Estimating Bradykinesia in Parkinson's Disease with a Minimum Number of Wearable Sensors

Daneault, Jean‐François; Lee, Sunghoon I.; Golabchi, Fatemeh Noushin; Patel, Shyamal; Shih, Ludy C.; Paganoni, Sabrina; Bonato, Paolo

doi:10.1109/chase.2017.94

Cited by 19 publications

(17 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, adding more limb sensors to improve naturalistic PD monitoring is controversial. Although there is evidence supporting the combined use of wrist, ankle [ 32 , 66 ], or insoles [ 67 ] sensory tracking, other reports have not shown improved performance and instead described additional burden to the patient [ 35 , 68 , 69 ].…”

Section: Discussionmentioning

confidence: 99%

Rapid Dynamic Naturalistic Monitoring of Bradykinesia in Parkinson’s Disease Using a Wrist-Worn Accelerometer

Habets

Kubben

Kuijf

et al. 2021

Sensors

View full text Add to dashboard Cite

Motor fluctuations in Parkinson’s disease are characterized by unpredictability in the timing and duration of dopaminergic therapeutic benefits on symptoms, including bradykinesia and rigidity. These fluctuations significantly impair the quality of life of many Parkinson’s patients. However, current clinical evaluation tools are not designed for the continuous, naturalistic (real-world) symptom monitoring needed to optimize clinical therapy to treat fluctuations. Although commercially available wearable motor monitoring, used over multiple days, can augment neurological decision making, the feasibility of rapid and dynamic detection of motor fluctuations is unclear. So far, applied wearable monitoring algorithms are trained on group data. In this study, we investigated the influence of individual model training on short timescale classification of naturalistic bradykinesia fluctuations in Parkinson’s patients using a single-wrist accelerometer. As part of the Parkinson@Home study protocol, 20 Parkinson patients were recorded with bilateral wrist accelerometers for a one hour OFF medication session and a one hour ON medication session during unconstrained activities in their own homes. Kinematic metrics were extracted from the accelerometer data from the bodyside with the largest unilateral bradykinesia fluctuations across medication states. The kinematic accelerometer features were compared over the 1 h duration of recording, and medication-state classification analyses were performed on 1 min segments of data. Then, we analyzed the influence of individual versus group model training, data window length, and total number of training patients included in group model training, on classification. Statistically significant areas under the curves (AUCs) for medication induced bradykinesia fluctuation classification were seen in 85% of the Parkinson patients at the single minute timescale using the group models. Individually trained models performed at the same level as the group trained models (mean AUC both 0.70, standard deviation respectively 0.18 and 0.10) despite the small individual training dataset. AUCs of the group models improved as the length of the feature windows was increased to 300 s, and with additional training patient datasets. We were able to show that medication-induced fluctuations in bradykinesia can be classified using wrist-worn accelerometry at the time scale of a single minute. Rapid, naturalistic Parkinson motor monitoring has the clinical potential to evaluate dynamic symptomatic and therapeutic fluctuations and help tailor treatments on a fast timescale.

show abstract

Section: Discussionmentioning

confidence: 99%

Rapid Dynamic Naturalistic Monitoring of Bradykinesia in Parkinson’s Disease Using a Wrist-Worn Accelerometer

Habets

Kubben

Kuijf

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Further, adding more limb sensors to improve naturalistic PD monitoring is controversial. Although there is evidence supporting the combined use of wrist, ankle 32,58 , or insoles 59 sensory, other reports do not show an improved performance but describe additional burden to the patient 35,60,61 .…”

Section: Future Scientific Opportunities To Improve Naturalistic Pd Monitoring Developmentmentioning

confidence: 99%

Rapid dynamic naturalistic monitoring of bradykinesia in Parkinson’s disease using a wrist-worn accelerometer

Habets

Kubben

Kuijf

et al. 2021

Preprint

View full text Add to dashboard Cite

Introduction: Motor fluctuations in Parkinson's disease are characterized by unpredictability in the timing and duration of dopaminergic therapeutic benefit on symptoms including bradykinesia and rigidity. These fluctuations significantly impair the quality of life of many Parkinson's patients. However, current clinical evaluation tools are not designed for the continuous, naturalistic (real-world) symptom monitoring needed to optimize clinical therapy to treat fluctuations. Although commercially available wearable motor monitoring, used over multiple days, can augment neurological decision making, the feasibility of rapid and dynamic detection of motor fluctuations is unclear. So far, applied wearable monitoring algorithms are trained on group data. Here, we investigate the influence of individual model training on short timescale classification of naturalistic bradykinesia fluctuations in Parkinson's patients using a single wrist-accelerometer. Methods: As part of the Parkinson@Home study protocol, 20 Parkinson patients were recorded with bilateral wrist-accelerometers for a one hour OFF medication session and a one hour ON medication session during unconstrained activities in their own homes. Kinematic metrics were extracted from the accelerometer data from the bodyside with the largest unilateral bradykinesia fluctuations across medication states. The kinematic accelerometer features were compared over the whole one-hour recordings, and medication-state classification analyses were performed on one-minute segments of data. The influence of individual versus group model training, data window length, and total amount of training patients included in group model training on classification was analyzed. Results: Statistically significant areas under the curves (AUCs) for medication induced bradykinesia fluctuation classification were seen in 85% of the Parkinson patients at the single minute timescale using the group models. Individually trained models performed at the same level as the group trained models (mean AUC both 0.70, +/- respectively 0.18 and 0.10) despite the small individual training dataset. AUCs of the group models improved as the length of the feature windows was increased to 300 seconds, and with additional training patient datasets. Conclusion: Medication induced fluctuations in bradykinesia can be classified using wrist worn accelerometery at the time scale of a single minute. Rapid, naturalistic Parkinson motor monitoring has important clinical potential to evaluate dynamic symptomatic and therapeutic fluctuations and help tailor treatments on a fast timescale.

show abstract

“… Reference Movement disorder Sensor Placement Protocol Rigas 2012 [24] Tremor Accelerometers Right and left wrist, right and left leg, chest and waist Postural activities Mariani 2013 [25] Gait Physilog module On-shoe fixation Standard 3-m TUG and gait tests Cole 2014 [26] Tremor & Dyskinesia Triaxial accelerometers and sEMG Wrist unconstrained activities of daily living in home environment Bernard 2015 [27] Motor response fluctuations Triaxial accelerometer Lower back Walking and being inactive (i.e. lying, sitting) Lennon 2015 [28] Dyskineisa Accelerometer & gyroscopes Wrists and ankles Daily life activities Jalloul 2015 [29] , [30] Dyskinesia Shimmer IMUs Ankle, hip, thigh, neck, wrist and arm Simple daily life activities Howcroft 2016 [31] Gait Pressure-sensing insoles and Triaxial accelerometers Head, pelvis, and Left and right shanks Dual-Task gait exercises Bourke 2016 [32] Fall detection Triaxial accelerometer and triaxial gyroscope L5 lumbar position Activities of daily living Kobsar 2017 [33] Knee Osteoarthritis Accelerometers Back, thigh and shank Hip-strengthening exercise intervention Denault 2017 [34] Bradykinesia Triaxial accelerometers Left & right upper arm, left & right forearm, left & right thigh, left & right hank Clinical evaluation …”

Section: Clinical Applications Of Wearable Sensorsmentioning

confidence: 99%

“…Another method for the detection of dyskinesia in PD patients is introduced in where activity classification in done prior to the detection of dyskinesia in order to enhance the accuracy of the system [29] , [30] . While accelerometer data was used to estimate clinical scores of bradykinesia and showed good correlation with limb-specific scores [34] .…”

Section: Clinical Applications Of Wearable Sensorsmentioning

confidence: 99%

Wearable sensors for the monitoring of movement disorders

Jalloul

2018

Biomedical Journal

View full text Add to dashboard Cite

This paper offers a review of the implementation of current wearable sensing technologies in monitoring the movement and activity of patients suffering from movement disorders. Recent literature has focused on incorporating simple and reliable wearable technologies for the continuous and objective monitoring of patient movement during normal daily activities. However, the use of such wearable sensing technologies has yet to find its way to clinical practice. In the following, the basic elements of such monitoring systems and their applications are introduced, and a discussion regarding current clinical applications is presented.

show abstract

Estimating Bradykinesia in Parkinson's Disease with a Minimum Number of Wearable Sensors

Cited by 19 publications

References 7 publications

Rapid Dynamic Naturalistic Monitoring of Bradykinesia in Parkinson’s Disease Using a Wrist-Worn Accelerometer

Rapid Dynamic Naturalistic Monitoring of Bradykinesia in Parkinson’s Disease Using a Wrist-Worn Accelerometer

Rapid dynamic naturalistic monitoring of bradykinesia in Parkinson’s disease using a wrist-worn accelerometer

Wearable sensors for the monitoring of movement disorders

Contact Info

Product

Resources

About