New machine learning model could help pinpoint stages of Parkinson’s

News

Author: Sophie BatesPublished: 13 August 2020

Parkinson's LifePrep: Parkinson's LifeCook: Parkinson's LifeServes:

A new machine learning model aims to help clinicians understand how Parkinson’s progresses in an individual, in relation to the emergence of symptoms of the condition.

The model, designed by US technology company IBM in collaboration with US charity The Michael J Fox Foundation (MJFF), assesses how advanced an individual’s Parkinson’s is – and takes into consideration how medication may mask visible symptoms such as tremors. Researchers at IBM plan to train the model using data from people with Parkinson’s, collected by MJFF, to help define each stage of the condition.

Kristen Severson, a postdoctoral researcher at IBM Research said: “In the future, progression models such as ours may help support various clinical applications. For example, once the disease states are learned, clinicians could quantitatively group patients as well as better predict progression – which could potentially help to inform more personalised patient care and management, as well as more effective drug trials.”


Read more:

Can over-the-counter drugs reduce risk of developing genetic Parkinson’s?

US hospital initiative improves on-time administration of Parkinson’s medication

Go Back

Share this story

Comments


Related articles


Eleanor Hogstrom

Interviews

Parkinson’s and end-of-life: “I’m not afraid of dying”

Eleonor Högström on end-of-life preparations

READ MORE
Close-up of African senior man in grey wool jumper leaning on his stick

Global update

How does the impact of DBS vary across Parkinson’s disease subtypes?

Exploring the treatment’s effect on non-motor symptoms

READ MORE
CVT-301 Inhaler lead

Advances

Fast-acting inhalable levodopa produces positive results in clinical trial

Is inhalable levodopa for treating Parkinson’s one step closer?

READ MORE