Objective assessment of bradykinesia in Parkinson’s disease using evolutionary algorithms: clinical validation

Abstract

BackgroundThere is an urgent need for developing objective, effective and convenient measurements to help clinicians accurately identify bradykinesia. The purpose of this study is to evaluate the accuracy of an objective approach assessing bradykinesia in finger tapping (FT) that uses evolutionary algorithms (EAs) and explore whether it can be used to identify early stage Parkinson’s disease (PD).MethodsOne hundred and seven PD, 41 essential tremor (ET) patients and 49 normal controls (NC) were recruited. Participants performed a standard FT task with two electromagnetic tracking sensors attached to the thumb and index finger. Readings from the sensors were transmitted to a tablet computer and subsequently analyzed by using EAs. The output from the device (referred to as "PD-Monitor") scaled from − 1 to + 1 (where higher scores indicate greater severity of bradykinesia). Meanwhile, the bradykinesia was rated clinically using the Movement Disorder Society-Sponsored Revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) FT item.ResultsWith an increasing MDS-UPDRS FT score, the PD-Monitor score from the same hand side increased correspondingly. PD-Monitor score correlated well with MDS-UPDRS FT score (right side: r = 0.819, P = 0.000; left side: r = 0.783, P = 0.000). Moreover, PD-Monitor scores in 97 PD patients with MDS-UPDRS FT bradykinesia and each PD subgroup (FT bradykinesia scored from 1 to 3) were all higher than that in NC. Receiver operating characteristic (ROC) curves revealed that PD-Monitor FT scores could detect different severity of bradykinesia with high accuracy (≥89.7%) in the right dominant hand. Furthermore, PD-Monitor scores could discriminate early stage PD from NC, with area under the ROC curve greater than or equal to 0.899. Additionally, ET without bradykinesia could be differentiated from PD by PD-Monitor scores. A positive correlation of PD-Monitor scores with modified Hoehn and Yahr stage was found in the left hand sides.ConclusionsOur study demonstrated that a simple to use device employing classifiers derived from EAs could not only be used to accurately measure different severity of bradykinesia in PD, but also had the potential to differentiate early stage PD from normality.

Role of data measurement characteristics in the accurate detection of Parkinson’s disease symptoms using wearable sensors

“…Other types of sensors, including those measuring bioelectrical activity (electromyography, electroencephalography), have also been used [17][18][19][20]. Results from current state-of-the-art models are encouraging, with accuracies exceeding 85% for detection of tremor and bradykinesia during controlled tasks or free movements [16,21]. These recent results indicate that wearable technologies have become increasingly viable for monitoring PD symptoms in the clinic and community.…”

“…Once trained, these models are used to detect symptom presence and severity for new data. Modeling motor symptoms of PD is primarily conducted using sensors that record body movements, such as accelerometers, gyroscopes, or electromagnetic motion trackers [12][13][14][15][16]. Other types of sensors, including those measuring bioelectrical activity (electromyography, electroencephalography), have also been used [17][18][19][20].…”

Parkinson’s disease in China: a forty-year growing track of bedside work

“…In PD clinics, more and more wearable devices could be applied. PD-Monitor applied with evolutionary algorithm could differentiate early stage PD patients with normality [99]. Spoons to help people with tremor eat food have been on the market.…”

Machine learning discriminates a movement disorder in a zebrafish model of Parkinson's disease

“…Neurodegeneration in PD is characterised by bradykinesia, resting tremor, rigidity and postural instability ( Jankovic, 2008 ); of these, bradykinesia is a key indicative feature ( Postuma et al, 2015 ). Recently, medical diagnosis of bradykinesia has been facilitated with a system called PD-Monitor that employs an evolutionary algorithm (EA) (a form of artificial intelligence or machine learning) to optimise predictive models capable of recognising bradykinesia from finger-tapping tasks ( Gao et al, 2018 ). EAs can diagnose PD in humans with high accuracy from data collected using tracking sensors on the thumb and finger to extract movement data from a finger-tapping exercise performed by PD patients and healthy age-matched controls.…”