treatment task sequences can be devised.Following this, the relationship between the discovered patterns and the CR treatment response are analyzed, offering a richer perspective than that provided by the single task focus traditionally used in the CR field.The paper provides a definition of the whole methodological approach proposed from a formal point of view, and its application to a real dataset. Comparisons with traditional AI approaches are also presented and the contribution of the proposed methodology to the AI field discussed.