Constance de Monts
Research Physical Therapist 2, Adult Neurology
All Publications
-
Deep learning models detect neuromuscular disease and quantify functional impairment from video-derived biomechanics data.
bioRxiv : the preprint server for biology
2026
Abstract
Measurements of human movement are critical for evaluating patients with neuromuscular diseases. However, current clinical tools are limited in sensitivity and can fail to detect the full spectrum of movement changes patients may exhibit. These limitations can obscure early signs of decline, delaying interventions that could preserve function and independence. OpenCap-a smartphone application that performs video-based markerless motion capture-can help address this gap by enabling scalable, out-of-lab measurements of human movement. Here, we present a method for both detecting disease and quantifying the severity of impaired movement from smartphone videos of a patient's motion. We used OpenCap to measure kinematics from 337 individuals with diagnoses spanning 12 rare, genetically-defined neuromuscular diseases and 78 age-matched healthy controls. Our dataset is the largest existing publicly available resource of body segment kinematics for this class of diseases. These data were collected in neuromuscular clinics during regular clinic visits as well as at conferences and community events across the United States. We trained deep learning models on these kinematic time series to differentiate between participants with neuromuscular disease and controls (AUROC = 0.97 [0.93-1.00]). We also developed a movement impairment severity score that correlates with both participants' ratings of their own functional abilities (ρ= -0.81, p<0.001) and existing clinical tests of movement capabilities such as run speed (ρ= -0.83, p<0.001). Our methods for detecting disease and deriving quantitative biomarkers of movement impairment from smartphone videos have the potential to complement clinical assessments, inform screening protocols, and improve clinical trial endpoints.
View details for DOI 10.64898/2026.09.30.754736
View details for PubMedID 42856621
View details for PubMedCentralID PMC13648720
-
Gait Speed in Spinal Muscular Atrophy: A Key Vital Sign Linked to Strength and Fatigability.
Muscle & nerve
2026
Abstract
Gait Speed (GS), a valid and reliable indicator of function and health in multiple populations, has not been explored in spinal muscular atrophy (SMA). The purpose of this study was to characterize GS and gait speed reserves (GSR), and explore associations with strength and fatigability in SMA and healthy controls (HC).Data were collected from ambulatory individuals with SMA (n = 14) and controls (HC) (n = 10). Using custom-engineered instrumented insoles, stride velocity (SV) was collected during the Six-Minute Walk Test (6MWT) and 10-m walk/run (10MWR). Three GS variables were identified; SV50th Centile6MWT (SV50C6MWT), 10MWR SV, and SV95th Centile6MWT (SV95C6MWT). Gait speed reserve (GSR) was calculated from 10MWR and SV50C6MWT. Repeated measures analysis of variance assessed differences in GS and GSR across groups. Spearman's Rho was used to assess associations between speed variables and clinical assessments.All speed variables were different within HC (p < 0.001) and SMA (p = 0.002). There was a significant Group × Speed interaction (p < 0.001) with greater differences in HC. GSR was lower in SMA (p < 0.001, d = 2.42). In SMA, thigh strength was associated with all three GS variables and inversely associated with fatigability (p < 0.05). In HC, associations between GS and strength or fatigability were not observed. GSR was not associated with strength, fatigability, or GS in either group.GS is diminished in SMA and correlated with strength and fatigability. While reduced in SMA, GSR was not associated with GS, strength, or function. GS is a key vital sign of health and may be a useful biomarker in SMA.
View details for DOI 10.1002/mus.70380
View details for PubMedID 42728817
-
Towards Real-World, Stride-Level Spatiotemporal and Kinetic Gait Monitoring with AI-Sole: Ecological Validation of COP-Derived Gait Metrics
IEEE. 2026: 289-294
View details for DOI 10.1109/BIOROB66782.2026.11681626
View details for Web of Science ID 001894516200041
-
Video-Based Biomechanical Analysis Captures Disease-Specific Movement Signatures of Different Neuromuscular Diseases.
NEJM AI
2025; 2 (9)
Abstract
Assessing human movement is essential for diagnosing and monitoring movement-related conditions like neuromuscular disorders. Timed function tests (TFTs) are among the most widespread types of assessments due to their speed and simplicity, but they cannot capture disease-specific movement patterns. Conversely, biomechanical analysis can produce sensitive disease-specific biomarkers, but it is traditionally confined to laboratory settings. Recent advances in smartphone video-based biomechanical analysis enable the quantification of three-dimensional movement with the ease and speed required for clinical settings. However, the potential of this technology to offer more sensitive assessments of human function than TFTs remains untested.To compare video-based analysis with TFTs, we collected an observational dataset from 129 individuals: 28 with facioscapulohumeral muscular dystrophy, 58 with myotonic dystrophy, and 43 controls with no diagnosed neuromuscular condition. We used OpenCap, a free open-source software tool, to capture smartphone video-based biomechanics of nine different movements in a median time of 16 minutes per participant. From these recordings, we extracted 34 interpretable movement features. Using these features, we evaluated the ability of video-based biomechanics to reproduce four TFTs (10-meter walk, 10-meter run, timed up-and-go, and 5-times sit-to-stand) while capturing additional disease-specific signatures of movement.Video-based biomechanical analysis reproduced all four TFTs (r>0.98) with similar test-retest reliability. In addition, video metrics outperformed TFTs at disease classification (P=0.021). Unlike TFTs, video-based biomechanical analysis identified disease-specific signatures of movement, such as differences in gait kinematics, that are not evident in TFTs.Video-based biomechanical analysis can complement existing functional movement assessments by capturing more sensitive, disease-specific outcomes from human movement. This technology enables digital health solutions for assessing and monitoring motor function, complementing traditional clinical outcome measures to enhance care, management, and clinical trial design for movement-related conditions. (Funded by the Wu Tsai Human Performance Alliance and others.).
View details for DOI 10.1056/aioa2401137
View details for PubMedID 40926960
View details for PubMedCentralID PMC12416922
-
Video-based biomechanical analysis captures disease-specific movement signatures of different neuromuscular diseases.
bioRxiv : the preprint server for biology
2025
Abstract
Assessing human movement is essential for diagnosing and monitoring movement-related conditions like neuromuscular disorders. Timed function tests (TFTs) are among the most widespread assessments due to their speed and simplicity, but they cannot capture disease-specific movement patterns. Conversely, biomechanical analysis can produce sensitive disease-specific biomarkers but is traditionally confined to laboratory settings. Recent advances in smartphone video-based biomechanical analysis enable quantification of 3D movement with the ease and speed required for clinical settings. However, the potential of this technology to offer more sensitive assessments of human function than TFTs remains untested.To compare video-based analysis against TFTs, we collected an observational dataset from 129 individuals: 28 with facioscapulohumeral muscular dystrophy, 58 with myotonic dystrophy, and 43 controls with no diagnosed neuromuscular condition. We used OpenCap, a free open-source software tool, to capture smartphone video-based biomechanics of nine different movements in a median time of 16 minutes per participant. From these recordings we extracted 34 interpretable movement features. Using these features, we evaluated the ability of video-based biomechanics to reproduce four TFTs (10-meter walk, 10-meter run, timed up-and-go, and 5-time sit-to-stand) while capturing additional disease-specific signatures of movement.Video-based biomechanical analysis reproduced all four TFTs (r > 0.98) with similar test-retest reliability. In addition, video metrics outperformed TFTs at disease classification (p = 0.021). Unlike TFTs, video-based biomechanical analysis identified disease-specific signatures of movement such as differences in gait kinematics that are not evident in TFTs.Video-based biomechanical analysis can complement existing functional movement assessments by capturing more sensitive, disease-specific outcomes from human movement. This technology enables digital health solutions for assessing and monitoring motor function, complementing traditional clinical outcome measures to enhance care, management, and clinical trial design for movement-related conditions.
View details for DOI 10.1101/2024.09.26.613967
View details for PubMedID 40766489
View details for PubMedCentralID PMC12324206
-
Cardiopulmonary Recovery After Maximal Exercise in Individuals with Neuromuscular Disease and Limited Mobility.
Journal of clinical medicine
2025; 14 (12)
Abstract
Background: Individuals with neuromuscular diseases (NMDs) have low physical activity levels and an increased risk of cardiovascular and pulmonary diseases. Respiratory gas kinetics obtained during cardiopulmonary exercise testing (CPET) may provide valuable insights into disease mechanisms and cardiorespiratory fitness in individuals with NMD. Recovery from exercise is an important marker of exercise performance and overall physical health, and impaired recovery is strongly associated with poor health outcomes. This study evaluates recovery metrics in individuals with NMD after performing maximal exertion during CPET. Methods: A total of 34 individuals with NMD and 15 healthy volunteers were recruited for the study. CPET was performed using a wearable metabolic system and a wheelchair-accessible total body trainer to peak exertion. Recovery metrics assessed were (i) the time to reach 50% O2 recovery compared with peak exercise and (ii) the ratios of ventilation and respiratory gases between peak exercise and the highest values observed during recovery (overshoot). Results: The NMD group had a significantly longer time to reach 50% O2 recovery (T1/2 VO2: 105 ± 43.4 vs. 76 ± 36.4 s, p = 0.02), lower respiratory overshoot (17.1 ± 13.0% vs. 28.8 ± 9.03%), and lower ventilation/VO2 (31.9 ± 28.3 vs. 52.2 ± 23.5) compared to the control group. Conclusions: This study observes significantly impaired recovery metrics following peak exercise in individuals with NMD compared to controls. These insights may improve the understanding of exercise recovery and mechanics, thus improving prognostication and optimizing exercise prescriptions for individuals with NMD.
View details for DOI 10.3390/jcm14124190
View details for PubMedID 40565934
-
Exercise And Recovery Ventilatory Responses Between Individuals With Neuromuscular Disease And Healthy Adults
LIPPINCOTT WILLIAMS & WILKINS. 2024: 925-926
View details for Web of Science ID 001315123204328
-
Investigating Recovery From Maximal Exercise In Patients With Neuromuscular Disease
LIPPINCOTT WILLIAMS & WILKINS. 2024: 657
View details for Web of Science ID 001315123203148
-
Towards Video-Based Movement Biomarkers for Neuromuscular Diseases
edited by Pons, J. L., Tornero, J., Akay, M.
SPRINGER INTERNATIONAL PUBLISHING AG. 2024: 501-504
View details for DOI 10.1007/978-3-031-77584-0_98
View details for Web of Science ID 001462655900098
-
Assessing the Assisted Six-Minute Cycling Test as a Measure of Endurance in Non-Ambulatory Patients with Spinal Muscular Atrophy (SMA).
Journal of clinical medicine
2023; 12 (24)
Abstract
Assessing endurance in non-ambulatory individuals with Spinal Muscular Atrophy (SMA) has been challenging due to limited evaluation tools. The Assisted 6-Minute Cycling Test (A6MCT) is an upper limb ergometer assessment used in other neurologic disorders to measure endurance. To study the performance of the A6MCT in the non-ambulatory SMA population, prospective data was collected on 38 individuals with SMA (13 sitters; 25 non-sitters), aged 5 to 74 years (mean = 30.3; SD = 14.1). The clinical measures used were A6MCT, Revised Upper Limb Module (RULM), Adapted Test of Neuromuscular Disorders (ATEND), and Egen Klassifikation Scale 2 (EK2). Perceived fatigue was assessed using the Fatigue Severity Scale (FSS), and effort was assessed using the Rate of Perceived Exertion (RPE). Data were analyzed for: (1) Feasibility, (2) Clinical discrimination, and (3) Associations between A6MCT with clinical characteristics and outcomes. Results showed the A6MCT was feasible for 95% of the tested subjects, discriminated between functional groups (p = 0.0086), and was significantly associated with results obtained from RULM, ATEND, EK2, and Brooke (p < 0.0001; p = 0.029; p < 0.001; p = 0.005). These findings indicate the A6MCT's potential to evaluate muscular endurance in non-ambulatory SMA individuals, complementing clinician-rated assessments. Nevertheless, further validation with a larger dataset is needed for broader application.
View details for DOI 10.3390/jcm12247582
View details for PubMedID 38137651
View details for PubMedCentralID PMC10743820
https://orcid.org/0009-0004-7659-8069