Stefano Romano

Background: Macrophage activation syndrome (MAS) is a hyperinflammatory and potentially fatal complication associated with rheumatologic disorders. In Kawasaki disease (KD), MAS is a rare and poorly described condition, making its differentiation from a severe, treatment-resistant presentation of KD particularly challenging. Objective: We aimed to describe MAS in KD by analyzing its epidemiological, clinical, and laboratory characteristics, complications, therapeutic strategies, and outcomes. Methods: A comprehensive literature review of PubMed, Embase, Scopus, and Cochrane Library was conducted to identify English-language studies on KD complicated by MAS, including case reports and case series, until 15 November 2024. Results: A total of 176 pediatric patients (60 females; median age 4 years, range 0.13–17) from 48 articles were included. MAS occurred after or simultaneously with KD diagnosis in 174/176 cases (99%). Common features included fever (100%), splenomegaly (49.4%), and hyperferritinemia (98.2%). Cardiac involvement was reported in 37% of children. The HLH-2004 criteria were met in 63% of cases, while the 2016 Ravelli criteria for MAS complicating systemic juvenile idiopathic arthritis were met in 94%. Treatment included additional doses of IVIG (36.2%), GCs (82.8%), cyclosporine A (28.7%), and biologics (13.8%), with complete MAS resolution in 93% of cases. Conclusions: MAS in KD is a rare but severe complication, with overlapping features that make its differentiation from severe and resistant KD challenging. Persistent fever despite initial IVIG administration, along with splenomegaly and hyperferritinemia, emerge as key warning signs. Ravelli criteria provide stronger diagnostic support compared to the HLH-2004 criteria. Moreover, MAS is associated with increased cardiac involvement.

Autoimmune hemolytic anemia (AIHA) is a rare hematologic disorder in the pediatric population and most cases are associated with microbiological infection. The pathological process is not completely clear, but some evidence suggests immunological dysregulation triggered by bacterial or viral infections. Based on the thermal range of the pathogenic antibody, AIHA can be divided into warm (WAIHA) and cold (CAIHA) groups. Cytomegalovirus (CMV) is one of the most common viruses reported as a trigger of AIHA. We present an unusual case of AIHA in a 2-month-old infant positive for both the direct antiglobulin test (C3 complement fraction) and CMV–Polymerase chain reaction in blood samples. In this case, the dating of the infection was uncertain, making it impossible to discriminate between congenital flare-up or a primary acute episode, emphasizing the importance of CMV prenatal testing as a screening measure. We adopted multiple therapeutic strategies including steroids (methylprednisolone and prednisone), Intravenous Immunoglobulin, antivirals (ganciclovir and valganciclovir), and red blood cell transfusion.

The latest extensive development of machine learning models in healthcare, and in particular their application to data from the intensive care unit (ICU), is directed towards the main objective to help clinicians in making more timely diagnoses and efficient decisions. Many studies have been focused on the identification of Sepsis in a complex environment such as the ICU by using the data collected in electronic health records. However, only a few studies have investigated associations between the patients' continuously monitored vital signs and their Sepsis status. This work aims at demonstrating that machine learning algorithms considering measures extracted from 103 patients from the publicly available MIMIC-III clinical and waveform databases are able to adequately identify Sepsis just within the first hour of stay in the ICU. A bagged tree classifier showed AUC=0.86, Specificity=0.85 and Sensitivity=0.86 on the test set, when trained using only the information extracted from the recorded electrocardiogram and arterial blood pressure waveforms, showing that the information coming from waveform monitoring may help in detecting Sepsis within the first hour of ICU stay.