A data mining approach to identify cognitive NeuroRehabilitation Range in Traumatic Brain Injury patients

21 Cognitive rehabilitation (CR) treatment consists of hierarchically organized tasks that require repetitive 22 use of impaired cognitive functions in a progressively more demanding sequence. Active monitoring of 23 the progress of the subjects is therefore required, and the difficulty of the tasks must be progressively 24 increased, always pushing the subjects to reach a goal just beyond what they can attain. There is an 25 important lack of well-established criteria by which to identify the right tasks to propose to the patient. 26 In this paper, the NeuroRehabilitation Range (NRR) is introduced as a means of identifying formal 27 operational models. These are to provide the therapist with dynamic decision support information for 28 assigning the most appropriate CR plan to each patient. Data mining techniques are used to build 29 data-driven models for NRR. The Sectorized and Annotated Plane (SAP) is proposed as a visual tool by 30 which to identify NRR, and two data-driven methods to build the SAP are introduced and compared. 31 Application to a specific representative cognitive task is presented. The results obtained suggest that 32 the current clinical hypothesis about NRR might be reconsidered. Prior knowledge in the area is taken 33 into account to introduce the number of task executions and task performance into NRR models and a 34 new model is proposed which outperforms the current clinical hypothesis. The NRR is introduced as a 35 key concept to provide an operational model identifying when a patient is experiencing activities in 36 his or her Zone of Proximal Development and, consequently, experiencing maximum improvement. 37 For the first time, data collected through a CR platform has been used to find a model for the NRR. 38 2014 Elsevier Ltd. All rights reserved. 39