Aim: General movement assessment requires substantial expertise for accurate visual interpretation. Our aim was to evaluate an automated pose estimation method, using conventional video records, to see if it could capture infant movements using objective biomarkers. Methods: We selected archived videos from 21 infants aged eight to 17 weeks who had taken part in studies at the IRCCS Fondazione Stella Maris (Italy), from 2011 to 2017. Of these, 14 presented with typical low-risk movements, while seven presented with atypical movements and were later diagnosed with cerebral palsy. Skeleton videos were produced using a computational pose estimation model adapted for infants and these were blindly assessed to see whether they contained the information needed for classification by human experts. Movements of skeletal key points were analysed using kinematic metrics to provide a biomarker to distinguish between groups. Results: The visual assessments of the skeleton videos were very accurate, with Cohen's K of 0.90 when compared with the classification of conventional videos. Quantitative analysis showed that arm movements were more variable in infants with typical movements. Conclusion: It was possible to extract automated estimation of movement patterns from conventional video records and convert them to skeleton footage. This could allow quantitative analysis of existing footage.

The risk for a very preterm child to develop cerebral palsy is significantly higher than for child born at term or later than 32 weeks of gestation. Doyle et al. published an updated systematic review of five RCT's in 2009 in which they proved, that antenatal magnesium sulfate administration markedly decreased the risk of cerebral palsy and substantial gross motor dysfunction in preterm infants. In a research of Magee et al. it was noted, that the NNT to prevent 1 CP or death was 43 and NNT to prevent one CP only was 50 at 32 weeks of gestation. The use of antenatal magnesium sulfate for fetal neuroprotection was launched in HUCH on June 7 th, 2012. After the pilot period of approximately two months, the implementation was evaluated and the decision to set-up the upper gestational age of 31+6 weeks for the fetal neuroprotection has been done (August 21st, 2012). Our main objective was to compare the implementation of antenatal magnesium sulfate for fetal neuroprotection, the proximity of the magnesium exposure to delivery and the determination of the delivery-related blood loss in those that received MgSO4 compared to the cohort of the same gestational age that have not received MgSO4. Pregnancy characteristics and fetal neuroprotection data were collected retrospectively and retrieved from the hospital records. The overall implementation rate during both periods was 83,7%. The rate of 86.2% in period 2012-2016 was higher than expected with an increase of 8,56% compared to the period A. To determine the accurate implementation rate (83,0%) we excluded those with elective CS. The implementation rate was found very successful and higher than that in any of the previous published study. Mean duration of magnesium administration was 7,13 hours and mean dose of MgSO4 was 17,61g. There was a decrease of 33% in women who did not receive magnesium sulfate even though indicated from period A to period B. The decrease of 77,9% from period A to period B with those who did not receive magnesium sulfate for an unknown reason is a huge accomplishment. We found the proximity of the magnesium exposure to delivery to be on a very satisfying level. Altogether 68,0% of women gave birth <12 hours after the exposure to MgSO4 had ceased, and as much as 58,4% delivered <6 hours after the exposure to magnesium. With 29,6% of those eligible for magnesium treatment, magnesium administration time was miscalculated (maintenance dose shorter 30 minutes). This non-adherence to the local guidelines has been noted and an auditing with midwives will be made. In conclusion, MgSO4 administration for fetal neuroprotection has been successfully and safely implemented in our institution.

Purpose: To evaluate whether a trial of planned vaginal breech labor affects neurologic development in children. Methods: This is a nationwide, Finnish, population-based record linkage study. An odds ratio with 95% confidence intervals was used to estimate the relative risk that a child delivered by planned vaginal breech labor would be diagnosed with adverse neurodevelopmental outcome (cerebral palsy, epilepsy, intellectual disability, sensor neural developmental outcome, hyperactivity, speech and language problems) at the age of 4 years. The reference group were children born by planned cesarean section. Results: During a study period of 7 years, 8374 infants were delivered in breech position. Among them, 3907 (46.7%) had an attempted labor and 4467 (53.3%) infants were delivered by planned cesarean section. There were no differences in the neurodevelopmental outcome. In the planned vaginal labor group, 133 (3.4%) children had an abnormal neurodevelopmental outcome at the age of 4 years compared to 142 (3.2%) in the planned cesarean section group. Conclusion: The absolute risk of abnormal neurological outcome in breech deliveries at term was low, regardless of planned mode of birth. Planned vaginal breech labor did not increase the risk for abnormal neurological outcome compared to planned cesarean section.