+1 Recommend
0 collections
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Evaluation of smartphone‐based testing to generate exploratory outcome measures in a phase 1 Parkinson's disease clinical trial

      , PhD 1 , , PhD 1 , , MSc 1 , , MSc 1 , , MSc 1 , , PhD 1 , , PhD 1 , , PhD 1 , , PhD 1 , , MD 1 , , BS 2 , , MA 1 , , PhD 1 , , MD 2 , , MD 2 , 3 , , PhD 4 , , MD 5 , , PhD 1 , , PhD 1 , , PhD 1 , , PhD , 1 , , PhD 1

      Movement Disorders

      John Wiley and Sons Inc.

      digital health, digital biomarkers, Parkinson's disease, clinical trial, remote patient monitoring

      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.


          Background: Ubiquitous digital technologies such as smartphone sensors promise to fundamentally change biomedical research and treatment monitoring in neurological diseases such as PD, creating a new domain of digital biomarkers.

          Objectives: The present study assessed the feasibility, reliability, and validity of smartphone‐based digital biomarkers of PD in a clinical trial setting.

          Methods: During a 6‐month, phase 1b clinical trial with 44 Parkinson participants, and an independent, 45‐day study in 35 age‐matched healthy controls, participants completed six daily motor active tests (sustained phonation, rest tremor, postural tremor, finger‐tapping, balance, and gait), then carried the smartphone during the day (passive monitoring), enabling assessment of, for example, time spent walking and sit‐to‐stand transitions by gyroscopic and accelerometer data.

          Results: Adherence was acceptable: Patients completed active testing on average 3.5 of 7 times/week. Sensor‐based features showed moderate‐to‐excellent test‐retest reliability (average intraclass correlation coefficient = 0.84). All active and passive features significantly differentiated PD from controls with P < 0.005. All active test features except sustained phonation were significantly related to corresponding International Parkinson and Movement Disorder Society–Sponsored UPRDS clinical severity ratings. On passive monitoring, time spent walking had a significant ( P = 0.005) relationship with average postural instability and gait disturbance scores. Of note, for all smartphone active and passive features except postural tremor, the monitoring procedure detected abnormalities even in those Parkinson participants scored as having no signs in the corresponding International Parkinson and Movement Disorder Society–Sponsored UPRDS items at the site visit.

          Conclusions: These findings demonstrate the feasibility of smartphone‐based digital biomarkers and indicate that smartphone‐sensor technologies provide reliable, valid, clinically meaningful, and highly sensitive phenotypic data in Parkinson's disease. © 2018 The Authors. Movement Disorders published by Wiley Periodicals, Inc. on behalf of International Parkinson and Movement Disorder Society.

          Related collections

          Most cited references 58

          • Record: found
          • Abstract: found
          • Article: found
          Is Open Access

          Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

          Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters’ influence on performance to provide insights about their optimisation.
            • Record: found
            • Abstract: found
            • Article: not found

            The pathogenesis of gait hypokinesia in Parkinson's disease.

            To identify the fundamental deficit in gait hypokinesia in Parkinson's disease (PD) we conducted a series of experiments that compared PD subjects with age- and height-matched controls in their capacity to regulate either stride length, cadence (steps per minute) or both parameters to three conditions. In the first condition the spatial and temporal parameters of gait were documented for slow, normal and fast walking. The second condition compared parkinsonian gait with the walking pattern of elderly controls whilst controlling for two movement speeds: fast (control preferred) speed and slow (PD preferred) speed. In the third condition we examined the ability of PD subjects to regulate one parameter (e.g. stride length) when the other two parameters (e.g. velocity and cadence) were held at control values. A total of 34 PD subjects and 34 matched controls were tested using a footswitch stride analysis system that measured the spatial and temporal parameters of gait for a series of 10 m walking trials. Parkinsonian subjects exhibited marked gait hypokinesia in each of the experiments. Although they retained the capacity to vary their gait velocity in a similar manner to controls, their range of response was reduced. Within the lower velocity range, PD subjects could vary their speed of walking by adjusting cadence and, to a lesser extent, stride length. However, when the speed of walking was controlled, the stride length was found to be shorter and the cadence higher in PD subjects than in controls. Stride length could not be upgraded by internal control mechanisms in response to a fixed cadence set for age and height-matched velocity. In contrast, cadence was readily modulated by external cues and by internal control mechanisms when stride length was fixed to the values obtained for age- and height-matched controls. It was concluded that regulation of stride length is the fundamental problem in gait hypokinesia and the relative increase in cadence exhibited by PD subjects is a compensatory mechanism for the difficulty in regulating stride length. These findings are discussed in the context of the hypothesized role of the basal ganglia in generating internal cues for the maintenance of the gait sequence and in relation to the structuring of movement rehabilitation strategies.
              • Record: found
              • Abstract: found
              • Article: not found

              Accelerometer and rate gyroscope measurement of kinematics: an inexpensive alternative to optical motion analysis systems.

              A general-purpose system to obtain the kinematics of gait in the sagittal plane based on body-mounted sensors was developed. It consisted of four uniaxial seismic accelerometers and one rate gyroscope per body segment. Tests were done with 10 young healthy volunteers, walking at five different speeds on a treadmill. In order to study the system's accuracy, measurements were made with an optic, passive-marker system and the body-mounted system, simultaneously. In all the comparison cases, the curves obtained from the two systems were very close, showing root mean square errors representing <7% full range in 75% of the cases (overall mean 6.64%, standard deviation 4.13%) and high coefficients of multiple correlation in 100% of cases (overall mean 0.9812, standard deviation 0.02). Calibration of the body-mounted system is done against gravity. The body-mounted sensors do not hinder natural movement. The calculation algorithms are computationally demanding and only are applicable off-line. The body-mounted sensors are accurate, inexpensive and portable and allow long-term recordings in clinical, sport and ergonomics settings.

                Author and article information

                Mov Disord
                Mov. Disord
                Movement Disorders
                John Wiley and Sons Inc. (Hoboken )
                27 April 2018
                August 2018
                : 33
                : 8 ( doiID: 10.1002/mds.v33.8 )
                : 1287-1297
                [ 1 ] Roche Pharma Research and Early Development, pRED Informatics, Pharmaceutical Sciences, Clinical Pharmacology, and Neuroscience, Ophthalmology, and Rare Diseases Discovery and Translational Area, Roche Innovation Center Basel, F. Hoffmann‐La Roche Ltd. Basel Switzerland
                [ 2 ] Prothena Biosciences Inc. South San Francisco California USA
                [ 3 ] Global R&D Partners, LLC San Diego California USA
                [ 4 ] Felix Platter Hospital, University Center for Medicine of Aging, Memory Clinic, Basel, Switzerland; University of Basel, Faculty of Psychology Basel Switzerland
                [ 5 ] Department of Neurology McGill University, Montreal General Hospital Montreal Quebec Canada
                Author notes
                [* ] Correspondence to: Dr. Christian Gossens, Roche Pharma Research and Early Development, Roche Innovation Center Basel, F. Hoffmann‐La Roche Ltd., Grenzacherstrasse 124, 4070 Basel, Switzerland; E‐mail: christian.gossens@
                © 2018 The Authors. Movement Disorders published by Wiley Periodicals, Inc. on behalf of International Parkinson and Movement Disorder Society.

                This is an open access article under the terms of the License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

                Page count
                Figures: 3, Tables: 2, Pages: 11, Words: 7889
                Funded by: F. Hoffmann‐La Roche Ltd.
                Funded by: Prothena Biosciences Inc.
                Research Article
                Regular Issue Articles
                Research Articles
                Custom metadata
                August 2018
                Converter:WILEY_ML3GV2_TO_NLMPMC version:version=5.5.0 mode:remove_FC converted:08.10.2018


                Comment on this article