Tesi etd-09262022-174027
Link copiato negli appunti
Tipo di tesi
Dottorato
Autore
CAMPAGNINI, SILVIA
URN
etd-09262022-174027
Titolo
Study and evaluation of personalisation of the rehabilitation process using machine learning and biomedical data science for outcome prediction after robot-mediated and technology-based rehabilitation
Settore scientifico disciplinare
ING-IND/34
Corso di studi
Istituto di Biorobotica - PHD IN BIOROBOTICA
Commissione
relatore Prof.ssa CARROZZA, MARIA CHIARA
Parole chiave
- Acquired Brain Injuries
- Data-driven solutions
- Rehabilitation
- Robotics
- Stroke
Data inizio appello
28/11/2022;
Disponibilità
parziale
Riassunto analitico
The personalisation of the treatment is the current goal in healthcare and specifically in rehabilitation medicine, given the evidence of its positive effects on patients’ recovery. Thus the objective of this work was to study and evaluate technologies for the personalisation of the rehabilitation process. The objective of personalisation was pursued with a twofold approach. Firstly, with a direct approach, the work consisted in tailorinig the robot-assisted treatment on the patients' needs. On the other hand, indirectly, the work concerned the development of prognostic models for the clinical outcome that could support the medical decision in the treatment selection and optimisation.
Whilst the research line about robotics mostly involved the realisation of clinical trials for the development or clinical validation of robotic devices, the data-driven research line involved a more articulated pipeline. More in detail, the work included the data collection and definition of study protocols, the application of biostatistical analyses, the validation of machine learning algorithms, and the development of clinical decision support tools for treatment selection.
Whilst the research line about robotics mostly involved the realisation of clinical trials for the development or clinical validation of robotic devices, the data-driven research line involved a more articulated pipeline. More in detail, the work included the data collection and definition of study protocols, the application of biostatistical analyses, the validation of machine learning algorithms, and the development of clinical decision support tools for treatment selection.
File
| Nome file | Dimensione |
|---|---|
Ci sono 1 file riservati su richiesta dell'autore. |
|