Wearable movement-tracking data identify Parkinson’s disease years before clinical diagnosis 2023 Schalkamp et al

Parkinson’s disease is a progressive neurodegenerative movement disorder with a long latent phase and currently no disease-modifying treatments. Reliable predictive biomarkers that could transform efforts to develop neuroprotective treatments remain to be identified.

Using UK Biobank, we investigated the predictive value of accelerometry in identifying prodromal Parkinson’s disease in the general population and compared this digital biomarker with models based on genetics, lifestyle, blood biochemistry or prodromal symptoms data. Machine learning models trained using accelerometry data achieved better test performance in distinguishing both clinically diagnosed Parkinson’s disease (n = 153) (area under precision recall curve (AUPRC) 0.14 ± 0.04) and prodromal Parkinson’s disease (n = 113) up to 7 years pre-diagnosis (AUPRC 0.07 ± 0.03) from the general population (n = 33,009) compared with all other modalities tested (genetics: AUPRC = 0.01 ± 0.00, P = 2.2 × 10−3; lifestyle: AUPRC = 0.03 ± 0.04, P = 2.5 × 10−3; blood biochemistry: AUPRC = 0.01 ± 0.00, P = 4.1 × 10−3; prodromal signs: AUPRC = 0.01 ± 0.00, P = 3.6 × 10−3).

Accelerometry is a potentially important, low-cost screening tool for determining people at risk of developing Parkinson’s disease and identifying participants for clinical trials of neuroprotective treatments.

Paywall, https://www.nature.com/articles/s41591-023-02440-2

 

This result could be useful in showing how useful accelerometry can be in disease states including ME.

Maybe relevant for Sarah Tyson's study.

ETA: Neil Harrison, one of the authors was involved in ME research at Sussex Uni, some of which was funded by AfME.
He gave a talk at one of their AGMs, ?2018, before he moved to Cardiff. He was looking at fMRI and there was inceased activity in the basal ganglia. I asked him about this after the talk, because only one of the two BGs showed this. I can't remember which side. He didn't know why.

 

This really should be applicable to ME. It is quite different from just measuring how much activity people do. The result is the pattern of acceleration identified. PWME ought to have signature pattern, or maybe two or three different patterns.

A study like this for ME would be much cheaper tha complicated lab tests and to my mind much more likely to produce a result.

 

Impressive that they made 103,712 people recruited to the UK Biobank wear an accelerometer for a period of 7 days. Within 2 years,
273 participants were diagnosed with Parkinson's Disease (PD). An additional 196 of participants eventually received a PD diagnosis after those 2 years, forming the prodromal group.

They found that both groups had lower acceleration before they were diagnosed with PD, compared to age- and sex-matched controls. This pattern was not seen in other other diseases such as Alzheimer or Osteoarthritis.


Unfortunately, they do not give an effect size of this difference (and no spread on the graph) but based on the p-values and sample size I think this is a small effect, somewhere around d = 0.2-0.25.

Their classification, with an area under precision recall curve (AUPRC) 0.14 also suggest weak predictive power although I'm not very familiar with this metric.

 

I suspect it is this device, costing 140 pounds each:
https://axivity.com/product/ax3