Longitudinal Monitoring of Progressive Supranuclear Palsy using Body‐Worn Movement Sensors

Abstract

Background We have previously shown that wearable technology and machine learning techniques can accurately discriminate between progressive supranuclear palsy (PSP), Parkinson's disease, and healthy controls. To date these techniques have not been applied in longitudinal studies of disease progression in PSP. Objectives We aimed to establish whether data collected by a body‐worn inertial measurement unit (IMU) network could predict clinical rating scale scores in PSP and whether it could be used to track disease progression. Methods We studied gait and postural stability in 17 participants with PSP over five visits at 3‐month intervals. Participants performed a 2‐minute walk and an assessment of postural stability by standing for 30 seconds with their eyes closed, while wearing an array of six IMUs. Results Thirty‐two gait and posture features were identified, which progressed significantly with time. A simple linear regression model incorporating the three features with the clearest progression pattern was able to detect statistically significant progression 3 months in advance of the clinical scores. A more complex linear regression and a random forest approach did not improve on this. Conclusions The reduced variability of the models, in comparison to clinical rating scales, allows a significant change in disease status from baseline to be observed at an earlier stage. The current study sheds light on the individual features that are important in tracking disease progression. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society

Patients with progressive supranuclear palsy need to be seen sooner and more frequently

“…In an open-ended, free-text survey question, one participant summarized their access to care challenges: “It was very hard to get my mother diagnosed, and there were essentially no treatments once she was. It became our job to explain PSP to most medical providers she encountered.” These clinical journeys and delays to diagnosis echo previous literature [ 4 , 5 , 13 , 14 ].…”

“…Clinical trials in PSP have taught us that clinical rating scales and imaging findings detectably worsen over 6 months [ 3 ], and certain objective gait and balance measures worsen over 3 months [ 4 ]. Thus, if we do not see a patient with PSP every 3–4 months, we may be more reactive to symptoms than proactive.…”

Balance and gait in progressive supranuclear palsy: a narrative review of objective metrics and exercise interventions

“…As part of a larger, longitudinal study in the United Kingdom, the "OxQuip" study, Pereira et al examined longitudinal changes in motor and cognitive symptoms on clinical scales in PSP (28), and then Sotirakis et al (29) built upon this background with longitudinal monitoring of PSP with 6 body-worn, inertial measurement units (IMU) sensors ("Opals, " by APDM). Pereira analyzed the PSPRS, MDS-UPDRS 3, MOCA, and MMSE in 28 subjects with possible or probable PSP by 2017 MDS criteria (with symptom onset at an average of 1.9 years prior to enrollment, but PSP subtypes were not specified) at visits every 3 months for 18 months.…”

“…The Sotrirakis and Abate studies (26,29) both suggest that wearable sensors may be important and more sensitive detectors of disease progression than the PSPRS. Both studies also found that dynamic gait parameters, rather than balance parameters, are related to disease progression.…”

Antiparkinsonian medication masks motor signal progression in de novo patients

“…These rating scales are the current gold standard in clinical practice, but they may be insensitive to small changes in movement in early-stage patients, and can also be affected by inter-rater variability [ [5] , [6] , [7] ]. Wearable movement sensors and digital forms of assessment are becoming increasingly popular in the study of neurodegenerative diseases [ [7] , [8] , [9] , [10] , [11] , [12] , [13] ] because of their precision and objectivity, and have been shown to discriminate between healthy adults and PD patients of different disease severity [ 11 , 14 ]. Three studies have used wearable devices in de novo patients as they are started on medication, but they have only examined two or three timepoints.…”