Development and Validation of a Deep Learning Method to Predict Cerebral Palsy From Spontaneous Movements in Infants at High Risk

Groos, Daniel; Adde, Lars; Aubert, Sindre; Boswell, Lynn; Regnier, Raye-Ann de; Fjørtoft, Toril; Gaebler‐Spira, Deborah; Haukeland, Andreas; Loennecken, Marianne; Msall, Michael E.; Møinichen, Unn Inger; Pascal, Aurelie; Peyton, Colleen; Ramampiaro, Heri; Schreiber, Michael D.; Silberg, Inger Elisabeth; Songstad, Nils Thomas; Thomas, Niranjan; Broeck, Christine Van den; Øberg, Gunn Kristin; Ihlen, Espen Alexander F.; Støen, Ragnhild

doi:10.1001/jamanetworkopen.2022.21325

Cited by 32 publications

(23 citation statements)

References 63 publications

(150 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent evidence supports the hypothesis that epigenetic phenomena, including DNA methylation, histone modifications, and regulatory noncoding RNAs, may contribute to musculoskeletal abnormalities of spastic CP [31]. A novel deep learning-based method may early identify CP at at least 12 months, based on videos of infants' spontaneous movements at 9-18 weeks with predictive accuracy on external validation, but it was not focused on spasticity prediction [32].…”

Section: Prediction Of Spasticitymentioning

confidence: 98%

Spasticity following brain and spinal cord injury: assessment and treatment

Tamburin

Filippetti

Mantovani

et al. 2022

Current Opinion in Neurology

View full text Add to dashboard Cite

Purpose of reviewSpasticity is a common sequela of brain and spinal cord injury and contributes to disability, reduces quality of life, and increases economic burden. Spasticity is still incompletely recognized and undertreated. We will provide an overview of recent published data on the definition, assessment, and prediction, therapeutic advances, with a focus on promising new approaches, and telemedicine applications for spasticity.Recent findingsTwo new definitions of spasticity have been recently proposed, but operational criteria should be developed, and test–retest and inter-rater reliability should be explored. Cannabinoids proved to be effective in spasticity in multiple sclerosis, but evidence in other types of spasticity is lacking. Botulinum neurotoxin injection is the first-line therapy for focal spasticity, and recent literature focused on optimizing its efficacy. Several pharmacological, interventional, and nonpharmacological therapeutic approaches for spasticity have been explored but low-quality evidence impedes solid conclusions on their efficacy. The recent COVID-19 pandemic yielded guidelines/recommendations for the use of telemedicine in spasticity.SummaryDespite the frequency of spasticity, robust diagnostic criteria and reliable assessment scales are required. High-quality studies are needed to support the efficacy of current treatments for spasticity. Future studies should explore telemedicine tools for spasticity assessment and treatment.

show abstract

Section: Prediction Of Spasticitymentioning

confidence: 98%

Spasticity following brain and spinal cord injury: assessment and treatment

Tamburin

Filippetti

Mantovani

et al. 2022

Current Opinion in Neurology

View full text Add to dashboard Cite

show abstract

“…Infants had a video from GCA 9 to 18 weeks assessed with the General Movement Assessment and were evaluated for a diagnosis of CP after GCA 12 months. Overall, the DL model had a sensitivity of 71.4% (95% CI, 47.8%-88.7%) and specificity of 94.1% (95% CI, 88.2%-97.6%) . Furthermore, the DL method differentiated among infants who developed ambulatory and nonambulatory CP, as well as unilateral and bilateral CP …”

mentioning

confidence: 94%

“…Overall, the DL model had a sensitivity of 71.4% (95% CI, 47.8%-88.7%) and specificity of 94.1% (95% CI, 88.2%-97.6%) . Furthermore, the DL method differentiated among infants who developed ambulatory and nonambulatory CP, as well as unilateral and bilateral CP …”

mentioning

confidence: 94%

See 1 more Smart Citation

Application of Video-Based Deep Learning for Early Diagnosis of Neurological Disorders

Massaad

Shin

2022

JAMA Netw Open

View full text Add to dashboard Cite

The study by Groos et al 1 reported that deep learning (DL)-based assessments of videos of spontaneous movements at gestational corrected age (GCA) 3 months could support early detection of cerebral palsy (CP) in infants with high risk. The study included 557 infants with high risk in 13 hospitals in the United States, Norway, India, and Belgium. Infants had a video from GCA 9 to 18 weeks assessed with the General Movement Assessment and were evaluated for a diagnosis of CP after GCA 12 months. Overall, the DL model had a sensitivity of 71.4% (95% CI, 47.8%-88.7%) and specificity of 94.1% (95% CI, 88.2%-97.6%). 1 Furthermore, the DL method differentiated among infants who developed ambulatory and nonambulatory CP, as well as unilateral and bilateral CP. 1This study by Groos et al 1 is an important contribution to the existing literature on leveraging video-based DL models to infer a disease based on early symptoms. To represent infant movements in the video, Groos and colleagues 1 used a spatiotemporal skeleton sequence divided into 5-second windows, which the DL model processed to estimate CP risk in that particular window time. The initial layer of the model detected features of movements of a single limb or joint, whereas subsequent layers detected features of whole-body movements. Finally, the model analyzed the biomechanical properties (position, velocity, and body segment length) in 5-second windows to detect whole-body movement features that distinguished infants with CP from infants without CP.In this regard, infants in a video sequence can be described by their motion, skeleton, and spatial characteristics, which could infer the diagnosis of CP. This interesting approach builds on the efforts of other researchers striving for more accurate detection and evaluation methods for neurological disorders with the help of machine learning. Gait analysis, which is a key aspect of clinical assessments for quantifying functional outcomes following a neurological or musculoskeletal disease, was attempted with DL analyses in various health conditions, such as stroke, Parkinson disease, CP, and spinal cord injury. [2][3][4] In Parkinson disease, DL-based assessments of gait features using video could allow early discovery of gait anomalies in the course of the disease. 4 This solution could be more reliable than commonly used clinical tests, such as the Hoehn and Yahr scale or the Unified Parkinson Disease Rating Scale. Similarly, singlecamera videos and pose estimation models based on DL networks could be used to quantify clinically relevant gait metrics in individuals poststroke, such as measuring reduced walking speeds, decreased cadence, prolonged swing time, and reduced stance time on the paretic side. 2 Likewise, a study by Bandini et al 3 proposed a DL algorithm for automatically detecting hand-object interactions in egocentric videos recorded by participants with cervical spinal cord injury during their daily activities at home. This technique allows the assessment of neurological function in an everyday life...

show abstract

“…The potential of these techniques for a clinical purpose within CP has been shown recently for the early detection of CP in infants at risk (Groos et al, 2022) or the predicting of gait parameters from common videos in ambulatory children with CP (Kidzinski et al, 2020). To our knowledge, automated video-based assessment has not yet been applied to complex movement disorders, such as dystonia in dyskinetic CP (Haberfehlner et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Towards automated video-based assessment of dystonia in dyskinetic cerebral palsy: A novel approach using markerless motion tracking and machine learning

Haberfehlner

Ven²,

Burg³

et al. 2023

Front. Robot. AI

View full text Add to dashboard Cite

Introduction: Video-based clinical rating plays an important role in assessing dystonia and monitoring the effect of treatment in dyskinetic cerebral palsy (CP). However, evaluation by clinicians is time-consuming, and the quality of rating is dependent on experience. The aim of the current study is to provide a proof-of-concept for a machine learning approach to automatically assess scoring of dystonia using 2D stick figures extracted from videos. Model performance was compared to human performance.Methods: A total of 187 video sequences of 34 individuals with dyskinetic CP (8–23 years, all non-ambulatory) were filmed at rest during lying and supported sitting. Videos were scored by three raters according to the Dyskinesia Impairment Scale (DIS) for arm and leg dystonia (normalized scores ranging from 0–1). Coordinates in pixels of the left and right wrist, elbow, shoulder, hip, knee and ankle were extracted using DeepLabCut, an open source toolbox that builds on a pose estimation algorithm. Within a subset, tracking accuracy was assessed for a pretrained human model and for models trained with an increasing number of manually labeled frames. The mean absolute error (MAE) between DeepLabCut’s prediction of the position of body points and manual labels was calculated. Subsequently, movement and position features were calculated from extracted body point coordinates. These features were fed into a Random Forest Regressor to train a model to predict the clinical scores. The model performance trained with data from one rater evaluated by MAEs (model-rater) was compared to inter-rater accuracy.Results: A tracking accuracy of 4.5 pixels (approximately 1.5 cm) could be achieved by adding 15–20 manually labeled frames per video. The MAEs for the trained models ranged from 0.21 ± 0.15 for arm dystonia to 0.14 ± 0.10 for leg dystonia (normalized DIS scores). The inter-rater MAEs were 0.21 ± 0.22 and 0.16 ± 0.20, respectively.Conclusion: This proof-of-concept study shows the potential of using stick figures extracted from common videos in a machine learning approach to automatically assess dystonia. Sufficient tracking accuracy can be reached by manually adding labels within 15–20 frames per video. With a relatively small data set, it is possible to train a model that can automatically assess dystonia with a performance comparable to human scoring.

show abstract

Development and Validation of a Deep Learning Method to Predict Cerebral Palsy From Spontaneous Movements in Infants at High Risk

Cited by 32 publications

References 63 publications

Spasticity following brain and spinal cord injury: assessment and treatment

Spasticity following brain and spinal cord injury: assessment and treatment

Application of Video-Based Deep Learning for Early Diagnosis of Neurological Disorders

Towards automated video-based assessment of dystonia in dyskinetic cerebral palsy: A novel approach using markerless motion tracking and machine learning

Contact Info

Product

Resources

About