Development and Validation of a Model for Endotracheal Intubation and Mechanical Ventilation Prediction in PICU Patients.

OBJECTIVES: To develop and externally validate an intubation prediction model for children admitted to a PICU using objective and routinely available data from the electronic medical records (EMRs). DESIGN: Retrospective observational cohort study. SETTING: Two PICUs within the same healthcare system: an academic, quaternary care center (36 beds) and a community, tertiary care center (56 beds). PATIENTS: Children younger than 18 years old admitted to a PICU between 2010 and 2022. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Clinical data was extracted from the EMR. PICU stays with at least one mechanical ventilation event (≥ 24 hr) occurring within a window of 1-7 days after hospital admission were included in the study. Of 13,208 PICU stays in the derivation PICU cohort, 1,175 (8.90%) had an intubation event. In the validation cohort, there were 1,165 of 17,841 stays (6.53%) with an intubation event. We trained a Categorical Boosting (CatBoost) model using vital signs, laboratory tests, demographic data, medications, organ dysfunction scores, and other patient characteristics to predict the need of intubation and mechanical ventilation using a 24-hour window of data within their hospital stay. We compared the CatBoost model to an extreme gradient boost, random forest, and a logistic regression model. The area under the receiving operating characteristic curve for the derivation cohort and the validation cohort was 0.88 (95% CI, 0.88-0.89) and 0.92 (95% CI, 0.91-0.92), respectively. CONCLUSIONS: We developed and externally validated an interpretable machine learning prediction model that improves on conventional clinical criteria to predict the need for intubation in children hospitalized in a PICU using information readily available in the EMR. Implementation of our model may help clinicians optimize the timing of endotracheal intubation and better allocate respiratory and nursing staff to care for mechanically ventilated children.

Use of plasma exchange in pediatric severe sepsis in children's hospitals.

Pediatric severe sepsis (PSS) is an important cause of death in children. Mortality increases in those with sepsis and multiple organ dysfunction syndrome (MODS). Plasma exchange (PE) has been used as an adjuvant therapy in sepsis, with trials demonstrating variable success. This observational retrospective cohort study aimed to characterize patient demographics, PE use, mortality and resource utilization in septic children from 43 children's hospitals from 2004 to 2012. Of 49,153 PSS cases, 1.8% utilized PE. Utilization increased to 4.8% in those with sepsis and MODS. Comorbidities affected 72-74% of patients. PE patients noted a longer hospitalization than PSS patients (39 vs 17 days). Overall mortality was 14.1% in PSS, increasing to 32.1% in PSS patients receiving PE. Mortality was 22% and 44.4% in PE patients without and with MODS respectively. Mortality decreased over the study period in both PE subgroups. In conclusion, PE utilization in PSS remained stable throughout the study period while PSS mortality decreased over time. Children utilizing PE had a higher associated mortality, but also greater comorbidities and MODS prevalence, likely representing a predilection towards use in more critically ill patients. These data can provide demographic and outcome results to inform future PE trials in sepsis.

Does pretreatment fluorescence in situ hybridization for BCR-ABL predict imatinib-associated hematologic toxicity in chronic myeloid leukemia?

Imatinib (IM)-associated myelosuppression is rare in gastrointestinal stromal cell tumors (<10%) but common in chronic myeloid leukemia (CML). Selective inhibition of predominantly Philadelphia chromosome (Ph+) driven hematopoiesis may explain myelosuppression in CML. In the absence of clinical methods to quantitate the Ph+/Ph- progenitor ratio, we hypothesized that the pre-IM percentage of BCR-ABL+ cells measured by fluorescence in situ hybridization (FISH) predicts for myelosuppression. FISH analyses performed within 30 days pre-IM 400 mg/day were analyzed in 89 patients with chronic phase CML at three institutions. Patients who developed grade ≥3 cytopenias had a higher percentage of positive FISH (90% vs. 83%; p = 0.02). Cytopenias lasted a median of 16 days, and all patients but one continued IM, achieved complete hematologic and cytogenetic remissions, and did not experience progression, with a follow-up of 61 months. In conclusion, IM-associated cytopenias are associated with a high pre-IM FISH, are reversible, and do not adversely affect outcomes.

Efficacy of dasatinib for the treatment of intractable chronic myeloid leukemia.

Dasatinib (DAS) is a well tolerated oral dual SRC inhibitor with remarkable activity against all phases of imatinib-resistant chronic myeloid leukemia (CML). This paper focuses on the activity of DAS in intractable CML, and reviews outcomes of patients enrolled on DAS clinical trials. Safety and tolerability as well as practical tips for management of side-effects, and drug interactions are included.