Central nervous system (CNS) diseases are a broad category of neurological disorders affecting the structure or the functionality of the brain or spinal cord. Multiple sclerosis (MS), Parkinson's disease (PD), and essential tremor are only some of the most common disorders causing the reduction of motor capabilities, yet their incidence and prevalence on the population are remarkable. Nowadays, CNS diseases represent one of the major public health challenges: to help with their management, it is important for doctors and people with these long-term conditions to understand how their disease changes over time. To this purpose, several assessment tests are used by clinicians to diagnose and monitor the disorders: however, although such tests are typically administered and performed in supervised environments (such as hospitals), most of the symptoms and episodes happen outside of the healthcare structures. The last decade has seen an increasing diffusion of wireless inertial platforms, and with them an explosion in the capability of monitoring individuals via sensors integrated in smartphones and wearable devices for medical and rehabilitation purposes in the healthcare field. Wearable technologies are typically used in two contexts. In a supervised context, subjects are followed by trained personnel while performing the required tests: by knowing a priori the test conditions and the surrounding environment, it is possible to exploit the wearable devices to extract many useful and disease-specific information. On the contrary, in an unsupervised context (such as home), subjects can be monitored while performing their everyday activities, increasing the probability of bumping into a scenario not replicable in clinic, for which the disease clearly shows itself: due the lack of prior knowledge, only general information about the subject activity can be actually inferred. For these reasons, accurate methods for retrieving information from data need to be designed on the basis of the specific monitored disease and usage context. In addition, other than the definition of the analysis algorithms, the wearable-based systems need to meet specific requirements in order for them to be used as long-term, research-grade monitoring tools. This thesis presents simple, wearable-based methods and algorithms oriented towards the monitoring of patients affected by CNS disorders. Applications range from the detailed analysis of particular diseases performed in supervised environments (e.g. hospital and clinics), to a more general evaluation of the physical performances, potentially adaptable to several movement disorders. Several analysis algorithms as well as a dedicated wearable platform were specifically designed to cover the entire range of the above mentioned use cases, in order to provide medical staff with objective and simple-to-use monitoring tools.

(2019). Monitoring Techniques based on Wearable Inertial Platforms for Patients Affected by Central Nervous System Diseases [doctoral thesis - tesi di dottorato]. Retrieved from http://hdl.handle.net/10446/128627

Monitoring Techniques based on Wearable Inertial Platforms for Patients Affected by Central Nervous System Diseases

Locatelli, Patrick
2019-04-02

Abstract

Central nervous system (CNS) diseases are a broad category of neurological disorders affecting the structure or the functionality of the brain or spinal cord. Multiple sclerosis (MS), Parkinson's disease (PD), and essential tremor are only some of the most common disorders causing the reduction of motor capabilities, yet their incidence and prevalence on the population are remarkable. Nowadays, CNS diseases represent one of the major public health challenges: to help with their management, it is important for doctors and people with these long-term conditions to understand how their disease changes over time. To this purpose, several assessment tests are used by clinicians to diagnose and monitor the disorders: however, although such tests are typically administered and performed in supervised environments (such as hospitals), most of the symptoms and episodes happen outside of the healthcare structures. The last decade has seen an increasing diffusion of wireless inertial platforms, and with them an explosion in the capability of monitoring individuals via sensors integrated in smartphones and wearable devices for medical and rehabilitation purposes in the healthcare field. Wearable technologies are typically used in two contexts. In a supervised context, subjects are followed by trained personnel while performing the required tests: by knowing a priori the test conditions and the surrounding environment, it is possible to exploit the wearable devices to extract many useful and disease-specific information. On the contrary, in an unsupervised context (such as home), subjects can be monitored while performing their everyday activities, increasing the probability of bumping into a scenario not replicable in clinic, for which the disease clearly shows itself: due the lack of prior knowledge, only general information about the subject activity can be actually inferred. For these reasons, accurate methods for retrieving information from data need to be designed on the basis of the specific monitored disease and usage context. In addition, other than the definition of the analysis algorithms, the wearable-based systems need to meet specific requirements in order for them to be used as long-term, research-grade monitoring tools. This thesis presents simple, wearable-based methods and algorithms oriented towards the monitoring of patients affected by CNS disorders. Applications range from the detailed analysis of particular diseases performed in supervised environments (e.g. hospital and clinics), to a more general evaluation of the physical performances, potentially adaptable to several movement disorders. Several analysis algorithms as well as a dedicated wearable platform were specifically designed to cover the entire range of the above mentioned use cases, in order to provide medical staff with objective and simple-to-use monitoring tools.
2-apr-2019
31
2017/2018
INGEGNERIA E SCIENZE APPLICATE
RE, Valerio
TRAVERSI, Gianluca
Locatelli, Patrick
File allegato/i alla scheda:
File Dimensione del file Formato  
TDUnibg_Locatelli-Patrick.pdf

accesso aperto

Versione: postprint - versione referata/accettata senza referaggio
Licenza: Licenza default Aisberg
Dimensione del file 21.3 MB
Formato Adobe PDF
21.3 MB Adobe PDF Visualizza/Apri
Files_Locatelli.zip

Solo gestori di archivio

Versione: non applicabile
Licenza: Licenza default Aisberg
Dimensione del file 23.96 MB
Formato zip
23.96 MB zip   Visualizza/Apri
Pubblicazioni consigliate

Aisberg ©2008 Servizi bibliotecari, Università degli studi di Bergamo | Terms of use/Condizioni di utilizzo

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10446/128627
Citazioni
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact