Association between the development of bronchopulmonary dysplasia and platelet transfusion: a protocol for a systematic review and meta-analysis.

Background: There is a lack of consensus on the management of thrombocytopenia in preterm infants, and the threshold for prophylactic platelet transfusion varies widely among clinicians and institutions. Reports in animal models suggested that platelets may play a relevant role in lung alveolarization and regeneration. Bronchopulmonary dysplasia (BPD) is a severe respiratory condition with a multifactorial origin that affects infants born at the early stages of lung development. Recent randomized controlled trials on the platelets count threshold for prophylactic transfusions in preterm infants with thrombocytopenia suggest that a higher exposition to platelet transfusion may increase the risk of BPD. Here, we report a protocol for a systematic review, which aims to assist evidence-based clinical practice and clarify if the administration of platelet products may be associated with the incidence of BPD and/or death in preterm infants. Methods: MEDLINE, Embase, Cochrane databases, and sources of gray literature for conference abstracts and trial registrations will be searched with no time or language restrictions. Case-control studies, cohort studies, and nonrandomized or randomized trials that evaluated the risk for BPD and/or death in preterm infants exposed to platelet transfusion will be included. Data from studies that are sufficiently similar will be pooled as appropriate. Data extraction forms will be developed a priori. Observational studies and nonrandomized and randomized clinical trials will be analyzed separately. Odds ratio with 95% confidence interval (CI) for dichotomous outcomes and the mean difference (95% CI) for continuous outcomes will be combined. The expected heterogeneity will be accounted for using a random-effects model. Subgroup analysis will be performed based on a priori-determined covariate of interest. In case of sufficient homogeneity of interventions and outcomes evaluated, results from subgroups of studies will be pooled together in a meta-analysis. Discussion: This systematic review will investigate the association of BPD/death with platelet components administration in preterm infants, and, consequently, it will provide reliable indications for the evidence-based management of premature patients with thrombocytopenia.

Artificial intelligence in the diagnosis of necrotising enterocolitis in newborns.

Necrotising enterocolitis (NEC) is one of the most common diseases in neonates and predominantly affects premature or very-low-birth-weight infants. Diagnosis is difficult and needed in hours since the first symptom onset for the best therapeutic effects. Artificial intelligence (AI) may play a significant role in NEC diagnosis. A literature search on the use of AI in the diagnosis of NEC was performed. Four databases (PubMed, Embase, arXiv, and IEEE Xplore) were searched with the appropriate MeSH terms. The search yielded 118 publications that were reduced to 8 after screening and checking for eligibility. Of the eight, five used classic machine learning (ML), and three were on the topic of deep ML. Most publications showed promising results. However, no publications with evident clinical benefits were found. Datasets used for training and testing AI systems were small and typically came from a single institution. The potential of AI to improve the diagnosis of NEC is evident. The body of literature on this topic is scarce, and more research in this area is needed, especially with a focus on clinical utility. Cross-institutional data for the training and testing of AI algorithms are required to make progress in this area. IMPACT: Only a few publications on the use of AI in NEC diagnosis are available although they offer some evidence that AI may be helpful in NEC diagnosis. AI requires large, multicentre, and multimodal datasets of high quality for model training and testing. Published results in the literature are based on data from single institutions and, as such, have limited generalisability. Large multicentre studies evaluating broad datasets are needed to evaluate the true potential of AI in diagnosing NEC in a clinical setting.

Steroid use for established bronchopulmonary dysplasia: study protocol for a systematic review and meta-analysis.

INTRODUCTION: Postnatal steroids during the first few weeks of life have been demonstrated to be effective in decreasing the incidence of bronchopulmonary dysplasia (BPD), a serious chronic respiratory condition affecting preterm infants. However, this preventive option is limited by the concern of neurological side effects. Steroids are used to treat established BPD in an attempt to reduce mortality, and length of stay and home oxygen therapy, both of which associated with high levels of parental stress and healthcare costs. Moreover, a late timing for steroid treatment may show a more favourable safety profile in terms of neurodevelopment outcomes, considering the added postnatal brain maturation of these infants. Here, we report a protocol for a systematic review, which aims to determine the efficacy and long-term safety of postnatal steroids for the treatment of established BPD in preterm infants. METHODS AND ANALYSIS: MEDLINE, Embase, Cochrane databases and sources of grey literature for conference abstracts and trial registrations will be searched with no time or language restriction. We will include case-control studies, cohort studies and non-randomised or randomised trials that evaluate postnatal steroids for infants diagnosed with moderate or severe established BPD at 36 weeks' postmenstrual age. We will pool data from studies that are sufficiently similar to make this appropriate. Data extraction forms will be developed a priori. Observational studies and non-randomised and randomised clinical trials will be analysed separately. We will combine OR with 95% CI for dichotomous outcomes and the mean difference (95% CI) for continuous outcomes. We will account for the expected heterogeneity by using a random-effects model. We will perform subgroup analysis based on the a priori determined covariate of interest. ETHICS AND DISSEMINATION: Systematic reviews are exempted from approval by an ethics committee. Attempts will be sought to publish all results. PROSPERO REGISTRATION NUMBER: CRD42021218881.