PhD: Individually tailored digital-motor outcomes in real life

My background

Medicine Made to Measure

• Doctoral network
• Funded by the Marie Curie Actions Scheme
• 10 PhD candidates
• 22 participating organisations

• Aim: to develop
• ASO (antisense oligonucleotide) treatments
• Tailored to single patients of nano-rare diseases

Supervisors

Dr. Sabato Mellone
University of Bologna

Prof. Dr. Matthis Synofzik
University of Tübingen

Prof. Dr. Mats Karlsson
University of Uppsala

Co-supervisors

Carlo Tacconi
mHealth Technologies s.r.l., Bologna

Prof. Dr. Lorenzo Chiari
University of Bologna

PhD Objective

• Robust assessment of motor performance in genetic ataxias
• Based on body-worn sensor recordings in real-life settings
• Sensitive to moderate-term change in a single patient

Spinocerebellar Ataxia (SCA)

• Inherited neurodegenerative disease
• Affects the cerebellum and spinal cord
• Rare disease: ≤5 people per 100,000

Gait features

• Currently ~50 features (+ ~2000 transformations)
• High redundancy

Available data

• Main dataset: gait recordings from Tübingen
• 27 spinocerebellar (pre-)ataxia patients
• 36 healthy controls
• Lab-based & real-life
• Yearly follow-ups over several years

• Existing lab-based movement recordings (PROSPAX)
• ≥25 spastic ataxia patients
• ≥50 healthy controls

• Planned prospective study
• ≥10 ataxia (SCA or AT) patients

Composite features

• Plan: Find the optimal combination of features
• That fits the expected longitudinal delta the closest
• (controls: 0/year, patients: 1/year)

1. Reduce feature space (e.g. factor analysis)
2. Least-squares / SVM / k-NN / …

Latent variable models

• Plan: Model the disease progression as a latent variable
• Model predictions can serve as a test for treatment effect

Context sensitivity

Further gait features