Patient-led development of digital endpoints and the use of computer vision analysis in assessment of motor function in rare diseases

Abstract

Digital health technologies are transforming the way health outcomes are captured and measured. Digital biomarkers may provide more objective measurements than traditional approaches as they encompass continuous and longitudinal data collection and use of automated analysis for data interpretation. In addition, the use of digital health technology allows for home-based disease assessments, which in addition to reducing patient burden from on-site hospital visits, provides a more holistic picture of how the patient feels and functions in the real world. Tools that can robustly capture drug efficacy based on disease-specific outcomes that are meaningful to patients, are going to be key to the successful development of new treatments. This is particularly important for people living with rare and chronic complex conditions, where therapeutic options are limited and need to be developed using a patient-focused approach to achieve the biggest impact. Working in partnership with patient Organisation Duchenne UK, we co-developed a video-based approach, delivered through a new mobile health platform (DMD Home), to assess motor function in patients with Duchenne muscular dystrophy (DMD), a genetic, rare, muscular disease characterized by the progressive loss of muscle function and strength. Motor function tasks were selected to reflect the “transfer stage” of the disease, when patients are no longer able to walk independently but can stand and weight-bear to transfer. This stage is important for patients and families as it represents a significant milestone in the progression of DMD but it is not routinely captured and/or scored by standard DMD clinical and physiotherapy assessments. A total of 62 videos were submitted by eight out of eleven participants who onboarded the app and were analysed with pose estimation software (OpenPose) that led to the extraction of objective, quantitative measures, including time, pattern of movement trajectory, and smoothness and symmetry of movement. Computer vision analysis of video tasks to identify voluntary or compensatory movements within the transfer stage merits further investigation. Longitudinal studies to validate DMD home as a new methodology to predict progression to the non-ambulant stage will be pursued.

A systematic review of the applications of markerless motion capture (MMC) technology for clinical measurement in rehabilitation

“…The rest of the studies were conducted on various other diseases: Fragile X syndrome (FXS) [ 60 ], chronic neck pain [ 61 ], breast cancer [ 9 ], spinal cord injury (SCI) [ 62 ], amyotrophic lateral sclerosis (ALS) [ 63 ], adhesive capsulitis of shoulder (AC) [ 64 ], dystrophinopathy [ 65 ] and neuromotor diseases [ 66 ]. There were also studies that had been conducted on wheelchair users (n = 2) [ 67 , 68 ], people awaiting total knee arthroplasty (TKR) [ 69 ], patients with gait disturbance [ 70 ], patients with neurodevelopment disorders (NDD) [ 71 ], patients with tremor [ 72 ], patients with Duchenne muscular dystrophy (DMD) [ 73 ], patients with cervical dystonia (CD) [ 74 ] and patients with a variety of diagnoses [ 75 ]. Table 1 summarizes the 65 selected studies.…”

“…Fifteen studies focused on comparing the movement patterns of the disease populations and a healthy population, with all of them reporting a significant difference in at least one of the measured parameters including gait parameters, hand movement patterns, head movement patterns and general body movements [ 16 , 20 , 26 , 28 , 41 , 49 , 52 , 55 – 57 , 60 , 61 , 66 , 70 , 71 ]. Fifteen studies applied MMC technology to detect and identify movement limitations or specific movement patterns of patients with certain diseases, and significant parameters that indicate movement abnormity including bradykinesia, shuffling gait, abnormal walking pattern, and tremor were identified [ 9 , 19 , 24 , 29 , 33 – 35 , 37 , 42 – 44 , 51 , 59 , 63 , 73 ]. Two studies used the MMC system to measure range of motion (ROM), and they suggested MMC could be an alternative to the goniometer as a tool for ROM assessment [ 64 , 75 ].…”

“…Twenty studies used Kinect in their research, thus making Kinect the most popular MMC system used in the selected studies [ 9 , 10 , 30 , 31 , 43 , 45 – 49 , 58 , 59 , 62 – 65 , 67 , 68 , 70 , 75 ]. Sixteen studies used camera including RGB camera, digital video camera, GoPro camera and webcam [ 16 – 18 , 20 , 24 , 25 , 29 , 32 , 33 , 35 , 37 , 41 , 51 , 54 , 55 , 71 ], while twelve studies analyzed patients’ movement by using smartphone or mobile tablet videos [ 14 , 19 , 21 , 22 , 27 , 36 , 38 , 44 , 50 , 57 , 72 , 73 ]. Six studies performed the motion analysis from YouTube video or video recordings that captured by nonspecific capturing device [ 23 , 34 , 52 , 53 , 66 , 74 ].…”

Human Pose Estimation for Clinical Analysis of Gait Pathologies

“…Step length (m): anterior-posterior distance between the right heel to the left heel 39 (heel-to-heel distance). 24 Normally, step length is considered to be half of the stride length.…”

“…Duchenne muscular dystrophy is a devastatingly severe, rare genetic condition distinguished by childhood-onset muscle weakness. 24 Duchenne muscular dystrophy almost affects boys, given that the x-chromosome contains the gene that encodes for dystrophin. 12 , 25 On average, around the globe, the existing incidence is estimated to be between 1 in 3500 and 1 in 5000 live male births.…”