No abstract

Aim The early diagnosis of cerebral palsy (CP) allows children timely access to early intervention. In 2018, Monash Children's Hospital established an Early Neurodevelopment Clinic based upon evidence‐based guidelines for the early diagnosis of CP in high‐risk infants. In this study, we aimed to characterise the infants presenting to the clinic and determine the rate of CP diagnosis. Methods This study analysed data from infants attending the Early Neurodevelopment Clinic between May 2019 and April 2020. Infants at high‐risk for CP attended the clinic at 3 months corrected age. Neuroimaging reports were reviewed, and a Prechtl's General Movement Assessment and Hammersmith Infant Neurological Examination were performed. Infants were diagnosed as having typical development, delayed development, high‐risk of CP or CP at the time of clinic attendance and referred on to the appropriate pathway. Results Ninety‐six high‐risk infants attended the clinic over the 1 year study period. Sixty‐eight (71%) infants were extremely preterm or extremely low birthweight, and 28 (29%) were infants at born at older gestation with evidence of moderate to severe brain injury. Nine (9.6%) infants received a CP diagnosis and 12 (12.5%) were considered high‐risk of CP. All infants with CP or high‐risk of CP were referred to the Victorian Paediatric Rehabilitation Service. Conclusions It is feasible to implement the early CP diagnosis guidelines into a high‐risk infant follow‐up clinic. Implementation of the guidelines allows for early diagnosis of CP and appropriate referral of high‐risk infants.

Aim Respiratory distress syndrome is a common condition among preterm neonates, and assessing lung aeration assists in diagnosing the disease and helping to guide and monitor treatment. We aimed to identify and analyse the tools available to assess lung aeration in neonates with respiratory distress syndrome. Methods A systematic review and narrative synthesis of studies published between January 1, 2004, and August 26, 2019, were performed using the OVID Medline, PubMed, Embase and Scopus databases. Results A total of 53 relevant papers were retrieved for the narrative synthesis. The main tools used to assess lung aeration were respiratory function monitoring, capnography, chest X‐rays, lung ultrasound, electrical impedance tomography and respiratory inductive plethysmography. This paper discusses the evidence to support the use of these tools, including their advantages and disadvantages, and explores the future of lung aeration assessments within neonatal intensive care units. Conclusion There are currently several promising tools available to assess lung aeration in neonates with respiratory distress syndrome, but they all have their limitations. These tools need to be refined to facilitate convenient and accurate assessments of lung aeration in neonates with respiratory distress syndrome.

In this study, a new method is proposed to assess heart and lung signal quality objectively and automatically on a 5-level scale in real-time, and to assess the effect of signal quality on vital sign estimation. A total of 207 10 s long chest sounds were taken from 119 preterm and full-term babies. Thirty of the recordings from ten subjects were obtained with synchronous vital signs from the Neonatal Intensive Care Unit (NICU). As a reference, seven annotators independently assessed the signal quality. For automatic quality classification, 400 features were extracted from the chest sounds. After feature ranking and selection, class balancing, and hyperparameter optimization, a variety of multi-class and ordinal classification and regression algorithms were trained. Then, heart rate and breathing rate were automatically estimated from the chest sounds. For the deep learning model, YAMNet, a deep convolutional neural network pre-trained on the AudioSet-Youtube corpus for sound classification was used. After modification of the final output layers of the neural network and class balancing, transfer learning was applied to YAMNet for heart and lung signal quality classification. The results of subject-wise leave-one-out cross-validation show that the best-performing models had a balanced accuracy of 56.8% and 51.2% for heart and lung qualities, respectively. The best-performing models for real-time analysis (<200 ms) had a balanced accuracy of 56.7% and 46.3%, respectively. Our experimental results underscore that increasing the signal quality leads to a reduction in vital sign error.