Skip to content
This repository has been archived by the owner on Oct 16, 2021. It is now read-only.

Repo for analysis on mPower Data released by Sage Bionetworks

License

Notifications You must be signed in to change notification settings

khizar-anjum/mPowerAnalysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This is a repository for my final year project. This only contains code and important information that I use for my project. Unfortunately, I cannot share the data, as can only be accessed by going through specific instructions described in [2].

What is the project about?

The project is regarding early diagnosis of Parkinson's disease. Parkinson’s is a neurodegenerative disease that can affect a person’s movement, speech, dexterity, and cognition. Physicians primarily diagnose Parkinson’s disease by performing a clinical assessment of symptoms. However, misdiagnoses are common. One factor that contributes to misdiagnoses is that the symptoms of Parkinson’s disease may not be prominent at the time the clinical assessment is performed [1]. Therefore, we are working on a deep learning approach to distinguish healthy patients from Parkinson’s patients using open-source data from mPower study [2]. This data consists of four different activities which are walking, tapping, memory and voice. Previous work on this data has achieved very impressive performance i.e. 0.85 area under characteristic curve [1]. This previous work uses expert hand-crafted features [3] which may be limiting the full potential of this data as these features can be suboptimal. Our goal is to implement end-to-end deep learning algorithm in order to explore the options for better discrimination between healthy and Parkinson’s patients.

How to Use this code?

This project basically revolves around analysing data collected from Sage-Bionetworks Research Kit App. The data can be accessed by going through these instructions. All contributions or usage of this code are welcome. Please contact me if you have any questions about the project.

References

[1] Schwab, Patrick, and Walter Karlen. "PhoneMD: Learning to Diagnose Parkinson's Disease from Smartphone Data." arXiv preprint arXiv:1810.01485 (2018).

[2] Bot, B. M. et al. The mPower Study, Parkinson Disease Mobile Data Collected Using ResearchKit. Sci. Data 3:160011 doi: 10.1038/sdata.2016.11 (2016).

[3] Arora, S.; Venkataraman, V.; Zhan, A.; Donohue, S.; Biglan, K.; Dorsey, E.; and Little, M. 2015. Detecting and monitoring the symptoms of Parkinson’s disease using smartphones: A pilot study. Parkinsonism & related disorders 21(6):650–653.

About

Repo for analysis on mPower Data released by Sage Bionetworks

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published