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

Parents' lived experience of early risk assessment for cerebral palsy in their young child using a mobile application after discharge from hospital in the newborn period

INTRODUCTION

General Movement assessment (GMA) is considered the golden standard for early identification of infants with a high risk of developing cerebral palsy (CP). The aim of this study was to explore parents' lived experience of early risk assessment for CP using a mobile application for home video recording after discharge from hospital stay in the newborn period.

METHODS

An inductive qualitative design using a hermeneutical phenomenological approach was chosen, and fourteen parents with children at risk of CP were interviewed at home. The hermeneutical phenomenological approach describes humans' lived experiences of a specific phenomenon with a possibility of deeper understanding of the expressed statements. The interviews were analyzed using the fundamental lifeworld existential dimensions as guidelines for describing the parents' lived experience.

RESULTS

The overall understanding of the parents' experience was 'Finding control in an uncontrolled life situation'. During the often-long hospitalizations, the parents struggled with loss of control and difficulty in understanding what was going on. The use of the mobile application followed by a swift result made them feel in control and have a brighter view of the future.

CONCLUSIONS

The findings suggest that the mobile application did not seem to worry the parents. Instead, it provided the parents with a sense of active participation in the care and treatment of their child. The mobile application should be accompanied with clear instructions and guidelines for the parents and details about how and when the result is given.

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.

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

BACKGROUND

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.

METHODS

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.

RESULTS

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.

CONCLUSION

Smartphone aided remote screening of cerebral palsy is acceptable in a lower middle-income population but requires additional technical support.

The Knowledge Translation of Early Cerebral Palsy (KiTE CP) Study: Implementing Screening Among a High-Risk Prospective Cohort of Australian Infants

OBJECTIVE

To describe the implementation of the international guidelines for the early diagnosis of cerebral palsy (CP) and engagement in the screening process in an Australian cohort of infants with neonatal risk factors for CP.

STUDY DESIGN

Prospective cohort study of infants with neonatal risk factors recruited at <6 months corrected age from 11 sites in the states of Victoria, New South Wales, and Queensland, Australia. First, we implemented a multimodal knowledge translation strategy including barrier identification, technology integration, and special interest groups. Screening was implemented as follows: infants with clinical indications for neuroimaging underwent magnetic resonance imaging and/or cranial ultrasound. The Prechtl General Movements Assessment (GMA) was recorded clinically or using an app (Baby Moves). Infants with absent or abnormal fidgety movements on GMA videos were offered further assessment using the Hammersmith Infant Neurological Examination (HINE). Infants with atypical findings on 2/3 assessments met criteria for high risk of CP.

RESULTS

Of the 597 infants (56% male) recruited, 95% (n = 565) received neuroimaging, 90% (n = 537) had scorable GMA videos (2% unscorable/8% no video), and 25% (n = 149) HINE. Overall, 19% of the cohort (n = 114/597) met criteria for high risk of CP, 57% (340/597) had at least 2 normal assessments (of neuroimaging, GMA or HINE), and 24% (n = 143/597) had insufficient assessments.

CONCLUSIONS

Early CP screening was implemented across participating sites using a multimodal knowledge translation strategy. Although the COVID-19 pandemic affected recruitment rates, there was high engagement in the screening process. Reasons for engagement in early screening from parents and clinicians warrant further contextualization and investigation.

E-BabyNet: Enhanced Action Recognition of Infant Reaching in Unconstrained Environments

Machine vision and artificial intelligence hold promise across healthcare applications. In this paper, we focus on the emerging research direction of infant action recognition, and we specifically consider the task of reaching which is an important developmental milestone. We develop E-babyNet, a lightweight yet effective neural-network-based framework for infant action recognition that leverages the spatial and temporal correlation of bounding boxes of infants' hands and objects to reach for to determine the onset and offset of the reaching action. E-babyNet consists of two main layers based on two LSTM and a Bidirectional LSTM (BiLSTM) model, respectively. The first layer provides a pre-evaluation of the reaching action for each hand by providing onset and offset keyframes. Then, the biLSTM model merges the previous outputs to deliver an outcome of the reaching actions detection for each frame including the reaching hand. We evaluated our approach against four other lightweight structures using a dataset comprising 5,865 annotated images resulting in 16,337 bounding boxes from 375 distinctive infant reaching actions performed while sitting by different subjects in unconstrained (home/clinic) environments. Results illustrate the effectiveness of our approach and ability to provide reliable reaching action detection and offer onset and offset keyframes with a precision of one frame. Moreover, the biLSTM layer can handle the transition between reaching actions and help reduce false detections.

The General Movement Optimality Score-Revised (GMOS-R) with Socioeconomically Stratified Percentile Ranks

Background: The general movement optimality score (GMOS) quantifies the details of general movements (GMs). We recently conducted psychometric analyses of the GMOS and developed a revised scoresheet. Consequently, the GMOS-Revised (GMOS-R) instrument necessitated validation using new percentile ranks. This study aimed to provide these percentile ranks for the GMOS-R and to investigate whether sex, preterm birth, or the infant's country of birth and residence affected the GMOS-R distribution. Methods: We applied the GMOS-R to an international sample of 1983 infants (32% female, 44% male, and 24% not disclosed), assessed in the extremely and very preterm period (10%), moderate (12%) and late (22%) preterm periods, at term (25%), and post-term age (31%). Data were grouped according to the World Bank's classification into lower- and upper-middle-income countries (LMICs and UMICs; 26%) or high-income countries (HICs; 74%), respectively. Results: We found that sex and preterm or term birth did not affect either GM classification or the GMOS-R, but the country of residence did. A lower median GMOS-R for infants with normal or poor-repertoire GMs from LMICs and UMICs compared with HICs suggests the use of specific percentile ranks for LMICs and UMICs vs. HICs. Conclusion: For clinical and scientific use, we provide a freely available GMOS-R scoring sheet, with percentile ranks reflecting socioeconomic stratification.

NeuroMotion smartphone application for remote General Movements Assessment: a feasibility study in Nepal

OBJECTIVES

To evaluate the feasibility of using the NeuroMotion smartphone application for remote General Movements Assessment for screening infants for cerebral palsy in Kathmandu, Nepal.

METHOD

Thirty-one term-born infants at risk of cerebral palsy due to birth asphyxia or neonatal seizures were recruited for the follow-up at Paropakar Maternity and Women's Hospital, 1 October 2021 to 7 January 2022. Parents filmed their children at home using the application at 3 months' age and the videos were assessed for technical quality using a standardised form and for fidgety movements by Prechtl's General Movements Assessment. The usability of the application was evaluated through a parental survey.

RESULTS

Twenty families sent in altogether 46 videos out of which 35 had approved technical quality. Sixteen children had at least one video with approved technical quality. Three infants lacked fidgety movements. The level of agreement between assessors was acceptable (Krippendorf alpha 0.781). Parental answers to the usability survey were in general positive.

INTERPRETATION

Engaging parents in screening of cerebral palsy with the help of a smartphone-aided remote General Movements Assessment is possible in the urban area of a South Asian lower middle-income country.

Automated identification of abnormal infant movements from smart phone videos

Cerebral palsy (CP) is the most common cause of physical disability during childhood, occurring at a rate of 2.1 per 1000 live births. Early diagnosis is key to improving functional outcomes for children with CP. The General Movements (GMs) Assessment has high predictive validity for the detection of CP and is routinely used in high-risk infants but only 50% of infants with CP have overt risk factors when they are born. The implementation of CP screening programs represents an important endeavour, but feasibility is limited by access to trained GMs assessors. To facilitate progress towards this goal, we report a deep-learning framework for automating the GMs Assessment. We acquired 503 videos captured by parents and caregivers at home of infants aged between 12- and 18-weeks term-corrected age using a dedicated smartphone app. Using a deep learning algorithm, we automatically labelled and tracked 18 key body points in each video. We designed a custom pipeline to adjust for camera movement and infant size and trained a second machine learning algorithm to predict GMs classification from body point movement. Our automated body point labelling approach achieved human-level accuracy (mean ± SD error of 3.7 ± 5.2% of infant length) compared to gold-standard human annotation. Using body point tracking data, our prediction model achieved a cross-validated area under the curve (mean ± S.D.) of 0.80 ± 0.08 in unseen test data for predicting expert GMs classification with a sensitivity of 76% ± 15% for abnormal GMs and a negative predictive value of 94% ± 3%. This work highlights the potential for automated GMs screening programs to detect abnormal movements in infants as early as three months term-corrected age using digital technologies.

Mobile Device-Based Video Screening for Infant Head Lag: An Exploratory Study

INTRODUCTION

Video-based automatic motion analysis has been employed to identify infant motor development delays. To overcome the limitations of lab-recorded images and training datasets, this study aimed to develop an artificial intelligence (AI) model using videos taken by mobile phone to assess infants' motor skills.

METHODS

A total of 270 videos of 41 high-risk infants were taken by parents using a mobile device. Based on the Pull to Sit (PTS) levels from the Hammersmith Motor Evaluation, we set motor skills assessments. The videos included 84 level 0, 106 level 1, and 80 level 3 recordings. We used whole-body pose estimation and three-dimensional transformation with a fuzzy-based approach to develop an AI model. The model was trained with two types of vectors: whole-body skeleton and key points with domain knowledge.

RESULTS

The average accuracies of the whole-body skeleton and key point models for level 0 were 77.667% and 88.062%, respectively. The Area Under the ROC curve (AUC) of the whole-body skeleton and key point models for level 3 were 96.049% and 94.333% respectively.

CONCLUSIONS

An AI model with minimal environmental restrictions can provide a family-centered developmental delay screen and enable the remote monitoring of infants requiring intervention.

Mobile Solutions for Clinical Surveillance and Evaluation in Infancy-General Movement Apps

The Prechtl General Movements Assessment (GMA) has become a clinician and researcher toolbox for evaluating neurodevelopment in early infancy. Given that it involves the observation of infant movements from video recordings, utilising smartphone applications to obtain these recordings seems like the natural progression for the field. In this review, we look back on the development of apps for acquiring general movement videos, describe the application and research studies of available apps, and discuss future directions of mobile solutions and their usability in research and clinical practice. We emphasise the importance of understanding the background that has led to these developments while introducing new technologies, including the barriers and facilitators along the pathway. The GMApp and Baby Moves apps were the first ones developed to increase accessibility of the GMA, with two further apps, NeuroMotion and InMotion, designed since. The Baby Moves app has been applied most frequently. For the mobile future of GMA, we advocate collaboration to boost the field's progression and to reduce research waste. We propose future collaborative solutions, including standardisation of cross-site data collection, adaptation to local context and privacy laws, employment of user feedback, and sustainable IT structures enabling continuous software updating.

Using Telemedicine to Overcome Barriers to Neurodevelopmental Care from the Neonatal Intensive Care Unit to School Entry

Dedicated Neonatal Intensive Care Unit (NICU) follow-up programs are recommended for ongoing surveillance for infants at high-risk for future neurodevelopmental impairment (NDI). Systemic, socioeconomic, and psychosocial barriers remain for referrals and the continued neurodevelopmental follow-up of high-risk infants. Telemedicine can help overcome these barriers. Telemedicine allows standardization of evaluations, increased referral rates, and reduced time to follow-up as well as increased therapy engagement. Telemedicine can expand neurodevelopmental surveillance and support all NICU graduates, facilitating the early identification of NDI. However, with the recent expansion of telemedicine during the COVID-19 pandemic, new barriers related to access and technological support have arisen.

Parent-recorded videos of infant spontaneous movement: Comparisons at 3-4 months and relationships with 2-year developmental outcomes in extremely preterm, extremely low birthweight and term-born infants

BACKGROUND

Infants born extremely preterm (EP, <28-week gestational age) or extremely low birthweight (ELBW, <1000 g) are at risk of developmental delay and cerebral palsy (CP). The General Movements Assessment (GMA) and its extension, the Motor Optimality Score, revised (MOS-R) (assesses movement patterns and posture), may help to identify early delays.

OBJECTIVES

To compare differences in the MOS-R scored from parent-recorded videos between infants born EP/ELBW and term-born infants, to determine relationships between the MOS-R and 2-year cognitive, language and motor outcomes and if any relationships differ between birth groups and the association of the GMA (fidgety) with CP.

METHODS

A geographical cohort (EP/ELBW and term-control infants) was assessed using the MOS-R inclusive of the GMA at 3- to 4-month corrected age (CA), and the Bayley Scales of Infant and Toddler Development, 3rd edition (Bayley-III) at 2-year CA. Differences in mean total MOS-R between groups, relationships between MOS-R and 2-year outcomes and relationships between GMA (fidgety) and CP in infants born EP/ELBW were estimated using linear/logistic regression.

RESULTS

Three hundred and twelve infants (147 EP/ELBW; 165 term) had complete MOS-R and Bayley-III assessments. Mean MOS-R was lower in infants born EP/ELBW than controls (mean difference -3.2, 95% confidence interval [CI] -4.2, -2.3). MOS-R was positively related to cognitive (β [regression coefficient] = 0.71, 95% CI 0.27, 1.15), language (β = 0.96, 95% CI 0.38, 1.54) and motor outcomes (β = .89, 95% CI 0.45, 1.34). There was little evidence for interaction effects between birth groups for any outcome. Absent/abnormal fidgety movements were related to CP in children born EP/ELBW (risk ratio 5.91, 95% CI 1.48, 23.7).

CONCLUSIONS

Infants born EP/ELBW have lower MOS-R than infants born at term. A higher MOS-R is related to better outcomes for 2-year development, with similar relationships in both birth groups. Absent/abnormal fidgety movements are related to CP in EP/ELBW survivors.

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 motor repertoire and neurodevelopment at 2 years in infants born extremely preterm or extremely-low-birthweight

AIM

To determine the relationship between early motor repertoire and 2-year neurodevelopment in infants born extremely preterm (<28 weeks' gestation) or extremely-low-birthweight (ELBW) (<1000g).

METHOD

This was a geographical prospective cohort of 139 infants born extremely preterm/ELBW (mean gestational age 26.7 weeks, standard deviation [SD] 2.0, 68/139 [49%] male), with parent-recorded videos suitable for scoring the General Movements Assessment (GMA). Motor repertoire was assessed using the Motor Optimality Score-Revised (MOS-R), with and without the fidgety movement subsection, and the GMA alone at 12 to 13⁺⁶  weeks corrected age and 14 to 15⁺⁶  weeks corrected age. At 2 years corrected age, impaired development was defined as Bayley Scales of Infant and Toddler Development, Third Edition motor and cognitive development scores 1SD or less relative to controls born at term; paediatricians diagnosed cerebral palsy (CP).

RESULTS

Greater MOS-R scores at 14 to 15⁺⁶  weeks corrected age were associated with lower odds of CP (odds ratio [OR] per 1-point increase=0.83, 95% confidence interval [CI]=0.71-0.99), and motor (OR=0.93, 95% CI=0.87-0.99), or cognitive impairment (OR=0.94, 95% CI=0.88-0.99). Absent/abnormal GMA at 14 to 15⁺⁶ weeks was associated with CP and motor delay. There was little evidence that MOS-R scores at 12 to 13⁺⁶ weeks were associated with neurodevelopmental outcomes at 2 years.

INTERPRETATION

Poorer MOS-R scores and absent/abnormal GMA, scored from parent-recorded videos at 14 to 15⁺⁶  weeks gestational age, are associated with CP and developmental impairment in 2-year-old infants born extremely preterm/ELBW.

Automated Movement Analysis to Predict Cerebral Palsy in Very Preterm Infants: An Ambispective Cohort Study

The General Movements Assessment requires extensive training. As an alternative, a novel automated movement analysis was developed and validated in preterm infants. Infants < 31 weeks’ gestational age or birthweight ≤ 1500 g evaluated at 3−5 months using the general movements assessment were included in this ambispective cohort study. The C-statistic, sensitivity, specificity, positive predictive value, and negative predictive value were calculated for a predictive model. A total of 252 participants were included. The median gestational age and birthweight were 274/7 weeks (range 256/7−292/7 weeks) and 960 g (range 769−1215 g), respectively. There were 29 cases of cerebral palsy (11.5%) at 18−24 months, the majority of which (n = 22) were from the retrospective cohort. Mean velocity in the vertical direction, median, standard deviation, and minimum quantity of motion constituted the multivariable model used to predict cerebral palsy. Sensitivity, specificity, positive, and negative predictive values were 55%, 80%, 26%, and 93%, respectively. C-statistic indicated good fit (C = 0.74). A cluster of four variables describing quantity of motion and variability of motion was able to predict cerebral palsy with high specificity and negative predictive value. This technology may be useful for screening purposes in very preterm infants; although, the technology likely requires further validation in preterm and high-risk term populations.

Instructional guides for filming infant movements at home are effective for the General Movements Assessment

AIM

To determine the effectiveness of two instructional guides to obtain video recordings for the General Movements Assessment (GMA).

METHODS

A cross-sectional study of a community sample of family participants with low-risk term newborn infants recruited via social media and randomly allocated to receive one of two instructional guides (detailed or quick versions) to film their infant's movements at home. Participants returned videos via a secure Research Electronic Database Capture link and videos were scored for quality across 10 criteria, along with scoring the GMA. Participants were surveyed about their perceptions of the instructional guides and electronic file transmission.

RESULTS

Seventy-six parents of infants were enrolled and randomly allocated to receive detailed (n = 38) and quick (n = 38) instructions to film their infant for a GMA. Videos were returned by 87% (95% confidence interval (CI) 72%, 96%) of detailed instruction users and 84% (95% CI 69%, 94%) of quick instruction users. The GMA could be conducted on all returned videos. The mean score for video quality was 9.9/10 (standard deviation 0.4, 95% CI 9.7, 10.0) for detailed instructions and 9.7 (standard deviation 0.6, 95% CI 9.4, 9.9) for quick instructions. Overall, participants felt that either instructional guide was easy to use. Fifteen (20%) participants had difficulties with video file transmission, requiring additional support.

CONCLUSIONS

Parents can successfully use one of two different instructional guides for filming their infant's movements for GMA; however, support should be provided for safe and easy file transmission.

Video-Based Automatic Baby Motion Analysis for Early Neurological Disorder Diagnosis: State of the Art and Future Directions

Neurodevelopmental disorders (NDD) are impairments of the growth and development of the brain and/or central nervous system. In the light of clinical findings on early diagnosis of NDD and prompted by recent advances in hardware and software technologies, several researchers tried to introduce automatic systems to analyse the baby's movement, even in cribs. Traditional technologies for automatic baby motion analysis leverage contact sensors. Alternatively, remotely acquired video data (e.g., RGB or depth) can be used, with or without active/passive markers positioned on the body. Markerless approaches are easier to set up and maintain (without any human intervention) and they work well on non-collaborative users, making them the most suitable technologies for clinical applications involving children. On the other hand, they require complex computational strategies for extracting knowledge from data, and then, they strongly depend on advances in computer vision and machine learning, which are among the most expanding areas of research. As a consequence, also markerless video-based analysis of movements in children for NDD has been rapidly expanding but, to the best of our knowledge, there is not yet a survey paper providing a broad overview of how recent scientific developments impacted it. This paper tries to fill this gap and it lists specifically designed data acquisition tools and publicly available datasets as well. Besides, it gives a glimpse of the most promising techniques in computer vision, machine learning and pattern recognition which could be profitably exploited for children motion analysis in videos.

The developing brain: Challenges and opportunities to promote school readiness in young children at risk of neurodevelopmental disorders in low- and middle-income countries

This paper discusses possibilities for early detection and early intervention in infants with or at increased risk of neurodevelopmental disorders in low- and middle-income countries (LMICs). The brain's high rate of developmental activity in the early years post-term challenges early detection. It also offers opportunities for early intervention and facilitation of school readiness. The paper proposes that in the first year post-term two early detection options are feasible for LMICs: (a) caregiver screening questionnaires that carry little costs but predict neurodevelopmental disorders only moderately well; (b) the Hammersmith Infant Neurological Examination and Standardized Infant NeuroDevelopmental Assessment (SINDA) which are easy tools that predict neurodisability well but require assessment by health professionals. The young brain's neuroplasticity offers great opportunities for early intervention. Ample evidence indicates that families play a critical role in early intervention of infants at increased risk of neurodevelopmental disorders. Other interventional key elements are responsive parenting and stimulation of infant development. The intervention's composition and delivery mode depend on the infant's risk profile. For instance, in infants with moderately increased risk (e.g., preterm infants) lay community health workers may provide major parts of intervention, whereas in children with neurodisability (e.g., cerebral palsy) health professionals play a larger role.

Telehealth Program for Infants at Risk of Cerebral Palsy during the Covid-19 Pandemic: A Pre-post Feasibility Experimental Study

Aim: To verify the effects of a telerehabilitation program for infants at high risk for Cerebral Palsy (CP) during the COVID-19 pandemic.Method: Longitudinal study. Infants were aged 3-18 months corrected age, at risk of developmental delay. The General Movement Assessment or a neurologic examination were performed to identify the risk of CP. Motor function was assessed using the Gross Motor Function Measure-88 (GMFM-88) and the Alberta Infant Motor Scale (AIMS). Caregivers of infants at high risk of CP applied a home-based program supervised by a Physical therapist, five times a week over 12 weeks. The program included guidance for optimal positioning, optimization of goal-directed activities, environmental enrichment, and educational strategies.Results: 100 infants at risk for delayed motor development were recruited. Eighteen infants were classified at high risk of CP, and 10 families completed telerehabilitation (83% final retention rate). No adverse events were reported. Adherence to the telecare program was high (90%). The costs were low. We found increased scores for all dimensions and the total score of the GMFM-88, and the AIMS percentile at the end of the intervention. Most infants presented a clinically significant change for the GMFM-88.Conclusions: The telecare program was feasible.

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.

Technology-assisted quantification of movement to predict infants at high risk of motor disability: A systematic review

AIM

To systematically review the scientific literature to determine the predictive validity of technology-assisted measures of observable infant movement in infants less than six months of corrected age (CA) to identify high-risk of motor disability.

METHOD

A comprehensive search for randomised and non-randomised controlled trials, cohort studies and cross-comparison trials was performed on five electronic databases up to Feb 2021. Studies were included if they quantified infant movement before 6 months CA using some method of technology-assistance and compared the instrumented measure to a diagnostic clinical measure of neurodevelopment. Studies were excluded if they did not report a technology-assisted measure of infant movement. Methodological quality of the included studies was assessed using the Downs and Black scale.

RESULTS

23 studies met the full inclusion and exclusion criteria. Methodological quality of the included papers ranged from 9 to 24 (out of 26) on the Downs and Black scale. Infant movement assessments included the General Movements Assessment (GMA) and domains of the Hammersmith Infant Neurological Assessment (HINE). Studies used 2D video recordings, RGB-Depth recordings, accelerometry, and electromagnetic motion tracking technologies to quantify movement. Analytical approaches and movement features of interest were individual and varied. Technology assisted quantitative assessments identified cases of later diagnosed CP with sensitivity 44-100 %, specificity 59-95 %, Area under the ROC Curve 82-93 %; and typical development with sensitivity range 30-46 %, specificity 88-95 %, Area under the ROC Curve 68 %.

INTERPRETATION

Technology-assisted assessments of movement in infants less than 6 months CA using current technologies are feasible. Validation of measurement tools are limited. Although methods and results appear promising clinical uptake of technology-assisted assessments remains limited.