Automatic planning in cognitive training: application to multiple sclerosis

ABSTRACT

Multiple sclerosis (MS) is the second-most common cause of neurological disability among young adults. Cognitive impairment, which typically worsens over time, is a major symptom of MS. Signs of cognitive impairment can be observed in many cognitive domains, often including executive-function disorders. Planning is one of the main skills related to executive functions and is fundamental for many cognitive and motor tasks. Brain games, initially available in paper-and-pen format, have been designed to improve planning abilities. Current computerized cognitive training tools also include this kind of exercises; however, they have several limitations, which can be addressed exploiting automated planning. This solution enables advanced forms of human-computer interaction, but poses several design challenges. We tested the usability of two cognitive training exercises for executive functions based on automated planning, which include various features and interaction mechanisms. We present the results of a multidomain cognitive training addressed to individuals affected by MS, including the exercise that performed better in the test. The aim of this study is to clarify design issues concerning executive-function exercises based on automated planning, showing that they can be used in a multidomain cognitive training by participants affected by MS.

KEYWORDS:

• Cognitive training
• multiple sclerosis
• executive functions
• planning

Acknowledgments

We would like to thank Dott. Sergio Stecchi: thanks to his idea, this project came into being. We also would like to thank all the AISM Bologna staff involved in the project, Adolfo Balma, Anna Fiorenza, Roberta Gollini, Carlo Mestitz, Manuela Panico, and all the participants. Their contributions were fundamental for the success of this project. Finally, we would like to thank the anonymous referee for their comments, which helped us improve this paper.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This project was partially supported by AIMS Bologna.

Notes on contributors

Mauro Gaspari

Mauro Gaspari is an associate professor at the Department of Computer Science and Engineering of the University of Bologna; his research interests include artificial intelligence, expert systems, AI languages, multi agent systems, cognitive training and health informatics.

Federica Pinardi

Federica Pinardi is a neurologist at the Multiple Sclerosis Rehabilitation UOSI, IRCCS Neurological Science Institute of Bologna; her research interests include multiple Sclerosis, inflammatory diseases of the CNS, cognitive assessment and rehabilitation.

Dario Signorello

Dario Signorello obtained his master degree in Cognitive Applied Psychology at University of Padova; he is currently collaborating through a research fellowship at the Department of General Psychology of the University of Padova.

Franca Stablum

Franca Stablum is a professor in the Department of General Psychology at the University of Padova; her research interests include attention, executive functions, cognitive assessment and rehabilitation.

Sara Zuppiroli

Sara Zuppiroli obtained a PhD in Computer Sciences at University of Bologna; she won a research fellowship at the Department of Computer Science and Engineering of the University of Bologna working on the design of exercises for cognitive rehabilitation using planners.