Background: Acute kidney injury (AKI) is among the most common complications following cardiac surgery in adult and pediatric patients, significantly affecting morbidity and mortality. Artificial Intelligence (AI) with Machine Learning (ML) can be used to predict outcomes. AKI diagnosis anticipation may be an ideal target of these methods. The scope of the study is building a Machine Learning (ML) train model with Random Forest (RF) algorithm, based on electronic health record (EHR) data, able to forecast AKI continuously after 48 h in post-cardiac surgery children, and to test its performance. Four hundred nineteen consecutive patients out of 1115 hospital admissions were enrolled in a single-center retrospective study. Patients were younger than 18 years and admitted from August 2018 to February 2020 in a pediatric cardiac intensive care unit (PCICU) undergoing cardiac surgery, invasive procedure (hemodynamic studies), and medical conditions with complete EHR records and discharged after 48 h or more. Results: Thirty-six variables were selected to build the algorithm according to commonly described cardiac surgery-associated AKI clinical predictors. We evaluated different models for different outcomes: binary AKI (no AKI vs. AKI), severe AKI (no-mild vs severe AKI), and multiclass classification (maximum AKI and the most frequent level of AKI, mode AKI). The algorithm performance was assessed with the area under the curve receiver operating characteristics (AUC ROC) for binary classification, with accuracy and K for multiclass classification. AUC ROC for binary AKI was 0.93 (95% CI 0.92–0.94), and for severe AKI was 0.99 (95% CI 0.98–1). Mode AKI accuracy was 0.95, and K was 0.80 (95% CI 0.94–0.96); maximum AKI accuracy was 0.92, and K was 0.71 (95% CI 0.91–0.93). The importance matrix plot demonstrated creatinine, basal creatinine, platelets count, adrenaline support, and lactate dehydrogenase for binary AKI with the addition of cardiopulmonary bypass duration for severe AKI as the most relevant variables of the model. Conclusions: We validated a ML model to detect AKI occurring after 48 h in a retrospective observational study that could help clinicians in individuating patients at risk of AKI, in which a preventive strategy can be determinant to improve the occurrence of renal dysfunction.

Background: The spread of carbapenem-resistant organisms (CROs) is an increasingly serious threat globally, especially in vulnerable populations, such as intensive care unit (ICU) patients. Currently, the antibiotic options for CROs are very limited, particularly in pediatric settings. We describe a cohort of pediatric patients affected by CRO infections, highlighting the important changes in carbapenemase production in recent years and comparing the treatment with novel cephalosporins (N-CEFs) to Colistin-based regimens (COLI). Methods: All patients admitted to the cardiac ICU of the Bambino Gesù Children’s Hospital in Rome during the 2016–2022 period with an invasive infection caused by a CRO were enrolled. Results: The data were collected from 42 patients. The most frequently detected pathogens were Pseudomonas aeruginosa (64%), Klebsiella pneumoniae (14%) and Enterobacter spp. (14%). Thirty-three percent of the isolated microorganisms were carbapenemase producers, with a majority of VIM (71%), followed by KPC (22%) and OXA-48 (7%). A total of 67% of patients in the N-CEF group and 29% of patients in the comparative group achieved clinical remission (p = 0.04). Conclusion: The increase over the years of MBL-producing pathogens in our hospital is challenging in terms of therapeutic options. According to the present study, N-CEFs are a safe and effective option in pediatric patients affected by CRO infections.

Artificial intelligence (AI) is rapidly transforming cardiovascular medicine, with profound implications for congenital heart disease (CHD). Tetralogy of Fallot (ToF), the most common cyanotic disease, requires lifelong surveillance and complex management because of late complications such as pulmonary regurgitation, arrhythmias, and right ventricular dysfunction. This review synthesizes current evidence on AI applications across the continuum of ToF care—from prenatal diagnosis to adulthood follow-up. We examine advances in imaging, perioperative planning, intraoperative monitoring, intensive care, and long-term surveillance, including wearable and implantable technologies. Machine learning (ML), deep learning (DL), and natural language processing (NLP) are revolutionizing diagnostic accuracy, risk stratification, surgical decision-making, and personalized long-term care. The future lies in the integration of multimodal data, including imaging, electronic health records (EHRs), genomic information, and continuous monitoring, to support precision medicine. Challenges remain regarding dataset limitations, interpretability, regulatory standards, and ethical concerns. Nevertheless, ongoing innovation and collaboration between clinicians, engineers, and regulators promise a new era in congenital cardiology. By embedding AI throughout the patient journey, healthcare systems may improve outcomes and quality of life for individuals with ToF.

OBJECTIVES: Therapeutic drug monitoring during vancomycin administration is recommended. However, little information is available in case of paediatric vancomycin prophylaxis. The aim of this study was to analyse vancomycin trough levels on postoperative day (POD) 2 and 3 after paediatric cardio-surgery to assess the clinical predictors and outcomes associated with vancomycin concentrations and to evaluate whether adjustments are effective to target optimal levels. METHODS: A retrospective study was conducted in paediatric patients receiving vancomycin prophylaxis after elective cardio-surgery. Adjustments were made if levels between 20 and 30 (halving subsequent dose) or ˃30 mg/l (dose withheld) were found. RESULTS: Vancomycin doses of the 100 examined children (3.7–6.4 years) were 12.8 (2.5), 9.4 (5.4) and 9.7 (4.5) mg/kg, on POD1, 2 and 3, respectively (P = 0.0001). The 200 vancomycin trough levels decreased from 16.9 (11.4) on POD2 to 14.6 (8.5) on POD3 (P = 0.003). Overall, 66 troughs were sub-target, 68 reached the optimal target and 66 were supra-target. On POD2 and 3, 32 and 27 dose adjustments were required, leading to a reduced number of patients with supra-target troughs. Neonates showed a higher number of supra-target levels with respect to non-neonatal patients on both POD2 (P = 0.003) and 3 (P = 0.0001). At multivariable regression analysis, vancomycin levels showed independent association with weight and creatinine levels on both POD2 and 3. Vancomycin levels correlated with ventilation days (P = 0.31, P = 0.039), but not with methicillin-resistant Staphylococcus aureus positivity (P = 0.69). CONCLUSIONS: Vancomycin prophylaxis in paediatric cardio-surgery requires strict therapeutic drug monitoring and several dosage adjustments. Supra-target troughs are frequent and neonatal age, weight and creatinine levels significantly affect vancomycin concentrations.