Necrotising enterocolitis (NEC) is often managed with a temporary enterostomy. Neonates with enterostomy are at risk of growth retardation during critical neurodevelopment. We examined their growth using z-score. We identified all patients with enterostomy from NEC in two neonatal surgical units (NSU) during January 2012–December 2016. Weight-for-age z-score was calculated at birth, stoma formation and closure, noting severely underweight as z < − 3. We compared those kept in NSU until stoma closure with those discharged to local units or home (LU/H) with a stoma. A total of 74 patients were included. By stoma closure, 66 (89%) had deteriorated in z-score with 31 (42%) being severely underweight. There was no difference in z-score at stoma closure between NSU and LU/H despite babies sent to LU/H having a more distal stoma, higher birth weight and gestational age. Babies in LU/H spent a much shorter period on parenteral nutrition while living with their stoma for longer, many needing readmission.Conclusion: Growth failure is a common and severe problem in babies living with enterostomy following NEC. z-score allowed growth trajectory to be accounted for in nutrition prescription and timing of stoma closure. Care during this period should be focused on minimising harm.What is Known:• Necrotising enterocolitis (NEC) is a life-threatening condition affecting predominately premature and very low birth weight neonates. Emergency treatment with temporary enterostomy often leads to growth failure.• There is no consensus on the optimal timing for stoma reversal, hence prolonging impact on growth during crucial developmental periods. Both malnutrition and surgical NEC are independently associated with poor neurodevelopment outcome.What is New:• Our study found growth in 89% of babies deteriorated while living with a stoma, with 42% having a weight-for-age z-score < − 3, meeting the WHO criteria of being severely underweight, despite judicial use of parenteral nutrition. Applying z-score to weight measurements will allow growth trajectory to be accounted for in clinical decisions, including nutrition prescription (both enteral and parenteral), and guide timing of stoma closure.• Surgeons who target stoma closure at a certain weight risk waiting for an indefinite period of time, during which babies’ growth may falter.

Despite decades of exploration into necrotising enterocolitis (NEC), we still lack the capacity to accurately diagnose the disease to improve outcomes in its management. Existing diagnostics struggle to delineate NEC from other neonatal intestinal diseases; it is also unable to highlight those likely to deteriorate to needing emergency life-saving surgery before it is too late. The diagnosis of NEC is heavily dependent on interpretation of radiological findings, especially abdominal radiography (AR) and abdominal ultrasound (AUS). Interexpert variability in interpreting AR imaging, and in the case of AUS, performing and interpreting the test, remains an unresolved challenge. With the compounding impact of the shrinking radiology workforce, a novel approach is imperative. Computer assisted detection (CAD) and classification of abnormal pathology in medical imaging is a rapidly evolving field of clinical and biomedical research. This technology is widely used as a preliminary screening tool. This research paper proposes a deep learning-based model to classify AR images in an automated manner, generating class activation maps (CAM) from various imaging features consistent with NEC pathology, as agreed by expert consensus papers (in neonatology and paediatric radiology). It also compares it with conventional machine learning methods. The suggested model aims to produce heatmaps for various imaging features to highlight NEC pathology in AR (or in future AUS). Once the model is trained, validation is done through quantitative measures and visually by the attending radiologist (clinician) reviewing the validity of the colour maps highlighting the pathology of the AR image (future extension to AUS). As the volume of imaging data is increasing year by year, CAD can be a key strategy to assist radiology departments meet service needs. This technology can greatly assist in screening for NEC, improving the detection of NEC and potentially aid in the earlier identification of disease. Furthermore, it can fast track research cost effectively by creating big data through the automatic labeling of imaging data to create big-data for NEC databases.

No abstract

No abstract