The Predictive Accuracy of the General Movement Assessment for Cerebral Palsy: A Prospective, Observational Study of High-Risk Infants in a Clinical Follow-Up Setting

Implementation of remote general movement assessment using the in-motion instructions in a high-risk norwegian cohort

BACKGROUND

General Movement Assessment (GMA) is recommended for early detection of risk for cerebral palsy but requires trained clinical experts. We aimed to implement home- and hospital-based filming for remote GMA in a Norwegian high-risk infant cohort, as well as evaluating parents' experiences in filming their infant at home.

METHODS

This knowledge translational study used a prospective cohort design including participants referred to neurodevelopmental follow-up across three sites in the Central Norway Regional Health Authority. Two home films of the fidgety type of general movements were collected between 12+1-14+6 and 15+1-17+6 weeks after term by parents. An additional film was collected at the hospital between 12+1 and 17+6 weeks after term. The instructional guide for all filming was the In-Motion App standards. Videos were transferred to a remote GMA team and classified as either "GMA scorable" or "GMA not scorable" based on Prechtl's GMA standards. Parents responded to an online survey using a 5-point Likert scale to collect information about their perspectives, experiences, and possible worries by filming their infant at home.

RESULTS

One-hundred-and-two infants from 95 families participated. Ninety-two (96.8%) families transferred 177 home-based videos. Eighty-four (92%) of these had 95 videos taken in their local hospital. All 177 home-videos were "GMA scorable" and three (3,1%) out of 95 hospital-based videos were classified as "GMA not scorable". Eight families did not respond to the survey and two families did not receive the survey due to a technical error. Seventy-eight (91.7%) respondents agreed or strongly agreed that it was easy to perform home filming and five (5.9%) agreed that they were more worried about their child`s development after filming at home. Almost 80% of respondents agreed that a video for GMA can be taken at home instead of in hospital.

CONCLUSIONS

This study strengthens the clinical implementation of home filming by parents and remote GMA for early detection of CP in high-risk follow-up programs. The implementation of remote GMA has the potential to facilitate early intervention to improve function in children with CP in line with international recommendations.

TRIAL REGISTRATION

ClinicalTrials.gov ID: NCT04287166 Date of registration: 27/02/2020.

Early Neurodevelopmental Assessments for Predicting Long-Term Outcomes in Infants at High Risk of Cerebral Palsy

Importance

Studies suggest that early neurodevelopmental assessments are beneficial for identifying cerebral palsy, yet their effectiveness in practical scenarios and their ability to detect cognitive impairment are limited.

Objective

To assess the effectiveness of early neurodevelopmental assessments in identifying cerebral palsy and cognitive and other neurodevelopmental impairments, including their severity, within a multidisciplinary clinic.

Design, Setting, and Participants

This diagnostic study was conducted at Monash Children's Hospital, Melbourne, Australia. Participants were extremely preterm infants born at less than 28 weeks' gestation or extremely low birth weight infants less than 1000 g and term encephalopathic infants who received therapeutic hypothermia, attending the early neurodevelopmental clinic between January 2019 and July 2021. Data were analyzed from December 2023 to January 2024.

Exposures

Early cerebral palsy or high risk of cerebral palsy, the absence of fidgety movements, and Hammersmith Infant Neurological Examination (HINE) scores at corrected age (CA) 3 to 4 months. Early cerebral palsy or high risk of cerebral palsy diagnosis was based on absent fidgety movements, a low HINE score (<57), and medical neurological examination.

Main Outcome and Measures

The outcomes of interest were cerebral palsy, cognitive and neurodevelopmental impairments and their severity, diagnosed at 24 to 36 months' CA.

Results

A total of 116 infants (median [IQR] gestational age, 27 [25-29] weeks; 65 [56%] male) were included. Diagnosis of early cerebral palsy or high risk of cerebral palsy demonstrated a sensitivity of 92% (95% CI, 63%-99%) and specificity of 84% (95% CI, 76%-90%) for predicting cerebral palsy and 100% (95% CI, 59%-100%) sensitivity and 80% (95% CI, 72%-87%) specificity for predicting moderate to severe cerebral palsy. Additionally, the accuracy of diagnosis of early cerebral palsy or high risk of cerebral palsy was 85% (95% CI, 77%-91%) for predicting cerebral palsy and 81% (95% CI, 73%-88%) for predicting moderate to severe cerebral palsy. Similarly, the absence of fidgety movements had an 81% (95% CI, 73%-88%) accuracy in predicting cerebral palsy, and HINE scores exhibited good discriminatory power with an area under the curve of 0.88 (95% CI, 0.79-0.97) for cerebral palsy prediction. However, for cognitive impairment, the predictive accuracy was 44% (95% CI, 35%-54%) for an early cerebral palsy or high risk of cerebral palsy diagnosis and 45% (95% CI, 36%-55%) for the absence of fidgety movements. Similarly, HINE scores showed poor discriminatory power for predicting cognitive impairment, with an area under the curve of 0.62 (95% CI, 0.51-0.73).

Conclusions and Relevance

In this diagnostic study of infants at high risk for cerebral palsy or other cognitive or neurodevelopmental impairment, early neurodevelopmental assessments at 3 to 4 months' CA reliably predicted cerebral palsy and its severity at 24 to 36 months' CA, signifying its crucial role in facilitating early intervention. However, for cognitive impairment, longer-term assessments are necessary for accurate identification.

Identifying Opportunities for Early Detection of Cerebral Palsy

This study aimed to evaluate assessment and referral practices for the early detection and diagnosis of children at risk for or with cerebral palsy (CP) by health care and education providers in Maryland and Delaware. A secondary aim was to identify barriers for using early detection tools and identify opportunities for change to support early diagnosis and improve care. Seventy-two participants answered ≥ 50% of the survey questions. Most were occupational or physical therapists (86%) working in early intervention (61%). Eighty-eight percent indicated awareness that CP can be diagnosed by 12 months. Though 86% stated they typically suspect a diagnosis of CP between 0 and 12 months, only 19% reported that their patients received a CP diagnosis < 12 months. The Developmental Assessment of Young Children (73%) and the Peabody Developmental Motor Scales-2 (59%) were used most. Many respondents indicated never using magnetic resonance imaging (70%), the General Movements Assessment (87%), or the Hammersmith Infant Neurological Exam (69%). Participants identified clinical signs and symptoms prompting a referral for the diagnostic assessment of CP, most commonly stiffness in legs (95%), excessive head lag (93%), and persistent fisting (92%). Policy and organizational change, clinician education, and training are needed to support the implementation of CP early detection guidelines.

Reduction in limb-movement complexity at term-equivalent age is associated with motor developmental delay in very-preterm or very-low-birth-weight infants

Reduced complexity during the writhing period can be crucial in the spontaneous movements of high-risk infants for neurologic impairment. This study aimed to verify the association between quantified complexity of upper and lower-limb movements at term-equivalent age and motor development in very-preterm or very-low-birth-weight infants. Video images of spontaneous movements at term-equivalent age were collected from very-preterm or very-low-birth-weight infants. A pretrained pose-estimation model and sample entropy (SE) quantified the complexity of the upper- and lower-limb movements. Motor development was evaluated at 9 months of corrected age using Bayley Scales of Infant and Toddler Development, Third Edition. The SE measures were compared between infants with and without motor developmental delay (MDD). Among 90 infants, 11 exhibited MDD. SE measures at most of the upper and lower limbs were significantly reduced in infants with MDD compared to those without MDD (p < 0.05). Composite scores in the motor domain showed significant positive correlations with SE measures at most upper and lower limbs (p < 0.05). The results show that limb-movement complexity at term-equivalent age is reduced in infants with MDD at 9 months of corrected age. SE of limb movements can be a potentially useful kinematic parameter to detect high-risk infants for MDD.

A Call for Early Detection of Cerebral Palsy

Cerebral palsy (CP) is the most common physical disability across the lifespan, but historically, CP has not been diagnosed before the age of 2 years. Barriers to early diagnosis ranged from lack of available biomarkers, absence of curative treatments, perceived stigma associated with a lifelong diagnosis, and a desire to rule out other diagnoses first. Most importantly, the fundamental question that remained was whether children would benefit from earlier detection and intervention given the paucity of research. However, evidence-based guidelines published in 2017 demonstrated that the General Movements Assessment, the Hammersmith Infant Neurological Examination, and neuroimaging can be combined with other elements such as a clinical history and standardized motor assessments to provide the highest predictive value for diagnosing CP as early as age 3 months in high-risk newborns. Implementation of these guidelines has been successful in decreasing the age at CP diagnosis, particularly in high-risk infant follow-up clinics with expertise in performing these assessments. Early detection of CP allows for clinical and research opportunities investigating earlier interventions during a critical period of neuroplasticity, with the goal of improving developmental trajectories for children and their families. New guidelines and research are now being developed with a focus on early, targeted interventions that continue to be studied, along with global detection initiatives.

Reach Out and Read Literacy Program for Infants in Neonatal Intensive Care Unit: A Pre-Post Experimental Study

The elevated prevalence of linguistic delay in youngsters emphasizes the necessity to focus on strategies to improve language development, hence aimed to evaluate the effectiveness of Reach Out and Read (ROR) intervention on language development for infants admitted to neonatal intensive care unit (NICU) at a tertiary care hospital, in Belagavi, India. Eighteen infants admitted 7 or more days in NICU and had APGAR scores of more than 6 at the first and fifth minute after birth were recruited. Reach Out and Read was done for 6 months. At recruitment, corrected age 3 and 5 months' general movement assessment (GMA) and at corrected age, 6 months' Bayley Scale of Infant Development III (BSID III) language subtest was recorded. Wilcoxon matched paired test showed significant improvement (P = .0277; P = .0431) in GMA over time. Six-month parent delivered ROR intervention confirms its effectiveness in promoting general movement developmental trajectories of infants admitted to NICU.

Early neurological and motor function in infants born moderate to late preterm or small for gestational age at term: a prospective cohort study

BACKGROUND

There are inconsistent findings regarding neurological and motor development in infants born moderate to late preterm and infants born small for gestational age at term. The primary aim of this study was to compare neurological and motor function between preterm, term SGA and term AGA infants aged three to seven months corrected age using several common assessment tools. The secondary aim was to investigate their motor function at two years.

METHODS

In this prospective cohort study, we included 43 infants born moderate to late preterm with gestational age 32-36 + 6 weeks, 39 infants born small for gestational age (SGA) at term with a birthweight ≤ 10th centile for gestational age, and 170 infants born at term with appropriate weight for gestational age (AGA). Neurological and motor function were assessed once in infancy between three to seven months corrected age by using four standardised assessment tools: Hammersmith Infant Neurological Examination (HINE), Test of Infant Motor Performance, General Movements Assessment and Alberta Infant Motor Scale. The Ages and Stages Questionnaire (ASQ-2) was used at two years.

RESULTS

At three to seven months corrected age, mean age-corrected HINE scores were 61.8 (95% confidence interval (CI): 60.5 to 63.1) in the preterm group compared with 63.3 (95% CI: 62.6 to 63.9) in the term AGA group. Preterm infants had 5.8 (95% CI: 2.4 to 15.4) higher odds for HINE scores < 10th percentile. The other test scores did not differ between the groups. At two years, the preterm group had 17 (95% CI: 1.9 to 160) higher odds for gross motor scores below cut-off on ASQ-2 compared with the term AGA group.

CONCLUSIONS

The present study found subtle differences in neurological function between preterm and term AGA infants in infancy. At two years, preterm children had poorer gross motor function. The findings indicate that moderate prematurity in otherwise healthy infants pose a risk for neurological deficits not only during the first year, but also at two years of age when compared with term AGA children.

Semi-supervised body parsing and pose estimation for enhancing infant general movement assessment

General movement assessment (GMA) of infant movement videos (IMVs) is an effective method for early detection of cerebral palsy (CP) in infants. We demonstrate in this paper that end-to-end trainable neural networks for image sequence recognition can be applied to achieve good results in GMA, and more importantly, augmenting raw video with infant body parsing and pose estimation information can significantly improve performance. To solve the problem of efficiently utilizing partially labeled IMVs for body parsing, we propose a semi-supervised model, termed SiamParseNet (SPN), which consists of two branches, one for intra-frame body parts segmentation and another for inter-frame label propagation. During training, the two branches are jointly trained by alternating between using input pairs of only labeled frames and input of both labeled and unlabeled frames. We also investigate training data augmentation by proposing a factorized video generative adversarial network (FVGAN) to synthesize novel labeled frames for training. FVGAN decouples foreground and background generation which allows for generating multiple labeled frames from one real labeled frame. When testing, we employ a multi-source inference mechanism, where the final result for a test frame is either obtained via the segmentation branch or via propagation from a nearby key frame. We conduct extensive experiments for body parsing using SPN on two infant movement video datasets; on these partially labeled IMVs, we show that SPN coupled with FVGAN achieves state-of-the-art performance. We further demonstrate that our proposed SPN can be easily adapted to the infant pose estimation task with superior performance. Last but not least, we explore the clinical application of our method for GMA. We collected a new clinical IMV dataset with GMA annotations, and our experiments show that our SPN models for body parsing and pose estimation trained on the first two datasets generalize well to the new clinical dataset and their results can significantly boost the convolutional recurrent neural network (CRNN) based GMA prediction performance when combined with raw video inputs.

The predictive ability of the Lacey Assessment of Preterm Infants (LAPI), Cranial Ultrasound (cUS) and General Movements Assessment (GMA) for Cerebral Palsy (CP): A prospective, clinical, single center observational study

BACKGROUND AND AIM

The LAPI, cUS and GMA are assessments used clinically in the UK to identify preterm infants at high risk of neurodevelopmental disabilities such as cerebral palsy. This study investigated the ability of these assessments to predict cerebral palsy at 2 years corrected gestational age.

METHODS

Design: Prospective longitudinal cohort study including infants born <30 weeks' gestation from a single tertiary neonatal intensive care unit. The LAPI and cUS were undertaken as part of routine care before term equivalent age and the GMA was undertaken at 11-18 weeks corrected gestational age.

RESULTS

There were 123 eligible infants and 95 infants (77.2%) were included. Thirteen infants (13.7%) had a diagnosis of CP at 2 years. There was no significant difference in gestational age, gender, or birth weight between the groups with and without a diagnosis of CP. The highest accuracy of prediction of CP was achieved by an aberrant, absent fidgety general movements classification with a sensitivity of 92.3% and specificity of 98.9%. Combining the GMA to include the cUS or LAPI did not increase the predictive accuracy.

CONCLUSION

The GMA when undertaken in clinical practice had high accuracy for predicting CP at 2 years corrected age in infants born <30 weeks gestation; LAPI and cUS did not improve this accuracy.

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

IMPORTANCE

Early identification of cerebral palsy (CP) is important for early intervention, yet expert-based assessments do not permit widespread use, and conventional machine learning alternatives lack validity.

OBJECTIVE

To develop and assess the external validity of a novel deep learning-based method to predict CP based on videos of infants' spontaneous movements at 9 to 18 weeks' corrected age.

DESIGN, SETTING, AND PARTICIPANTS

This prognostic study of a deep learning-based method to predict CP at a corrected age of 12 to 89 months involved 557 infants with a high risk of perinatal brain injury who were enrolled in previous studies conducted at 13 hospitals in Belgium, India, Norway, and the US between September 10, 2001, and October 25, 2018. Analysis was performed between February 11, 2020, and September 23, 2021. Included infants had available video recorded during the fidgety movement period from 9 to 18 weeks' corrected age, available classifications of fidgety movements ascertained by the general movement assessment (GMA) tool, and available data on CP status at 12 months' corrected age or older. A total of 418 infants (75.0%) were randomly assigned to the model development (training and internal validation) sample, and 139 (25.0%) were randomly assigned to the external validation sample (1 test set).

EXPOSURE

Video recording of spontaneous movements.

MAIN OUTCOMES AND MEASURES

The primary outcome was prediction of CP. Deep learning-based prediction of CP was performed automatically from a single video. Secondary outcomes included prediction of associated functional level and CP subtype. Sensitivity, specificity, positive and negative predictive values, and accuracy were assessed.

RESULTS

Among 557 infants (310 [55.7%] male), the median (IQR) corrected age was 12 (11-13) weeks at assessment, and 84 infants (15.1%) were diagnosed with CP at a mean (SD) age of 3.4 (1.7) years. Data on race and ethnicity were not reported because previous studies (from which the infant samples were derived) used different study protocols with inconsistent collection of these data. On external validation, the deep learning-based CP prediction method had sensitivity of 71.4% (95% CI, 47.8%-88.7%), specificity of 94.1% (95% CI, 88.2%-97.6%), positive predictive value of 68.2% (95% CI, 45.1%-86.1%), and negative predictive value of 94.9% (95% CI, 89.2%-98.1%). In comparison, the GMA tool had sensitivity of 70.0% (95% CI, 45.7%-88.1%), specificity of 88.7% (95% CI, 81.5%-93.8%), positive predictive value of 51.9% (95% CI, 32.0%-71.3%), and negative predictive value of 94.4% (95% CI, 88.3%-97.9%). The deep learning method achieved higher accuracy than the conventional machine learning method (90.6% [95% CI, 84.5%-94.9%] vs 72.7% [95% CI, 64.5%-79.9%]; P < .001), but no significant improvement in accuracy was observed compared with the GMA tool (85.9%; 95% CI, 78.9%-91.3%; P = .11). The deep learning prediction model had higher sensitivity among infants with nonambulatory CP (100%; 95% CI, 63.1%-100%) vs ambulatory CP (58.3%; 95% CI, 27.7%-84.8%; P = .02) and spastic bilateral CP (92.3%; 95% CI, 64.0%-99.8%) vs spastic unilateral CP (42.9%; 95% CI, 9.9%-81.6%; P < .001).

CONCLUSIONS AND RELEVANCE

In this prognostic study, a deep learning-based method for predicting CP at 9 to 18 weeks' corrected age had predictive accuracy on external validation, which suggests possible avenues for using deep learning-based software to provide objective early detection of CP in clinical settings.

Early prediction of neurodevelopmental outcomes at 12 years in children born extremely preterm

BACKGROUND

Extremely preterm (EPT) birth is a major risk factor for neurodevelopmental impairments. The aim was to evaluate the predictive value of Prechtl General Movement Assessment (GMA), including the Motor Optimality Score-Revised (MOS-R), at 3 months corrected age (CA) for adverse neurodevelopmental outcome at the age of 12 years.

METHODS

The GMA, including the MOS-R, was applied at 3 months CA and outcomes were assessed at 12 years by Touwen's neurological examination, the Movement Assessment Battery for Children-2, and chart reviews.

RESULTS

Fifty-three infants born EPT (33 boys, mean GA 25 weeks, mean body weight 805 ± 156 g) were included. Forty-two (79%) children participated in the follow-up (mean age 12.3 ± 0.4) and 62% of these had adverse outcomes. The MOS-R differed between groups (p = 0.007). The respective predictive values of GMA, aberrant FMs, and the MOS-R cut-off of 21 for adverse outcomes were positive predictive values (PPVs) of 1.00 and 0.77, negative predictive value of 0.47 and 0.63, sensitivity of 0.31 and 0.77, and specificity of 1.00 and 0.77.

CONCLUSIONS

Using the Prechtl GMA, including the MOS-R, at 3 months CA predicted an overall adverse neurodevelopment at 12 years, with a high PPV, specificity, and sensitivity in children born EPT.

IMPACT

The Prechtl GMA, including the MOS-R, can improve early identification of long-term adverse neurodevelopmental outcomes. This is the first study to investigate the predictive value of the MOS-R for neurodevelopmental outcome at mid-school age in children born EPT. Using the GMA, including the MOS-R, is suggested as one important part of the neurological assessment at 3 months CA in children born EPT. Aberrant FMs in combination with a MOS of <21 is an indicator of an increased risk of future adverse neurodevelopment in children born EPT.

Prediction of outcome from MRI and general movements assessment after hypoxic-ischaemic encephalopathy in low-income and middle-income countries: data from a randomised controlled trial

OBJECTIVE

To evaluate the accuracy of neonatal MRI and general movements assessment (GMA) in predicting neurodevelopmental outcomes in infants with hypoxic-ischaemic encephalopathy (HIE).

DESIGN

Secondary analyses of a randomised controlled trial (RCT).

SETTING

Tertiary neonatal intensive care unit in India.

METHODS

Fifty infants with HIE were included in an RCT of therapeutic hypothermia (25 cooled and 25 non-cooled). All infants underwent brain MRI at day 5, GMA at 10-15 weeks and outcome assessments including Bayley Scales of Infant and Toddler Development, third edition, at 18 months. Associations between patterns of brain injury, presence/absence of fidgety movements (FMs) and outcomes were assessed.

RESULTS

Seventeen of 47 (36%) had adverse outcome (5 (21%) cooled vs 12 (52%) non-cooled, p=0.025). Eight infants died (four before an MRI, another three before GMA). Two developed severe cerebral palsy and seven had Bayley-III motor/cognitive composite score <85. Twelve (26%) had moderately/severely abnormal MRI and nine (23%) had absent FMs. The positive predictive value (95% CI) of an adverse outcome was 89% (53% to 98%) for moderate/severe basal ganglia and thalami (BGT) injury, 83% (56% to 95%) for absent/equivocal signal in the posterior limb of the internal capsule (PLIC) and 67% (38% to 87%) for absent FMs. Negative predictive values (95% CI) were 85% (74% to 92%) for normal/mild BGT injury, 90% (78% to 96%) for normal PLIC and 86% (74% to 93%) for present FMs.

CONCLUSIONS

Neonatal MRI and GMA predicted outcomes with high accuracy in infants with HIE. The GMA is a feasible low-cost method which can be used alone or complementary to MRI in low-resource settings to prognosticate and direct follow-up.

TRIAL REGISTRATION NUMBER

CTRI/2013/05/003693.

Towards human-level performance on automatic pose estimation of infant spontaneous movements

Assessment of spontaneous movements can predict the long-term developmental disorders in high-risk infants. In order to develop algorithms for automated prediction of later disorders, highly precise localization of segments and joints by infant pose estimation is required. Four types of convolutional neural networks were trained and evaluated on a novel infant pose dataset, covering the large variation in 1424 videos from a clinical international community. The localization performance of the networks was evaluated as the deviation between the estimated keypoint positions and human expert annotations. The computational efficiency was also assessed to determine the feasibility of the neural networks in clinical practice. The best performing neural network had a similar localization error to the inter-rater spread of human expert annotations, while still operating efficiently. Overall, the results of our study show that pose estimation of infant spontaneous movements has a great potential to support research initiatives on early detection of developmental disorders in children with perinatal brain injuries by quantifying infant movements from video recordings with human-level performance.

Inter-observer reliability using the General Movement Assessment is influenced by rater experience

OBJECTIVE

To describe the inter-observer reliability of the General Movement Assessment (GMA) among a sample of infants at high-risk of cerebral palsy (CP) among raters with various levels of experience.

METHODS

Video assessments of 150 high-risk infants at 10-15 weeks corrected age were rated by three Prechtl GMA-certified observers with varied experience using the assessment. Videos were scored based on temporal organization of fidgety movements (FMs), presence of abnormal FMs, or absence of FMs. Inter-observer agreements were analyzed with Gwet's AC1 statistic.

RESULTS

We found fair to moderate agreement when subcategories of normal FMs (continuous and intermittent) were included (AC₁ = 0.32-0.57) and moderate to near perfect agreement when normal categories of FMs were combined (AC₁ = 0.60-0.95). Reliability was higher among observers with more experience using the GMA (AC₁ = 0.57-0.98) than the observer with less experience (AC₁ = 0.32-0.61).

CONCLUSIONS

Caution may be warranted when the GMA is used to differentiate "continuous and intermittent" FMs temporal organization. The GMA is highly reliable among experienced raters when comparing normal FMs to other FMs categorizations.

The assessment of general movements in term and late-preterm infants diagnosed with neonatal encephalopathy, as a predictive tool of cerebral palsy by 2 years of age-a scoping review

BACKGROUND

The General Movements Assessment is a non-invasive and cost-effective tool with demonstrated reliability for identifying infants at risk for cerebral palsy. Early detection of cerebral palsy allows for the implementation of early intervention and is associated with better functional outcomes. No review to date has summarized the utility of the General Movements Assessment to predict cerebral palsy in term and late-preterm infants diagnosed with neonatal encephalopathy.

METHODS

We conducted a scoping review involving infants born greater than or equal to 34 weeks gestational age to identify all available evidence and delineate research gaps. We extracted data on sensitivity, specificity, and positive and negative predictive values and described the strengths and limitations of the results. We searched five databases (MEDLINE, Embase, PsychINFO, Scopus, and CINAHL) and the General Movements Trust website. Two reviewers conducted all screening and data extraction independently. The articles were categorized according to key findings, and a critical appraisal was performed.

RESULTS

Only three studies, a cohort and two case series, met all of the inclusion criteria. The total number of participants was 118. None of the final eligible studies included late-preterm neonates. All three studies reported on sensitivity, specificity, and positive predictive and negative predictive values. An abnormal General Movement Assessment at 3-5 months has a high specificity (84.6-98%) for cerebral palsy with a similarly high negative predictive value (84.6-98%) when it was normal. Absent fidgety movements, in particular, are highly specific (96%) for moderate to severe cerebral palsy and carry a high negative predictive value (98%) when normal. In the time period between term and 4-5 months post-term, any cramped synchronized movements had results of 100% sensitivity and variable results for specificity, positive predictive value, and negative predictive value.

CONCLUSIONS

A normal General Movements Assessment at 3 months in a term high-risk infant is likely associated with a low risk for moderate/severe cerebral palsy. The finding of cramped synchronized General Movements is a strong predictor for the diagnosis of cerebral palsy by 2 years of age in the term population with neonatal encephalopathy. The deficit of high-quality research limits the applicability, and so the General Movements Assessment should not be used in isolation when assessing this population.

SYSTEMATIC REVIEW REGISTRATION

Title registration with Joanna Briggs Institute. URL: http://joannabriggswebdev.org/research/registered_titles.aspx .

In-Motion-App for remote General Movement Assessment: a multi-site observational study

OBJECTIVES

To determine whether videos taken by parents of their infants' spontaneous movements were in accordance with required standards in the In-Motion-App, and whether the videos could be remotely scored by a trained General Movement Assessment (GMA) observer. Additionally, to assess the feasibility of using home-based video recordings for automated tracking of spontaneous movements, and to examine parents' perceptions and experiences of taking videos in their homes.

DESIGN

The study was a multi-centre prospective observational study.

SETTING

Parents/families of high-risk infants in tertiary care follow-up programmes in Norway, Denmark and Belgium.

METHODS

Parents/families were asked to video record their baby in accordance with the In-Motion standards which were based on published GMA criteria and criteria covering lighting and stability of smartphone. Videos were evaluated as GMA 'scorable' or 'non-scorable' based on predefined criteria. The accuracy of a 7-point body tracker software was compared with manually annotated body key points. Parents were surveyed about the In-Motion-App information and clarity.

PARTICIPANTS

The sample comprised 86 parents/families of high-risk infants.

RESULTS

The 86 parent/families returned 130 videos, and 121 (96%) of them were in accordance with the requirements for GMA assessment. The 7-point body tracker software detected more than 80% of body key point positions correctly. Most families found the instructions for filming their baby easy to follow, and more than 90% reported that they did not become more worried about their child's development through using the instructions.

CONCLUSIONS

This study reveals that a short instructional video enabled parents to video record their infant's spontaneous movements in compliance with the standards required for remote GMA. Further, an accurate automated body point software detecting infant body landmarks in smartphone videos will facilitate clinical and research use soon. Home-based video recordings could be performed without worrying parents about their child's development.

TRIALS REGISTRATION NUMBER

NCT03409978.

Early intervention and its short-term effect on the temporal organization of fidgety movements

BACKGROUND

The Prechtl General Movement Assessment (GMA) predicts various neurological and developmental disorders while also documenting therapeutic effects.

AIMS

To describe the temporal organization of fidgety general movements in infants with mild to moderate postural asymmetries and/or tonus regulation problems, and to analyze to what extent the temporal organization of fidgety movements will change after physiotherapy.

STUDY DESIGN

Repeated measure design.

PARTICIPANTS

Twelve infants (five females) with mild to moderate postural asymmetries and/or tonus regulation problems were admitted for an early intervention program. The gestational age ranged from 27 to 40 weeks (Median, 36 weeks; nine infants born preterm) with birth weights ranging from 740 g to 3500 g (Median, 2590 g).

MEASURES

Fidgety movements and their temporal organization were measured using the Prechtl GMA at 9 to 19 weeks post term age (Median, 14 weeks) before and after an early motor training procedure. The movements of one of the infants were analysed using a computer-based approach, measuring the mean and standard deviation of quantity of motion, height of motion and width of motion.

RESULTS

Seven infants had sporadic fidgety movements, and five had intermittent fidgety movements. None had continual fidgety movements before the intervention was initiated. After intervention, the temporal organization of fidgety movements increased in all infants. The observations of these movements were supported by computer-based analysis.

CONCLUSION

The study indicates that early intervention increases the temporal organization of fidgety movements in infants with postural asymmetries and/or tonus regulation problems. The clinical significance of this finding needs to be further evaluated.

Advances in cerebral palsy biomarkers

Cerebral palsy (CP), defined as a group of nonprogressive disorders of movement and posture, is the most common cause of severe neurodisability in children. The prevalence of CP is the same across the globe, affecting approximately 17 million people worldwide. Cerebral Palsy is an umbrella term used to describe the disease due to its inherent heterogeneity. For instance, CP has multiple (1) causes; (2) clinical types; (3) patterns of neuropathology on brain imaging and (4) it's associated with several developmental pathologies such as intellectual disability, autism, epilepsy, and visual impairment. Understanding its physiopathology is crucial to developing protective strategies. Despite its importance, there is still insufficient progress in the areas of CP prediction, early diagnosis, treatment, and prevention. Herein we describe the current risk factors and biomarkers used for the diagnosis and prediction of CP. With the advancement in biomarker discovery, we predict that our understanding of the etiopathophysiology of CP will also increase, lending to more opportunities for developing novel treatments and prognosis.

Establishing an early identification score system for cerebral palsy based on detailed assessment of general movements

Objective

This retrospective study aimed to establish an early identification score system of cerebral palsy (CP) in the writhing movement period of high-risk infants by detailed assessment of general movements (GMs).

Methods

High-risk infants from our hospital during January 2016 to January 2017 were included. GMs were assessed and a detailed score was calculated. The 52-neuromotor examination for 0- to 1-year-olds was performed and follow-up outcome was determined at the 12th month according to CP diagnostic criteria. An early identification score of detailed assessment was established in the writhing movement period of infants.

Results

The detailed score during the writhing movement period was significantly different among the normal, poor repertoire, and cramped-synchronized groups of GMs (F = 208.186). Detailed scores were positively related to 52-neuromotor examination scores, with a correlation coefficient of 0.218. The predictive validity of the early identification score was 92.11%, sensitivity was 100%, specificity was 90.00%, the positive predictive value was 72.73%, the negative predictive value was 100%, the false positive rate was 10, and the false negative rate was 0.

Conclusion

The detailed GM score in the writhing movement period is correlated with 52-neuromotor examination results. The CP early identification score could be useful in clinical practice.

Machine Learning of Infant Spontaneous Movements for the Early Prediction of Cerebral Palsy: A Multi-Site Cohort Study

BACKGROUND

Early identification of cerebral palsy (CP) during infancy will provide opportunities for early therapies and treatments. The aim of the present study was to present a novel machine-learning model, the Computer-based Infant Movement Assessment (CIMA) model, for clinically feasible early CP prediction based on infant video recordings.

METHODS

The CIMA model was designed to assess the proportion (%) of CP risk-related movements using a time-frequency decomposition of the movement trajectories of the infant's body parts. The CIMA model was developed and tested on video recordings from a cohort of 377 high-risk infants at 9-15 weeks corrected age to predict CP status and motor function (ambulatory vs. non-ambulatory) at mean 3.7 years age. The performance of the model was compared with results of the general movement assessment (GMA) and neonatal imaging.

RESULTS

The CIMA model had sensitivity (92.7%) and specificity (81.6%), which was comparable to observational GMA or neonatal cerebral imaging for the prediction of CP. Infants later found to have non-ambulatory CP had significantly more CP risk-related movements (median: 92.8%, p = 0.02) compared with those with ambulatory CP (median: 72.7%).

CONCLUSION

The CIMA model may be a clinically feasible alternative to observational GMA.