Filippo Giuseppe Costa
Automatic Differential diagnosis of Parkinson’s Disease through multimodal techniques.
Rel. Gabriella Olmo. Politecnico di Torino, Corso di laurea magistrale in Mechatronic Engineering (Ingegneria Meccatronica), 2024
|
PDF (Tesi_di_laurea)
- Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (1MB) | Preview |
Abstract: |
Parkinson’s disease (PD) is a neurodegenerative disorder that produces both motor and non-motor complications, degrading the quality of life of PD patients. One of the main critical problems regarding this disease is linked to the difficulty of differentiating that from other similar diseases having common symptoms. Recent advances in wearable devices technology and in machine learning, as well as in cognitive and neuropsycological studies, have provided new methods of investigating these crucial differences. The aim of this thesis is to provide a comprehensive review of current applications where a multimodal differential diagnosis have been tested, through video, movement, voice, cognitive and electrophysiological exams, in order to properly recognize and differentiate PD from atypical parkinsonism (AP) and other critical neurodegenerative syndromes, like Alzheimer's Disease (AD). This review provides the reader with a summary of the current studies and applications in the field of differential diagnosis of PD and AP, focusing on multi-modals not yet widely used but potentially promising in terms of reliability, cost and convenience. Following PRISMA (Systematic Reviews and Meta-Analyses) guidelines, fifty-six studies were selected and analyzed. For each study, information on sample size, sensors, diagnostic modes and results according to the specific symptoms under study were extracted and summarized. The majority of studies (43%) were published within the last 3 years, demonstrating the increasing focus on innovative and practical methods for a correct differential diagnosis of PD. Motor symptoms (MS) and Non-motor symptoms (NMS) were treated in equally manner, respectively 52% vs 48%, but for different types of diagnosis (the two most frequently treated were PD vs ET and DLB vs AD). Electrical sensors were the most used technology, followed by inertial and optical sensors. Finally, note that the use of machine-learning algorithms has been used in several studies. The results of this review highlight several challenges related to the use of wearable technology and cognitive/neuropsycological tests in the automatic differential diagnosis of PD, despite the advantages this technology could bring in the development and implementation of automated systems for PD assessment. |
---|---|
Relators: | Gabriella Olmo |
Academic year: | 2023/24 |
Publication type: | Electronic |
Number of Pages: | 84 |
Subjects: | |
Corso di laurea: | Corso di laurea magistrale in Mechatronic Engineering (Ingegneria Meccatronica) |
Classe di laurea: | New organization > Master science > LM-25 - AUTOMATION ENGINEERING |
Aziende collaboratrici: | Politecnico di Torino |
URI: | http://webthesis.biblio.polito.it/id/eprint/31926 |
Modify record (reserved for operators) |