Artificial intelligence (AI) has been applied to early recognition and management of rapidly progressive, community-acquired pediatric sepsis, a leading cause of childhood mortality. The broad adoption of electronic health records combined with rapid advances in digital technologies have enabled the federated training of both knowledge-driven AI, known as expert systems, trained by teams of collaborating clinicians, and data-driven AI, known as machine learning (ML), to derive predictive, clustering algorithms trained on “big data.” An important subset of ML is “deep learning,” which includes tools that understand, interpret, and manipulate human imagery and language, such as natural language processing and its subset large language models. We are in an era of rapid deployment of AI/ML-powered tools ranging from real-time electronic health records–embedded decision support tools to continuous wearable vital sign monitors and mobile/conversational virtual assistants/triage apps. These applications have the potential of transforming the timeliness of life-saving sepsis care delivery. This review explores the current and potential AI/ML applications in sepsis care, including tools for screening/early detection, risk stratification/outcome prediction, personalized treatment, and continuous patient monitoring. We highlight successful implementations and ongoing clinical trials, emphasizing the impact on patient outcomes. Finally, we address practical considerations for the future, such as bias mitigation and integration into clinical workflows.
Background: Percutaneous ultrasound-guided renal biopsy (PRB) is a key element for diagnosis and management of several renal pathologies. We aimed to lay out the experience of our pediatric nephrology unit performing PRBs. The rationale and findings of these biopsies, safety issues and considerations of the extracted data are going to be analyzed. Methods: A retrospective study was conducted from 2008 to 2023 based on the review of the medical records of pediatric patients who underwent PRBs. In total, 216 kidney biopsies in 206 patients were performed: 115 (53.2%) during the 2008–2015 period and 101 (46.8%) during the 2016–2023 period. Results: The most frequent clinical indication for PRBs was nephritic syndrome followed by nephrotic syndrome, observed in 84 (40.8%) and 72 (34.9%) patients, respectively. The predominant diagnosis was minimal change disease (MCD) (23.3%), followed by focal segmental glomerulosclerosis (FSGS) (15%) equal to lupus nephritis (LN) (15%), and immunoglobulin A nepropathy (10.2%). Minor complications, such as subcapsular hematomas were observed in approximately 15% of patients while no therapeutic intervention was needed. Conclusions: This report is the first review of pathohistological data covering a pediatric population over a 15-year period in Greece and one of the largest in southeastern Europe, especially in the Balkan region. The main indication for a PRB was nephritic syndrome; however, MCD was the main histological diagnosis. This study emphasis the fact that PRBs constitute a safe and reliable method of diagnostic approach to kidney diseases in childhood and offers important information on therapeutic approaches as well as the prognosis of these patients.
Bardet–Biedl syndrome (BBS) is a genetically heterogeneous ciliopathy associated with hyperphagic obesity and kidney disease. Evidence on setmelanotide after pediatric kidney transplantation is limited. We evaluated two children with BBS treated with setmelanotide after kidney transplantation, collecting anthropometric, hunger, metabolic, graft-function, cyclosporine and genetic data. Patient 1, a 17-year-old boy with a homozygous pathogenic SDCCAG8 exon deletion, improved over 12 months: weight 55.6 to 48.0 kg, BMI 26.6 to 23.0 kg/m2, BMI-for-age z-score +1.60 to +0.43, maximal-hunger score 8/10 to 5/10, and HbA1c 6.5% to 5.1%. Patient 2, an 8-year-old girl with a homozygous likely pathogenic BBS5 splice-site variant and a heterozygous PCSK1 N221D variant, showed reduced hunger and an initial z-score fall from +6.10 to +5.69 by month 2.5, meeting the 0.2-point threshold for clinically meaningful change; this was not sustained, and BMI rose from 38.0 to 42.7 kg/m2 by eight months despite a dose of 3 mg/day. Graft function and cyclosporine trough concentrations remained stable, and skin hyperpigmentation was the only treatment-related adverse effect. In these two patients, setmelanotide was not associated with graft deterioration or altered cyclosporine trough concentrations, although two cases cannot establish safety. The divergent trajectories highlight interindividual variability; the role of PCSK1 N221D remains uncertain, and these observations are hypothesis-generating.