General Movements Assessment Research Articles

Predictive value of the General Movements Assessment and Standardized Infant NeuroDevelopmental Assessment in infants at high risk of neurodevelopmental disorders.

Predictive value of the General Movements Assessment and Standardized Infant NeuroDevelopmental Assessment in infants at high risk of neurodevelopmental disorders.

Telehealth of Infants at Risk During the COVID-19 Pandemic: Physical Therapists’ and Caregiver’s Perceptions and Costs

Aim We aimed to describe telehealth used to detect infants at risk of neurodevelopmental delay and assess the assessors’ and caregivers’ perceptions and costs. Methods This was an observational study in which five physical therapists applied the General Movement Assessment, the neurological exam based on the Hammersmith Infant Neurological Examination, and the Alberta Infant Motor Scale via telehealth in 65 infants at risk of neurologic delay during the COVID-19 pandemic. The perceptions of assessors and caregivers were assessed using a questionnaire. We tabulated the family’s costs (internet access) and the therapist’s expenses (internet access and professional fees). Results In general, assessors felt comfortable and reported good quality of teleassessment. They highlighted the significant effort they and caregivers required for synchronous methods, challenges in clearly guiding caregivers on infant positioning, difficulties in adjusting the camera’s position, and unstable internet connections. Most assessors expressed a willingness to continue using telehealth. Caregivers displayed high satisfaction, and the costs were minimal. Conclusion Teleassessment during the COVID-19 pandemic was feasible, although implementing this method of health service in general clinical practice still requires further scrutiny.

A randomized-controlled trial of parent-administered interventions to improve short-term motor outcomes in hospitalized very low birthweight infants.

Premature infants are at increased risk for cerebral palsy (CP). Early interventions with a motor focus and administered by parents may improve motor outcomes. Secondary study evaluating the short-term motor outcomes and risk for CP in very low birthweight (VLBW) infants randomized to multimodal interventions with a motor focus provided by parents versus usual care. Randomized controlled trial (intervention vs. usual care (control group)). Infants (<32 weeks' gestational age (GA) and/or <1500 grams birthweight) born between March 2019 and October 2020. Short-term motor outcomes and risk for CP was evaluated using the Hammersmith Infant Neurological Evaluation (HINE, primary motor outcome), the General Movement Assessment (GMA) and the Test of Infant Motor Performance (TIMP) at 3 months' postmenstrual age (PMA). 70 participants were enrolled (GA 28.3±2.7 weeks, birthweight 1139.2±376.6 grams, 64.3% male). The in-person follow-up rate was 73%, lower than expected, in part due to COVID-19 restrictions, resulting in 25 infants (intervention) and 26 infants (control) with outcome data available for analysis. There was not a significant difference in the HINE, GMA or TIMP at 3 months' PMA between groups. Multimodal interventions with a motor focus and provided by parents need further investigation to determine if they can improve short-term motor outcomes in VLBW infants. These interventions are evidence-based and the evaluation of broader implementation into routine care is also needed.

Fine-grained Fidgety Movement Classification using Active Learning.

Typically developing infants, between the corrected age of 9-20 weeks, produce fidgety movements. These movements can be identified with the General Movement Assessment, but their identification requires trained professionals to conduct the assessment from video recordings. Since trained professionals are expensive and their demand may be higher than their availability, computer vision-based solutions have been developed to assist practitioners. However, most solutions to date treat the problem as a direct mapping from video to infant status, without modeling fidgety movements throughout the video. To address that, we propose to directly model infants' short movements and classify them as fidgety or non-fidgety. In this way, we model the explanatory factor behind the infant's status and improve model interpretability. The issue with our proposal is that labels for an infant's short movements are not available, which precludes us to train such a model. We overcome this issue with active learning. Active learning is a framework that minimizes the amount of labeled data required to train a model, by only labeling examples that are considered "informative" to the model. The assumption is that a model trained on informative examples reaches a higher performance level than a model trained with randomly selected examples. We validate our framework by modeling the movements of infants' hips on two representative cohorts: typically developing and at-risk infants. Our results show that active learning is suitable to our problem and that it works adequately even when the models are trained with labels provided by a novice annotator.

Neurodevelopmental outcome at two years of age and predictive value of General Movement Assessment in infants exposed to alcohol and/or drugs during pregnancy: a prospective cohort study

BackgroundExposure to alcohol and/or other addictive drugs in pregnancy is a documented risk factor for neurological impairment. We aimed to assess neurodevelopmental outcome at two years of age in infants exposed to prenatal alcohol and/or other addictive drugs and to examine the predictive value of early motor assessment.MethodsThis was a follow-up at two years of age in the prospective cohort study Children Exposed to Alcohol and/or Drugs in Intrauterine Life (CEADIL). The exposed group comprised 73 infants recruited from primary health care and included in a hospital follow-up programme at St. Olavs Hospital, Trondheim University Hospital, Norway. The control group comprised 93 healthy, unexposed infants recruited from the maternity ward at the same hospital. All children had been assessed by physiotherapists using the General Movement Assessment (GMA) at three months of age. Presence of fidgety movements, movement character and the Motor Optimality Score – Revised (MOS-R) were used. At two years of age, the children were assessed by trained examiners using the Bayley Scales of Infant and Toddler Development – Third Edition (BSID-III), Ages & Stages Questionnaires: Social-Emotional (ASQ:SE) and the Hollingshead Two-Factor Index of Social Position (SES).ResultsThe cognitive, language and motor composite scores of BSID-III were considerably lower in the exposed group than in the control group. Mean differences adjusted for age and parental SES ranged from − 13.3 (95% confidence interval, CI: -18.6 to -8.0) to -17.7 (95% CI: -23.3 to -12.2). Suboptimal fidgety movements and monotonous movement character had high sensitivity (0.94 to 0.74), but low specificity (0.10 to 0.32), while sensitivity and specificity of the MOS-R was around 50 and 60%, respectively.ConclusionsNeurodevelopmental outcome at two years of age was poorer in a group of children exposed to alcohol and/or drugs in pregnancy compared with a control group of healthy, unexposed children. Sensitivity of suboptimal fidgety movements and monotonous movement character at three months of age for later neurodevelopmental outcome was high to acceptable, but the MOS-R had limited sensitivity.

Automation to approximate the Gestalt: applying machine learning to the general movement assessment

Automation to approximate the Gestalt: applying machine learning to the general movement assessment

Early neurodevelopmental outcomes of preterm infants with intraventricular haemorrhage and periventricular leukomalacia.

Intraventricular haemorrhage (IVH) and periventricular leukomalacia (PVL) in preterm infants are associated with an increased risk of long-term neurodevelopmental impairments (NDI) and cerebral palsy (CP). However, little is known about their impact on early neurodevelopmental outcomes despite increasing evidence highlighting the feasibility and importance of early NDI/CP diagnosis. We aimed to determine the early neurodevelopmental outcomes of preterm infants with IVH and PVL. This was a retrospective single-centre cohort study of preterm infants born at <29 weeks gestation or <1000 g birth weight who attended an Early Neurodevelopment Clinic at 3 to 4 months of corrected age. Primary outcomes of early NDI and CP/high-risk CP diagnoses based on Prechtl's General Movements Assessment and the Hammersmith Infant Neurological Examination were compared between infants without IVH and infants with mild IVH (grades I-II), severe IVH (grades III-IV), and severe brain injury (SBI; severe IVH or cystic PVL). Of 313 infants, 52.1% (n = 163), 41.2% (n = 129), 6.7% (n = 21) and 8.6% (n = 27) had no IVH, mild IVH, severe IVH and SBI, respectively. The adjusted odds of early CP/high-risk CP diagnosis were significantly higher in infants with severe IVH (aOR 6.07, 95% CI 1.50-24.50) and SBI (aOR 15.28, 95% CI 3.70-63), but not in those with mild IVH (aOR 1.24, 95% CI 0.49-3.10). However, the adjusted odds of any early NDI were similar across groups. Preterm infants with severe IVH and SBI are at increased risk of early CP/high-risk of CP diagnosis at 3 to 4 months of corrected age.

The Importance of Follow-Up Visits for Children at Risk of Developmental Delay-A Review.

The group of patients for whom the structured follow-up systems are intended were children born very preterm (<32 weeks gestation) or full-term born children with severe neonatal complications. The methods for monitoring neurodevelopment include the following: The General Movements Assessment (GMA), the Ages and Stages Questionnaire (ASQ-3), the Bayley Scales of Infant and Toddler Development (BSID-4), and the Parent Report of Children's Abilities-Revised (PARCA-R). The results of follow-up visits should be registered. The benefits of follow-up neuromotor development assessments can be observed at school age and even in adulthood.

The PRECISE-DYAD Neurodevelopmental substudy protocol: neurodevelopmental risk in children of mothers with pregnancy complications.

Over 250 million children are not reaching their developmental potential globally. The impact of prenatal factors and their interplay with postnatal environmental factors on child neurodevelopment, is still unclear-particularly in low- and middle-income settings. This study aims to understand the impact of pregnancy complications as well as environmental, psychosocial, and biological predictors on neurodevelopmental trajectories. This is an observational cohort study of female and male children (≈3,950) born to women (≈4,200) with and without pregnancy complications (pregnancy-induced hypertension, foetal growth restriction, and premature birth) previously recruited into PREgnancy Care Integrating Translational Science, Everywhere study with detailed biological data collected in intrapartum and post-partum periods. Children will be assessed at six weeks to 6 months, 11-13 months, 23-25 months and 35-37 months in rural and semi-urban Gambia (Farafenni, Illiasa, and Ngayen Sanjal) and Kenya (Mariakani and Rabai). We will assess children's neurodevelopment using Prechtls General Movement Assessment, the Malawi Development Assessment Tool (primary outcome), Observation of Maternal-Child Interaction, the Neurodevelopmental Disorder Screening Tool, and the Epilepsy Screening tool. Children screening positive will be assessed with Cardiff cards (vision), Modified Checklist for Autism in Toddlers Revised, and Pediatric Quality of Life Inventory Family Impact. We will use multivariate logistic regression analysis to investigate the impact of pregnancy complications on neurodevelopment and conduct structural equation modelling using latent class growth to study trajectories and relationships between biological, environmental, and psychosocial factors on child development. We aim to provide information regarding the neurodevelopment of infants and children born to women with and without pregnancy complications at multiple time points during the first three years of life in two low-resource African communities. A detailed evaluation of developmental trajectories and their predictors will provide information on the most strategic points of intervention to prevent and reduce the incidence of neurodevelopmental impairments.

The Motor Optimality Score-Revised Improves Early Detection of Unilateral Cerebral Palsy in Infants with Perinatal Cerebral Stroke.

Neonatal cerebral stroke includes a range of focal and multifocal ischemic and hemorrhagic brain lesions, occurring in about one of 3000 live births. More than 50% of children with neonatal stroke develop adverse outcomes, mainly unilateral cerebral palsy. Asymmetries in segmental movements at three months have been proven to be an early sign of CP in infants with unilateral brain damage. Recognition of additional early signs could enhance prognostic assessment and enable an early and targeted intervention. The aim of the study was to assess early signs of CP in infants with arterial cerebral stroke through the General Movements Assessment and the Motor Optimality Score-Revised (MOS-R). Twenty-four infants born at term (12 females and 12 males) diagnosed with ACS, and 24 healthy infants (16 females and 8 males) were assessed. The GMs (fidgety movements) and MOS-R were assessed from videos recorded at 11-14 weeks of post-term age. Cognitive and motor outcomes were assessed at 24 months using the Griffiths III developmental quotient and Amiel-Tison neurological examination. The gross motor function classification system expanded and revised (GMFCS-E&R) was adopted to categorize CP. Among infants with ACS, 21 (87.5%) developed unilateral CP. Most of them showed non-disabling CP (14 had GMFCS-E&R grade 1 [66.6%], 6 grade 2 [28.6%], and 1 grade 5 [4.8%]). Fidgety movements (FMs) were absent in 17 (70.8%), sporadic in 4 (16.7%) infants, and normal in 3 (12.5%). Segmental movement asymmetry was found in 22/24 (91.7%). According to the MOS-R, motor items (kicking, mouth movements), postural patterns (midline centered head, finger posture variability), and movement character (monotonous and stiff) were statistically different among infants with ACS and healthy infants. The MOS-R median global score was lower in the group with ACS compared to the control group (6 vs 26; p < 0.01). FMs, segmental movement asymmetry, and MOS-R global score were significantly correlated with abnormal outcome. MOS-R global scores less than or equal to 13 had 100% specificity and sensitivity in predicting GMFCS-E&R grade ≥ 2 CP in infants with ACS. The rate of CP was high among infants with ACS, but in most cases it showed low GMFCS-E&R grades. The study highlighted a significant correlation between MOS-R, together with absent FMs and unilateral CP in infants with ACS. Moreover, the MOS-R showed high sensitivity and specificity in the prediction of CP. Combined assessment of FMs and MOS-R could help to better identify infants at high risk of developing UCP in a population of infants with ACS. Early identification of precocious signs of unilateral CP is fundamental to providing an early individualized intervention.

Automated detection of abnormal general movements from pressure and positional information in hospitalized infants.

Prechtl's general movements assessment (GMA) allows visual recognition of movement patterns that, when abnormal (cramped synchronized, or CS), have very high sensitivity in predicting later neuromotor disorders; however, training requirements and subjective perceptions from some clinicians may hinder universal adoption of the GMA in the newborn period. To address this, we used a three-phased approach to design a preliminary and clinically-oriented approach to automated CS GMA detection. 335 hospitalized infants were dually recorded on video and a pressure-sensor mat that collected time, spatial, and pressure data. Video recordings were scored by advanced GMA readers. We then conducted a series of unsupervised machine learning and supervised classification modeling with features extracted from clinician- and mat-driven datasets. Finally, the resulting algorithm was converted to a software interface. A classification model combining normalization, clustering, and decision tree modeling resulted in the highest sensitivity for CS movements (100%). Results were delivered via the software interface within 20 min of data recording. The combination of clinical research, machine learning, and repurposing of existing sensor mat technology produced a feasible preliminary approach to automatically detect abnormal GMA in infants while still in the NICU. Further refinements of software and algorithms are needed. Machine learning can differentiate cramped synchronized general movement patterns in the neonatal intensive care unit with good sensitivity and specificity. Increasing access to the GMA through automated detection methods may allow for earlier identification of a greater number of children at high risk for movement delay. Large studies leveraging new artificial intelligence approaches could increase the impact of such detection.

General Movements Assessment in Infants with High Birth Weight

BackgroundHigh birth weight (HBW) describes fetal birth weight of more than 4000 g. Infants with HBW have a high risk of developing neurological and developmental problems. Until recently, there were no studies in the literature that investigated the quality of spontaneous movements and the integrity of the developing nervous system in infants with HBW. The aims of this study were (1) to describe age-specific detailed early spontaneous movements in infants with HBW and (2) to compare the detailed early spontaneous movements of infants with HBW and normal birth weight (NBW). MethodsTwenty-two infants with HBW (median birth weight = 4190 g) and 22 infants with NBW (median birth weight = 3255 g) were included at 10 to 19 weeks post-term age (median = 13 weeks). All infants were assessed according to General Movement Assessment using three- to five-minute video recordings. Video recordings of each infant were evaluated using Motor Optimality Score for three- to five-month-old infants-Revised score sheet. ResultsMotor Optimality Score-Revised (MOS-R) (P < 0.001), observed postural patterns (P < 0.001), and age-adequate movement repertoire (P = 0.005) were significantly lower in the infants with HBW. Infants with HBW had more aberrant (abnormal or absent) fidgety movements (18%) than those with NBW (0%). ConclusionsThe results of this study demonstrated that the motor repertoire of infants with HBW tended to decrease more than that of those with NBW. To enable the follow-up of progression as a result of these assessments infants in need should be referred to age-adequate early intervention programs.

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

BackgroundGeneral 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.MethodsThis 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.ResultsOne-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.ConclusionsThis 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 registrationClinicalTrials.gov ID: NCT04287166 Date of registration: 27/02/2020.

Development of Movement and Postural Patterns in Full-Term Infants Who Are at Low Risk in Belgium, India, Norway, and the United States.

The objective of this study was to investigate the influences on motor development in infants who are at low risk from Belgium, India, Norway, and the United States using the General Movement Assessment at 10-16weeks postterm age. This was a cross-sectional study of prospectively enrolled full-term infants at low risk (n = 186). Certified General Movement Assessment observers rated the fidgety movements, quality of the movement patterns, age-adequacy of the movement repertoire, postural patterns, movement character, and overall Motor Optimality Score-Revised (MOS-R). Scores were evaluated for associations with sex, birth weight category, gestational age, postterm age at video, and country. The majority of infants had normal fidgety movements (179/186, 96.2%). This did not vary by sex, birth weight, gestational age, postterm age at video, or country. All infants showed normal>atypical movement patterns. Variability was seen for age adequacy (optimal: 137/183, 74.9%), postural patterns (normal>atypical: 164/183, 89.6%), and smooth/ fluent movement character (138/183, 75.4%). Gestational age and postterm age at video were associated with atypical postural patterns, but in multivariable regression, only younger postterm age retained significance (OR = 2.94, 95% CI = 1.05-8.24). Lack of age adequacy was associated with postterm age (OR = 13.15, 95% CI = 4.36-39.72) and country (compared with Norway; Belgium OR = 3.38 95% CI = 12.4-9.22; India OR = 3.16, 95% CI = 1.01-9.87; United States not significant). Infants from India also showed lower rates of an optimal MOS-R (25-28) than infants from Norway. The normality and temporal organization of fidgety movements did not differ by sex, birth weight, postterm age, or country, suggesting that the fidgety movements are free of cultural and environmental influences. The majority of full-term infants who were healthy in this cohort showed normal scores for all aspects of motor development tested using the MOS-R. Differences in age adequacy and MOS-R by country warrant investigation with larger cohorts and longitudinal follow-up. Understanding variations in typical motor development is essential to interpreting patterns of movement and posture in infants at risk for atypical development. Using the framework of Prechtl's General Movement Assessment, this study showed that the development of movement and posture in healthy infants was affected by age and country of birth, but the development of the fidgety movements appeared to be free of these influences. Local norms may be needed to interpret the Motor Optimality Score-Revised in all populations, but further research on this topic is needed.

Hybrid developmental follow-up for preterm infants in Brazil: A feasibility study

IntroductionThe low attendance of families in child developmental follow-up programs for at-risk preterm children is a challenge in Brazil. ObjectiveThis study evaluates the feasibility of implementing a developmental follow-up program for Brazilian preterm infants in a hybrid format. MethodsThis is an observational, prospective cohort study, involving preterm infants. Longitudinal developmental test results, the participation frequency in the program, and the number of referrals to early intervention programs were used to assess feasibility. The General Movements (GMs) assessment, Alberta Infant Motor Scale (AIMS) and, Survey of Wellbeing of Young Children (SWYC) Milestones were administered via telehealth. The Bayley-III was administered in-person. ResultsThirty-four preterm infants attended the follow-up until 12 months of corrected age and 18 (52.9 %) concluded all follow-up assessments. Twenty-six (76.5 %) attended all assessments via telehealth, and 26 (76.5 %) attended the in-person assessment. Eighteen (52.9 %) infants showed at least one altered result in development tests. Infants exhibiting abnormal results in the GMs assessment, motor developmental delay according to the AIMS, or developmental delay based on Balley-III were promptly referred to early intervention services. ConclusionThis study demonstrated high participation rate and low dropout in a developmental follow-up program employing a hybrid format. The substantial number of identified infants with developmental delay emphasizes the importance of timely detection of motor delays to referral to early intervention services.

Combined Effects of Manual Therapy and Functional Electrical Stimulation on Torticollis among Adults

Background: Acquired muscular torticollis is a common musculoskeletal disorder that occurs after birth due to various etiologies. This condition is characterized by the abnormal tilt and twist of the neck muscles, causing significant discomfort and functional impairment. Objective: This study aimed to investigate the combined effects of manual therapy and functional electrical stimulation (FES) on adults with acquired torticollis. Methods: A 45-year-old male patient with acquired torticollis was evaluated using a detailed general movement assessment and an arthrodial goniometer to measure cervical ranges of motion. The patient exhibited tightness of the right sternocleidomastoid (SCM) muscle with limited ranges of motion. The treatment protocol included both manual therapy and electrotherapy for three months, with sessions conducted four days per week, each lasting 40 minutes. Manual therapy consisted of soft tissue mobilization, stretching of the right SCM, and isometric exercises for the left SCM. Electrotherapy included transcutaneous electrical nerve stimulation (TENS), DL2 stimulator, infrared radiation therapy (IRR), and ultrasonic therapy. The patient’s cervical ranges of motion were measured before and after the intervention to assess the effectiveness of the combined therapy. Results: Significant improvements were observed in the patient’s cervical ranges of motion after the 12-week treatment protocol. The mean lateral flexion of the affected right SCM improved from 35 degrees to 20 degrees, and the mean rotation improved from 43 degrees to 28 degrees. These changes indicate a noticeable improvement in both the ranges of motion and posture of the patient. Conclusion: The combined effects of manual therapy and functional electrical stimulation significantly improved the cervical ranges of motion and overall posture in an adult patient with acquired torticollis. These findings suggest that integrating multiple therapeutic modalities can enhance treatment outcomes for musculoskeletal deformities.

'We did everything by phone': a qualitative study of mothers' experience of smartphone-aided screening of cerebral palsy in Kathmandu, Nepal.

International guidelines recommend early intervention to all children at risk of cerebral palsy, but targeted screening programs are often lacking in low- and middle-income settings with the highest burden of disease. Smartphone applications have the potential to improve access to early diagnostics by empowering parents to film their children at home followed by centralized evaluation of videos with General Movements Assessment. We explored mothers' perceptions about participating in a smartphone aided cerebral palsy screening program in Kathmandu, Nepal. This is an explorative qualitative study that used focus group discussions (n = 2) and individual interviews (n = 4) with mothers of term-born infants surviving birth asphyxia or neonatal seizures. Parents used the NeuroMotion™ smartphone app to film their children at home and the videos were analysed using Precthl's General Movements Assessment. Sekhon et al.'s framework on the acceptability of health care interventions guided the design of the group discussions and interviews, and the deductive qualitative content analysis. Mothers were interested in engaging with the programme and expressed hope it would benefit their children. Most felt using the app was intuitive. They were, however, unclear about the way the analysis was performed. Support from the research team was often needed to overcome an initial lack of self-confidence in using the technology, and to reduce anxiety related to the follow-up. The intervention was overall perceived as recommendable but should be supplemented by a face-to-face consultation. Smartphone aided remote screening of cerebral palsy is acceptable in a lower middle-income population but requires additional technical support.

A self-supervised spatio-temporal attention network for video-based 3D infant pose estimation

General movement and pose assessment of infants is crucial for the early detection of cerebral palsy (CP). Nevertheless, most human pose estimation methods, in 2D or 3D, focus on adults due to the lack of large datasets and pose annotations on infants. To solve these problems, here we present a model known as YOLO-infantPose, which has been fine-tuned, for infant pose estimation in 2D. We further propose a self-supervised model called STAPose3D for 3D infant pose estimation based on videos. We employ multi-view video data during the training process as a strategy to address the challenge posed by the absence of 3D pose annotations. STAPose3D combines temporal convolution, temporal attention, and graph attention to jointly learn spatio-temporal features of infant pose. Our methods are summarized into two stages: applying YOLO-infantPose on input videos, followed by lifting these 2D poses along with respective confidences for every joint to 3D. The employment of the best-performing 2D detector in the first stage significantly improves the precision of 3D pose estimation. We reveal that fine-tuned YOLO-infantPose outperforms other models tested on our clinical dataset as well as two public datasets MINI-RGBD and YouTube-Infant dataset. Results from our infant movement video dataset demonstrate that STAPose3D effectively comprehends the spatio-temporal features among different views and significantly improves the performance of 3D infant pose estimation in videos. Finally, we explore the clinical application of our method for general movement assessment (GMA) in a clinical dataset annotated as normal writhing movements or abnormal monotonic movements according to the GMA standards. We show that the 3D pose estimation results produced by our STAPose3D model significantly boost the GMA prediction performance than 2D pose estimation. Our code is available at github.com/wwYinYin/STAPose3D.

Early Detection and Intervention for Children with High Risk of Cerebral Palsy: A Survey of Physical Therapists and Occupational Therapists in Brazil

Aims The purpose of this study was to assess the current clinical practice of physiotherapists and occupational therapists on early detection and early intervention for children with cerebral palsy (CP) in Brazil. Methods This was a cross-sectional study. A purpose-developed electronic survey was disseminated across the country to physiotherapists and occupational therapists working with young children with or at risk of CP. Results A total of 205 anonymous respondents were included. Most participants (64.4%) agree that the diagnosis of CP can be made before 6 months of age. General Movements Assessment (26.8%) and Hammersmith Infant Neurological Examination (37.1%) were used infrequently. Infants at risk for CP receive therapy twice a week or more by 58.5% of therapists, 93.2% identified parents’ goals as the most important factor in customizing the early intervention program. The most frequent intervention strategies for this age group were active stimulation of the child (n = 182), family training (n = 161), strategies to optimize the environment (n = 143), and neurodevelopmental treatment/Bobath (n = 99). Conclusions Currently, pediatric physiotherapists and occupational therapists in Brazil do not fully incorporate best practice tools for early identification of children with CP, nor sufficient best evidence-based interventions.

Early detection of cerebral palsy with the Standardized Infant NeuroDevelopmental Assessment versus the General Movements Assessment: Is another assessment the way forward?

Early detection of cerebral palsy with the Standardized Infant NeuroDevelopmental Assessment versus the General Movements Assessment: Is another assessment the way forward?