Spontaneous Leg Movements Measured by Wearable Sensors in Infancy Differentiate Later Risk for Cerebral Palsy.

To investigate the relationship between early motor repertoire, assessed using the General Movements Optimality Score - Revised (GMOS-R), and motor outcomes at 1, 2 and 5-years' corrected age (CA) in infants born <30weeks' gestation. This prospective cohort study included General Movement Assessments recorded at 34weeks' post menstrual age (PMA) (n=76) and term equivalent age (n=66) in infants born <30weeks' gestation (mean gestational age 27.6weeks, standard deviation 1.4; 53% male). Early motor repertoire was assessed using the GMOS-R. Motor outcomes were measured using the Alberta Infant Motor Scale (AIMS) and Neurosensory Motor Developmental Assessment (NSMDA) at 1-year CA; the Bayley Scales of Infant and Toddler Development, Third Edition motor composite score and/or cerebral palsy at 2-years' CA; and the Movement Assessment Battery for Children, Second Edition and/or cerebral palsy at 5-years' CA. Higher GMOS-R scores at both 34weeks' PMA and term equivalent age were associated with better motor outcomes at 1-year CA (34-weeks: AIMS regression coefficient=0.35, 95% confidence interval [CI]=0.05, 0.65, p=0.02; term equivalent age: regression coefficient=0.50, 95% CI=0.14, 0.86, p=0.01; NSMDA regression coefficient=-0.17, 95% CI=-0.30, -0.03, p=0.01; term equivalent age: regression coefficient=-0.20, 95% CI=-0.36, -0.04, p=0.02). However, there was limited evidence of an association between GMOS-R scores and motor outcomes at 2- and 5-years' CA. Higher GMOS-R scores during the preterm and term period are associated with better motor outcomes at 1-year CA in infants born <30weeks' gestation, suggesting potential value for early identification of risk of motor delay and subsequent direction of early intervention. This relationship, however, was not evident at 2 and 5-years' CA.

To evaluate and synthesize the literature on machine learning and deep learning methodologies in automated infant General Movements Assessment (GMA) for early prediction of cerebral palsy (CP). A scoping review was conducted using the framework of Arksey and O'Malley and reported in accordance with the PRISMA/PRISMA-ScR guidelines. Literature published from 2015 to February 2025 was searched across major databases. Included studies were analysed for key factors commonly identified as influencing GMA classification performance. Forty-three studies met the inclusion criteria. The most common analysis pipeline involved deep learning-based markerless pose reconstruction, followed by classification, typically using support vector machines (machine learning) and convolutional neural networks (deep learning). Smaller datasets (12-38 infants) yielded greater accuracy (up to 100%) in maximum general movement classification than larger datasets (557-776 infants), which achieved up to 93.8%. All CP classification studies reported accuracies above 90%. Although deep learning methods generally outperform traditional machine learning approaches, reported performance varies substantially across studies and is shaped by factors such as data quality and diversity, recording conditions, pose estimation methods, feature representation, and classifier design. Unlike earlier reviews, this work provides a comprehensive synthesis of recent automated GMA literature, explicitly linking methodological choices across data acquisition, pose estimation, feature extraction, and classification to differences in reported performance, generalizability, and clinical interpretability. By consolidating these interdependent sources of variability into a single clinically oriented framework, this review offers a stand-alone reference to the field and provides guidance for developing more robust and clinically meaningful automated GMA systems for early detection of CP.

Automating the General Movements Assessment: Potential, pitfalls, and a path forward.

Repeatable outpatient screening tools are needed to support early identification of infants at neurodevelopmental risk. We assessed the feasibility of an automated, contactless radar-based movement analysis for outpatient screening in infants without overt neurological concerns. Infants born at 29-41 weeks of gestation underwent outpatient assessments between 37-60 weeks of postmenstrual age; infants with congenital anomalies, major brain injury, or clinical instability were excluded. Seventy-seven infants contributed 100 assessments. Each visit included a 450-second frequency-modulated continuous-wave (FMCW) radar recording. A pretrained model classified 45 non-overlapping 10-second epochs for asymmetric movements and cramped-synchronized general movements, and the NeuroRiskAbility (NRA) index was computed. NRA-based classification was compared with the outpatient clinical classification based on neurological and developmental assessment, including developmental concerns warranting follow-up. With prespecified parameters (α = 0.5, cutoff 20), concordance with clinical classification was 58%. Exploratory within-cohort recalibration (α = 0.4, cutoff 24) increased concordance to 93% (κ = 0.86). NRA values showed no monotonic association with postmenstrual age (ρ = 0.045, p = 0.658). Among 23 infants assessed twice, 14 (61%) changed clinical classification between visits. A brief, non-contact radar-based model can generate an automated movement-based index with high concordance to outpatient clinical classification, supporting feasibility for serial surveillance to identify infants requiring closer follow-up in early infancy. Contactless frequency-modulated continuous-wave (FMCW) radar enables brief outpatient recordings to quantify spontaneous infant movements and generate an automated movement-based index with high concordance to routine outpatient clinical classification. Routine outpatient clinical classification often changed over short intervals in infants without overt neurological concerns, highlighting the need for serial surveillance. A low-burden, privacy-preserving, automated tool may enable scalable serial assessment in outpatient follow-up, supporting earlier identification of infants at risk for motor delay who may benefit from closer monitoring or referral for formal assessment.

The General Movement Assessment (GMA) according to Prechtl’s method has the best predictive value for early detection of Cerebral Palsy (CP) in infants under 5 months of age. However, access to specialists in this assessment is scarce, particularly in lower and middle-income countries. The main objective was to determine the better accelerometric features for distinguishing spontaneous movements of infants with risk factors for CP (RF), and healthy controls (HC), under 9 weeks. We carried out a cross-sectional study. General movements (GMs) were recorded in 48 infants under 9 weeks of age, 12 RF and 36 HC, using an instrumented assessment (accelerometers on limbs and trunk) and Prechtl’s method. Clinical variables and 62 accelerometer parameters were collected and analysed using descriptive and inferential statistics. To classify infants, we employed the Random Forest Classifier, based on their condition (Healthy vs. Risk Factors), with subsequent analysis of model accuracy. Afterward, we determined the features that best differentiated between the two groups. We found 46 parameters that differentiate RF and HC groups. Random Forest classified infants with 100% accuracy. Eight parameters were optimal for differentiation, and half of them were from trunk sensors. Wireless accelerometry effectively identified infant movement patterns indicative of cerebral palsy risk factors. This study establishes a scalable, personnel-independent screening of neonatal neurodevelopmental disorders, especially where specialized expertise is unavailable via Precht´s method. Deployment would facilitate widespread, cost-effective early risk stratification for CP.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-026-54620-y.

Background and Objectives: Early identification and referral for intervention of former premature infants at risk of neurodevelopmental impairment is considered a standard of care. The main purpose of this review was to assess the optimal timing of the first visit in a neurodevelopmental follow-up programme in order to identify at-risk infants in a timely and reliable manner. Materials and Methods: We considered three possible moments for the first evaluation: before 37 weeks postmenstrual age, at Term Equivalent Age (TEA, also known as 40 weeks postmenstrual age) and at 3-5 months corrected age (CA). A structured scoping review, informed by PRISMA-ScR principles, was performed. We searched PubMed/MEDLINE, Web of Science Core Collection, and Scopus from database inception through March 2026, combined with a Wohlin-type snowballing strategy. Two assessment techniques were evaluated: the Amiel-Tison neurological examination of the newborn and infant, and the General Movements Assessment (GMA). We collected data on sensitivity, specificity, and positive and negative predictive values at each of the three moments, and reviewed whether early intervention was associated with improved prognosis. Results: Intervention initiated before 12 months of age was associated with improved cognitive and motor outcomes in infancy compared with standard care; an additional benefit was observed when intervention started before discharge, particularly for cognitive outcomes in infancy. Both examinations showed very good specificity and negative predictive value at all three evaluation moments, consistent with their shared optimality concept. Sensitivity and specificity increased with the infant's age. At each moment, the examinations identified (i) a high-risk group clearly requiring early intervention, (ii) a "grey zone" with uncertain evolution requiring closer surveillance, and (iii) a normal group with a very low risk of adverse outcomes. Combining two examination techniques at the same visit consistently improved discriminative and predictive performance. Conclusions: Evaluation at TEA alone may be too early because some abnormal findings normalize by 3 months CA, yet also too late for the most severely affected infants, who may manifest abnormal signs before term. We propose a stratified approach, with repeated evaluations using both the Amiel-Tison examination and GMA at 35-37 weeks postmenstrual age, at TEA, and at 3-5 months CA, in order to progressively identify infants at risk and refer them to appropriate early intervention. This proposal requires validation through prospective, well-designed research.

Beyond "low tone". What do the General Movements Assessment and Motor Optimality Score tell us about infants with developmental central hypotonia? A scoping review.

Preterm birth is associated with increased oxidative stress and brain dysmaturation, contributing to adverse neurodevelopmental outcomes. Preterm infants are physiologically unable to produce melatonin during early postnatal life, potentially increasing their vulnerability to oxidative injury. We planned and conducted a prospective, multicentre, randomized, double-blind, placebo-controlled study to investigate whether 15 days of early oral melatonin (ME) supplementation after birth increases ME levels and reduces oxidative stress in preterm newborns at the end of administration period. The level of malondialdehyde (MDA), a lipid peroxidation product, was considered an early biological marker of the efficacy of ME treatment. The results of the first phase of the study are already available to view on Journal of Pineal Research. Here, we presented the results of the second phase of the trial, in which we investigated whether early oral ME supplementation supports clinical outcomes and brain maturation at term-equivalent age (TEA) in 54 infants with a gestational age of ≤ 29 weeks + 6 days, who received either oral ME or a placebo (PL) for 15 days after birth. No significant differences were observed between groups in the incidence of major neonatal comorbidities in particular patent ductus arteriosus (PDA), sepsis, necrotizing enterocolitis (NEC), bronchopulmonary dysplasia (BPD) and retinopathy of prematurity (ROP). Cranial ultrasound findings and clinical assessments using General Movements (GMs), the Neonatal Neurobehavioral Scale (NNNS), and the NAVEG scale showed comparable results. On the other hand, magnetic resonance imaging (MRI) revealed a significantly higher total brain maturity score in ME-treated infants compared with the PL group (46 vs. 43; p = 0.011), with in particular more advanced white matter and subplate compartment maturation. Quantitative MRI analysis demonstrated significantly higher T1-weighted/T2-weighted signal ratio values in major white matter tracts, including the pyramidal tract, consistent with enhanced myelination. Additionally, we observed a positive trend in the association between reduced serum MDA levels-reflecting lower lipid peroxidation-at the end of ME administration and higher T1-weighted/T2-weighted ratio values in the pyramidal bundles in subjects at TEA. These findings suggest that early oral melatonin supplementation supports cerebral white matter maturation in preterm infants, potentially through antioxidant mechanisms. Melatonin may represent a promising adjunctive strategy to mitigate oxidative stress-related brain dysmaturation in this vulnerable population, warranting further investigation in larger trials. Trial Registration: ClinicalTrials.gov Registration Number: NCT04235673; Web link to study on registry: https://clinicaltrials.gov/study/NCT04235673.

Neonatal imitation (NI) is a foundational marker of early social-cognitive development, yet its universality remains debated, particularly in non-WEIRD (Western, Educated, Industrialized, Rich, and Democratic) populations and in infants at higher neurodevelopmental risk. This study examined NI in healthy late-preterm newborns, compared their responses with term infants, and explored the prognostic value of imitation using longitudinal Prechtl's General Movements Assessment (GMA). Twenty-three late-preterm and 27 term infants were tested within 72 h of birth for facial imitation using a blinded, counterbalanced protocol focusing on mouth opening (MO) and tongue protrusion (TP). Neurodevelopmental status was assessed using Prechtl's GMA at corrected ages of 5 and 11 weeks. Both groups exhibited significantly more TP gestures in response to the matching TP model (late-preterm: p = 0.002; term: p <0.001), whereas MO responses did not differ significantly (p >0.05). Imitative behavior was present from Day 1 (p = 0.005) and strengthened on Days 2-3 (p <0.001). No significant sex differences were observed. NI scores did not significantly correlate with GMA outcomes (p >0.05), likely reflecting the clinical homogeneity of this mostly healthy sample. Selective NI for TP emerges within the first days of life in both late preterm and term infants. By including a non-WEIRD population and late preterm infants, this study expands the generalizability of NI. Strengths include early assessment, blinded scoring, and standardized neurodevelopmental evaluation. NI appears robust across gestational age and sociocultural contexts, highlighting its potential as an early neurobehavioral marker. Further longitudinal research in diverse populations is warranted.

The role of asymmetrical finger postures during fidgety age in the prediction of unilateral cerebral palsy.

Background/Objectives: Assessment of infant General Movements (GMs) is essential for early detection of neurological disorders such as cerebral palsy, but current methods depend on expert interpretation. This study proposes an automated and interpretable framework for infant movement classification using pose-based representations from RGB videos. Methods: A pose-driven pipeline was developed to extract 2D skeletal key points using a two-stage tracking strategy. Joint coordinates were normalized using the shoulder center and inter-shoulder distance. Videos were segmented into overlapping temporal windows, and each segment was represented using Pose-LBP histograms and motion ratio features. Classification was performed with a cost-sensitive subspace k-nearest neighbor ensemble (CSS-kNN-E). Performance was evaluated using stratified 10-fold cross-validation on a five-class infant movement dataset. Results: The proposed method achieved 99.16% (±0.48%) accuracy, 99.19% (±0.50%) sensitivity, 99.76% (±0.13%) specificity, and 99.23% (±0.48%) F1-score. The model demonstrated strong discrimination across classes and robustness to class imbalance. Conclusions: The framework provides an accurate and scalable solution for automated infant movement analysis. It reduces dependency on expert evaluation and has strong potential for early clinical screening and decision support.

HighlightsWhat are the main findings?The Early Intensive Stojčević–Polovina Rehabilitation Method (EIR–SPM) was associated with a more optimal early motor repertoire.The Motor Optimality Score–Revised (MOS–R) increased between the first and second fidgety assessments during a period of intensive rehabilitation and ongoing neuroplasticity.What are the implications of the main findings?Rehabilitation in high-risk infants can be initiated during the writhing period.In high-risk infants, rehabilitation can be achieved by using family settings.Background/Objectives: Abnormal general movements (GMs) in high-risk infants are among the most sensitive early predictors of cerebral palsy (CP) and other neurodevelopmental disorders. This study described changes in the quality of GMs over time in high-risk infants who received the Early Intensive Stojčević–Polovina Rehabilitation Method (EIR–SPM). The EIR–SPM is a rehabilitation method designed for children with CP, those at risk of developing CP, and children with other developmental disabilities. In high-risk infants, it is initiated within the first three months of corrected age, preferably while writhing movements (WMs) are still present. Methods: This study was conducted in eight high-risk infants with abnormal WMs and structural brain injury. The EIR–SPM was initiated between 41 and 47 weeks postmenstrual age (PMA) and was applied until 60 weeks PMA. Prechtl’s General Movements Assessment (GMA), the Detailed GM score, and the Motor Optimality Score–Revised (MOS–R) were assessed. Results: During the writhing period, two infants showed a poor repertoire (PR) pattern and six showed a cramped–synchronized (CS) pattern of GMs; at follow-up, three showed PR, and five showed CS. During the fidgety period, two infants showed normal fidgety movements (F+), two sporadic fidgety movements (sFM), one infant showed abnormal fidgety movements (aFM), and three showed absent fidgety movements (F−) at the first assessment, while at the second assessment, three infants showed F+, two sFM, one aFM, and two F−. The median Detailed GM score increased from 12 (range 11–17) to 13.5 (range 11–19; p = 0.068). The median MOS–R increased from 17.0 (range 12–24) to 19.5 (range 17–27) between the two fidgety assessments (p = 0.027). Conclusions: Improvements in motor repertoire, reflected by increased MOS–R scores, were observed during the EIR–SPM initiated in the writhing period. Larger controlled studies are needed to confirm these preliminary observations.

Thyroid hormones (THs) play a vital role in neonatal development. The present study aimed to evaluate the association between thyroid function and bronchopulmonary dysplasia (BPD) incidence as well as neurodevelopment in extremely and very preterm infants. This retrospective study involved 125 preterm infants born between 26 and 32 weeks of gestation from January 2020 to October 2025. Thyroid function tests were performed at 2 and 4 weeks after birth, and neurodevelopment was assessed using General Movements (GMs) at 36 weeks and 40 weeks of postmenstrual age (PMA). Among the 125 infants, 40 infants (32%) developed BPD; of these 40 infants, 27 and 13 infants were classified as grade 1 and grade 2 BPD, respectively. Notably, the grade 2 BPD group had significantly lower TH levels compared to both grade 1 BPD and non-BPD groups (P <0.05). Additionally, the non-BPD and grade 1 BPD groups showed a tendency to exhibit better neurological development at 36 and 40 weeks PMA compared to the grade 2 BPD group, although this difference was not significant. Serial thyroid function monitoring during the first month of life may be useful in identifying extremely and very preterm infants who are most at risk of developing severe BPD (grade 2). Future intervention studies are needed to determine whether thyroid replacement therapy in this particular high-risk group may reduce the severity of BPD and potentially improve neurodevelopmental outcomes.

To describe writhing General Movements Assessment (GMA) classification and General Movement Optimality Score-Revised (GMOS-R) profiles in the general population; to explore relationships between GMOS-R scores and GMA classification, age of assessment and infant socio-demographic factors; and to establish the inter-rater reproducibility of writhing age GMA classification and GMOS-R. A cross-sectional study of 1861 infants recruited from the general population in Perth, Western Australia, including 7.5% born preterm. Parent-recorded videos were collected between 41- and 45-weeks post-menstural age, when writhing movements are typically observed. General movements (GMs) classification and GMOS-R were assessed independently by at least 2 experienced advanced-trained clinicians. The majority of infants' GMs were classified as normal (66.8%) or poor repertoire (33.2%), with one infant's movements classified as cramped synchronized (0.1%). The median GMOS-R score was 33 (interquartile range 27-36). The GMOS-R differentiated GMA classifications. Lower gestational age, any nursery admission, minority ethnicity, and older age at video collection were each associated with a small but statistically significant reduction in GMOS-R scores. GMA classification had excellent inter-rater reliability and agreement. Total GMOS-R had excellent inter-rater reliability and moderate agreement. Although most infants had normal GMs there was a high prevalence of poor repertoire GMs in the general population. GMOS-R scores effectively differentiated movement quality within the poor repertoire classification. This study provides population-based percentile ranks for interpreting individual post-term GM assessments and as a reference for future research.

ObjectiveTo evaluate AI-assisted GMA performance for (i) prediction of later cerebral palsy (CP) diagnosis and (ii) classification of expert-rated GMA labels, and to assess heterogeneity and risk of bias.MethodsA systematic review and meta-analysis was conducted in accordance with PRISMA 2020 guidelines. A total of 105 studies were included in qualitative synthesis, of which 28 were eligible for quantitative synthesis. Random-effects meta-analysis of proportions with logit transformation was used to estimate pooled diagnostic accuracy.ResultsOf 105 eligible studies in qualitative synthesis, 28 were included in quantitative synthesis (17 CP diagnosis outcomes; 11 expert GMA label outcomes). For CP diagnosis outcomes, the pooled diagnostic accuracy was 0.884 (95% CI: 0.838-0.918). For expert-rated GMA label outcomes, the pooled classification accuracy was 0.848 (95% CI: 0.761-0.908). Heterogeneity was substantial across analyses.InterpretationAI-assisted GMA shows high pooled performance for both CP diagnosis prediction and expert-label classification; however, certainty remains very low due to heterogeneity and risk of bias. No single GM developmental phase, or sensor modality, demonstrated clear superiority, underscoring the importance of standardized protocols, high-quality datasets, and transparent validation. These findings support the clinical potential of AI-enabled GMA as an objective and scalable screening tool, particularly in settings with limited access to specialized expertise.

The objective of this study is to determine the predictive value of magnetic resonance imaging (MRI), amplitude-integrated electroencephalography (aEEG), the Hammersmith Neonatal Neurological Examination (HNNE), and the General Movements Assessment (GMA) for cerebral palsy (CP) in neonates with hypoxic-ischemic encephalopathy (HIE), and to evaluate whether combining these modalities improves diagnostic accuracy.In this prospective two-center cohort study, 53 term or late-preterm infants with HIE treated with standardized therapeutic hypothermia (33.5°C for 72 hours) were evaluated. aEEG and MRI findings were compared with concurrent HNNE and GMA results. CP was diagnosed during follow-up by a pediatric neurologist blinded to neonatal data. Diagnostic performance was analyzed using receiver-operating characteristic curves and multivariable logistic regression according to the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines.CP developed in 11 infants (20.8%). aEEG showed the highest predictive accuracy (area under the curve = 0.816 [95% confidence interval: 0.65-0.98]), and abnormal aEEG independently predicted CP (odds ratio = 18.5, p = 0.004). The combined "MRI or aEEG abnormal" model achieved the best overall accuracy (86.8%), with sensitivity = 90.9% and negative predictive value = 97.3%. MRI and HNNE had moderate predictive value, whereas GMA showed high specificity but low sensitivity.aEEG emerged as a robust and independent early biomarker for CP prediction after HIE. Combining aEEG with MRI substantially enhanced diagnostic precision, reflecting complementary functional and structural brain injury mechanisms. Although HNNE and GMA add screening value, they are insufficient alone. Standardized multimodal protocols integrating structural (MRI), functional (aEEG), and clinical (HNNE-GMA) assessments should be incorporated into clinical practice to improve early prognostication and guide neuroprotective interventions. · Early multimodal tools improve CP prediction.. · MRI and aEEG show higher diagnostic accuracy.. · Low HNNE scores indicate increased CP risk.. · Abnormal GMA supports early neurological impairment.. · Combining MRI + GMA + HNNE enhances prediction..

High-risk infants, particularly those with Cerebral Palsy (CP), face major challenges. Early identification of CP is crucial to reducing the disease burden and initiating early intervention. The General Movement Assessment (GMA) is a gold-standard assessment that is cost-effective, non-invasive, and highly reliable. However, translation into clinical practice remains challenging in low-resource settings. To implement GMA for at least 80% of the eligible infants accessing the High-Risk Neonatal Follow-up clinic (HRNFC) and assess its contribution to the follow-up rates. This study was conducted in HRNFC from July 2024 to March 2025 and is ongoing. After counselling and consent, eligible infants (37–43 weeks and 9–20 weeks of corrected gestational age (CGA) were enrolled. GMA standard videos were taken, stored securely, and reported by 2 certified assessors, then shared with parents. Infants with absent/ abnormal fidgety were referred for multidisciplinary team (MDT) evaluation. 188 infants were enrolled, and 252 GMA videos were recorded. Since August 2024, GMA enrolment sustained at 80%. 16 infants were identified with absent/ abnormal fidgety movements, and 12(75%) of them accessed MDT services before 5 months of CGA. Follow-up rates improved at 40 weeks (58%-65%; p = 0.1736) and at 3 months (30%-41%; p = 0.0422). 75% of infants accessed MDT before 5 months of CGA (p = 0.0001). GMA was successfully implemented and sustained as part of routine HRNFC. The majority (75%) of the identified infants who were abnormal were enrolled in MDT services before 5 months, with improved follow-up continuity and access to early intervention. The GMA corner setup demonstrates a high cost benefit.

Developmental assessment of young children is challenging. Detailed assessment with a trained therapist is prohibitively expensive for widespread screening, reserved only for high-risk children or those in whom early concern is raised. Thus, even in high-income countries, only 1% to 2% of all children will be assessed using detailed and objective measurements. The other 98% may, at best, be screened using parental questionnaires, with inherent difficulties. Parents can generally be relied upon to accurately list the motor skills achieved; however, the quality of movement and normality of tone and posture is more difficult to capture. Hence a wide gap exists between universal parental questionnaires and standardized face-to-face developmental or neurological assessment. The Ages and Stages Questionnaires are the most universally recommended, but have low sensitivity for mild delay, particularly in typically developing cohorts.1 Airaksinen et al. raise the question as to whether technology can fill this gap and allow reliable universal early motor screening.2 The authors present data on the use of a wearable suit for the automated assessment of motor development in young children.2 Families of 42 infants were given wearable suits with in-built sensors (Motor Assessment of Infants with a JUmpsuit [MAIJU]) which tracked their movements and postures for an average of 2 hours. Automated reports of posture and movement were generated (BABA infant motor score) with a high correlation with an in-clinic or video-assessed Alberta Infant Motor Scale. Why is early screening of motor milestones important? These milestones are surrogate markers of overall brain and nervous system development. Motor delay may be the first sign of general developmental delay and often precedes social, behavioural, and cognitive delay. Equally, aberrant motor development may herald evolving signs of cerebral palsy (CP). The success of early CP screening in high-risk infants through the combination of imaging, general movements assessment, and the Hammersmith Infant Neurological Examination remains limited to infants with clear risk factors at birth.3 We know that at least 50% of CP cases are born outside of this risk profile and their aberrant motor development must be picked up by parents who then seek out trained professionals; a gap which results in delayed detection and delayed intervention. Technology might also help to fill this gap. Videos of an infant's early movements provided by carers via smartphone-based applications can be accurately analysed by remote assessors and are comparable to in-person general movements assessment. However, the manpower and expertise required for remote human assessment is still prohibitive for universal screening. This has driven researchers to explore the ability of artificial intelligence (AI) to replace the remote assessor and to risk-stratify for CP. Results are promising but currently limited to a few small populations.4 Collaboration between these groups is vital to allow validation of these promising AI models, and to ensure that they are suitable for use in all populations, not limited to specific cultural norms. Large libraries of video and sensor-based data from geographically and culturally diverse populations will be required. Data will need to be analysed in a way which is compliant with ethical and data-sharing regulations to ensure protection of the children involved.5 Whilst early general movements assessments are a snapshot at a specific phase in early development, serial recordings of movement and posture over the first year of life may be required to fulfil the promise of early motor screening for all. The MAIJU suit is not designed for CP screening and has not yet been validated in a high-risk group. It is unlikely to detect subtle asymmetries of tone. However, it offers the potential of early serial tracking of movement and posture and is a good step in the right direction. Not required.

Infants who have meningitis are at increased risk of adverse neurodevelopmental outcomes. Early screening tools can add value in identifying infants who may benefit from early intervention supports. The Motor Optimality Score Revised (MOS-R) is a relatively new tool used between 3 and 5months of age that may have predictive value. To describe the motor optimality of infants diagnosed with meningitis and determine whether the MOS-R is associated with development at 12months of age. A retrospective, single-center, cohort study from 2011 to 2023. The MOS-R was taken at 3-4months corrected gestational age and development was assessed using the Bayley Scales of Infant and Toddler Development (Bayley) III/IV at 12 or 24months of age. Participants included 73 infants (mean gestational age 37+3), admitted to hospital with meningitis before 4months of age, who had a general movements assessment. Infants had a mean MOS-R of 22.3 (SD 3.29), with most infants in the study having MOS-R scores indicating mildly reduced optimality (78.8%). Significant positive correlations were found between MOS-R total scores and the receptive language, expressive language and gross motor domains of the Bayley III/IV. Infants with MOS-R scores <21 were more likely to show developmental delays in cognition, expressive language and receptive language. For infants who had meningitis, MOS-R scores were associated with development at 12months of age. The MOS-R, used in addition to GMA may have the potential to identify infants who would benefit from early intervention to support their development. Further research is needed to understand the use of the MOS-R, alongside other screening tools for populations at risk of adverse neurodevelopmental outcomes.