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.

Expiratory airflow at 7-8 years of age in children born extremely low birthweight from 14 years before to 14 years after the introduction of exogenous surfactant.

Background: It is unclear if expiratory airflow in survivors born extremely low birth weight (ELBW; 500-999 g) has improved after the introduction of exogenous surfactant into clinical practice in 1991. The primary aim of this study was to describe the changes in airflow at 7-8 years of age of survivors born ELBW in five discrete cohorts from 14 years before to 14 years after the introduction of exogenous surfactant into clinical practice. Methods: The cohorts comprised consecutive survivors born ELBW in 1977-82 and 1985-87 at the Royal Women's Hospital, Melbourne, and in 1991-92, 1997 and 2005 in the state of Victoria, Australia. Survival rates to 2-years of age for infants born ELBW in the state of Victoria rose from approximately 1-in-4 to 3-in-4 over the time of this study. Expiratory airflow measurements at 7-8 years included the forced expired volume in 1 s (FEV1), converted to z-scores for age, height, sex, and race. Findings: There were 596 ELBW participants with expiratory flow data, 280 (47%) of whom had bronchopulmonary dysplasia (BPD). Overall, there was little change in zFEV1 over the 28-year period (mean change per year; 0.003, 95% CI -0.010, 0.015, P = 0.67). There was, however, evidence of an interaction between BPD and year; zFEV1 in those who had BPD fell over time (mean change per year -0.019, 95% CI -0.037, -0.009, P = 0.035), whereas zFEV1 improved in those who did not have BPD (mean change per year 0.021, 95% CI 0.006, 0.037, P = 0.007). Interpretation: Contrary to recent evidence, expiratory airflow of children born ELBW has not improved with the introduction of surfactant, and may be deteriorating in those who had BPD. Funding: National Health and Medical Research Council (Australia); Victorian Government's Operational Infrastructure Support Program.

Postnatal Brain Growth Assessed by Sequential Cranial Ultrasonography in Infants Born <30 Weeks' Gestational Age.

BACKGROUND AND PURPOSE: Brain growth in the early postnatal period following preterm birth has not been well described. This study of infants born at <30 weeks' gestational age and without major brain injury aimed to accomplish the following: 1) assess the reproducibility of linear measures made from cranial ultrasonography, 2) evaluate brain growth using sequential cranial ultrasonography linear measures from birth to term-equivalent age, and 3) explore perinatal predictors of postnatal brain growth. MATERIALS AND METHODS: Participants comprised 144 infants born at <30 weeks' gestational age at a single center between January 2011 and December 2013. Infants with major brain injury seen on cranial ultrasonography or congenital or chromosomal abnormalities were excluded. Brain tissue and fluid spaces were measured from cranial ultrasonography performed as part of routine clinical care. Brain growth was assessed in 3 time intervals: <7, 7-27, and >27 days' postnatal age. Data were analyzed using intraclass correlation coefficients and mixed-effects regression. RESULTS: A total of 429 scans were assessed for 144 infants. Several linear measures showed excellent reproducibility. All measures of brain tissue increased with postnatal age, except for the biparietal diameter, which decreased within the first postnatal week and increased thereafter. Gestational age of ≥28 weeks at birth was associated with slower growth of the biparietal diameter and ventricular width compared with gestational age of <28 weeks. Postnatal corticosteroid administration was associated with slower growth of the corpus callosum length, transcerebellar diameter, and vermis height. Sepsis and necrotizing enterocolitis were associated with slower growth of the transcerebellar diameter. CONCLUSIONS: Postnatal brain growth in infants born at <30 weeks' gestational age can be evaluated using sequential linear measures made from routine cranial ultrasonography and is associated with perinatal predictors of long-term development.

The Baby Moves prospective cohort study protocol: using a smartphone application with the General Movements Assessment to predict neurodevelopmental outcomes at age 2†years for extremely preterm or extremely low birthweight infants.

INTRODUCTION: Infants born extremely preterm (EP; <28 weeks' gestation) and/or with extremely low birth weight (ELBW; <1000 g birth weight) are at increased risk for adverse neurodevelopmental outcomes. However, it is challenging to predict those EP/ELBW infants destined to have long-term neurodevelopmental impairments in order to target early intervention to those in most need. The General Movements Assessment (GMA) in early infancy has high predictive validity for neurodevelopmental outcomes in preterm infants. However, access to a GMA may be limited by geographical constraints and a lack of GMA-trained health professionals. Baby Moves is a smartphone application (app) developed for caregivers to video and upload their infant's general movements to be scored remotely by a certified GMA assessor. The aim of this study is to determine the predictive ability of using the GMA via the Baby Moves app for neurodevelopmental impairment in infants born EP/ELBW. METHODS AND ANALYSIS: This prospective cohort study will recruit infants born EP/ELBW across the state of Victoria, Australia in 2016 and 2017. A control group of normal birth weight (>2500 g birth weight), term-born (≥37 weeks' gestation) infants will also be recruited as a local reference group. Parents will video their infant's general movements at two time points between 3 and 4 months' corrected age using the Baby Moves app. Videos will be scored by certified GMA assessors and classified as normal or abnormal. Parental satisfaction using the Baby Moves app will be assessed via survey. Neurodevelopmental outcome at 2 years' corrected age includes developmental delay according to the Bayley Scales of Infant and Toddler Development-III and cerebral palsy diagnosis. ETHICS AND DISSEMINATION: This study was approved by the Human Research and Ethics Committees at the Royal Children's Hospital, The Royal Women's Hospital, Monash Health and Mercy Health in Melbourne, Australia. Study findings will be disseminated via peer-reviewed publications and conference presentations.

Early developmental intervention programs post hospital discharge to prevent motor and cognitive impairments in preterm infants.

BACKGROUND: Infants born preterm are at increased risk of developing cognitive and motor impairments compared with infants born at term. Early developmental interventions have been used in the clinical setting with the aim of improving the overall functional outcome for these infants. However, the benefit of these programs remains unclear. OBJECTIVES: To review the effectiveness of early developmental intervention post-discharge from hospital for preterm (< 37 weeks) infants on motor or cognitive development. SEARCH STRATEGY: The Cochrane Neonatal Review group search strategy was used to identify randomised and quasi-randomised controlled trials of early developmental interventions post hospital discharge. Two review authors independently searched the Cochrane Central Register of Controlled Trials (CENTRAL, The Cochrane Library), MEDLINE Advanced, CINAHL, PsychINFO and EMBASE (1966 through February 2006). SELECTION CRITERIA: Studies included had to be randomised or quasi-randomised controlled trials of early developmental intervention programs that commenced within the first 12 months of life for infants born at < 37 weeks with no major congenital abnormalities. Intervention could commence as an inpatient; however, a post discharge component was necessary to be included in this review. The outcome measures were not pre-specified other than that they had to assess cognitive and/or motor ability. The rates of intellectual impairment, cerebral palsy and development co-ordination disorder were also documented. DATA COLLECTION AND ANALYSIS: Data were extracted and entered by two independent review authors. Cognitive and motor outcomes were pooled in three age groups - infant (0 to 2 years), preschool (3 to < 5 years) or school age (5 to 17 years). Meta-analysis was carried out using RevMan 4.2 to determine the effects of early developmental intervention in the short (0 to 2 years), medium (3 to < 5 years) and long term (5 to 17 years). Subgroup analysis was carried out in relation to; gestational age, birthweight, brain injury, commencement of intervention, focus of intervention and study quality. MAIN RESULTS: Sixteen studies met the inclusion criteria (2379 randomised patients). Six of these studies were RCTs and had strong methodological quality. There was variability with regard to the focus and intensity of the intervention, and in length of follow-up. Meta-analysis concluded that intervention improved cognitive outcomes at infant age (developmental quotient [DQ]: standard mean difference [SMD] 0.46 SD; 95% CI 0.36 0.57; P < 0.0001), and at preschool age (intelligence quotient [IQ]; SMD 0.46 SD; 95%CI 0.33, 0.59; P < 0.0001). However, this effect was not sustained at school age (IQ; SMD 0.02 SD; 95% CI -0.10, 0.14; P = 0.71). There was significant heterogeneity between studies for cognitive outcomes at infant and school ages. There was little evidence of an effect of early intervention on motor outcomes in the short, medium or long-term, but there were only two studies reporting outcomes beyond 2 years. AUTHORS' CONCLUSIONS: Early intervention programs for preterm infants have a positive influence on cognitive outcomes in the short to medium term. However, there was significant heterogeneity between the interventions included in this review. Further research is needed to determine which early developmental interventions are the most effective at improving cognitive and motor outcomes, and on the longer-term effects of these programs. Cost-effectiveness and access to services should also be evaluated since they are important factors when considering implementation of an early developmental intervention program for a preterm infant.