Prediction of pediatric peanut oral food challenge outcomes using machine learning.

Background: Clinical testing, including food-specific skin and serum IgE level tests, provides limited accuracy to predict food allergy. Confirmatory oral food challenges (OFCs) are often required, but the associated risks, cost, and logistic difficulties comprise a barrier to proper diagnosis. Objective: We sought to utilize advanced machine learning methodologies to integrate clinical variables associated with peanut allergy to create a predictive model for OFCs to improve predictive performance over that of purely statistical methods. Methods: Machine learning was applied to the Learning Early about Peanut Allergy (LEAP) study of 463 peanut OFCs and associated clinical variables. Patient-wise cross-validation was used to create ensemble models that were evaluated on holdout test sets. These models were further evaluated by using 2 additional peanut allergy OFC cohorts: the IMPACT study cohort and a local University of Michigan cohort. Results: In the LEAP data set, the ensemble models achieved a maximum mean area under the curve of 0.997, with a sensitivity and specificity of 0.994 and 1.00, respectively. In the combined validation data sets, the top ensemble model achieved a maximum area under the curve of 0.871, with a sensitivity and specificity of 0.763 and 0.980, respectively. Conclusions: Machine learning models for predicting peanut OFC results have the potential to accurately predict OFC outcomes, potentially minimizing the need for OFCs while increasing confidence in food allergy diagnoses.

A novel 2-step process for the management of inpatient beta-lactam allergy labels.

BACKGROUND: Inpatient beta-lactam allergy labels may increase the unnecessary use of aztreonam and non-beta-lactam antibiotics, which can then lead to more adverse events and increased health care costs, OBJECTIVE: To assess the impact of a novel 2-step process (medication history review followed by risk stratification) on rates of beta-lactam delabeling, aztreonam use, and desensitizations on pediatric, adult, and obstetrics inpatients at a tertiary academic center. METHODS: We prospectively collected data on 700 patients who received inpatient consultation from the Beta-Lactam Allergy Evaluation Service between August 2021 and July 2022. Patients were delabeled either by medication review alone, drug challenge alone if with a low-risk history, or penicillin skin test followed by drug challenge if with a high-risk history. Generalized linear regression modeling was used to compare aztreonam days of therapy in the intervention year with the 2 prior years. Drug desensitizations were assessed by electronic chart review. RESULTS: Most of the patients (n = 656 of 700, 94%) had more than or equal to 1 beta-lactam allergy label removed, clarified, or both; 77.9% of these patients (n = 511 of 656) had 587 beta-lactam allergy labels removed. Nearly one-third (n = 149, 27.6%) had 162 allergy labels removed solely by medication history review. All 114 penicillin skin tests performed had negative results, and 98% (8 of 381) of the patients who underwent any drug challenge passed. Only 5.7% of the delabeled patients were relabeled. There was a 27% reduction in aztreonam use (P = .007). Beta-lactam desensitizations were reduced by 80%. CONCLUSION: A full-time inpatient beta-lactam allergy service using medication history review and risk stratification can safely and effectively remove inpatient beta-lactam allergy labels, reduce aztreonam use, and decrease beta-lactam desensitizations.

Vaccination counseling with and without excipient skin testing in patients with suspected allergic reactions to mRNA COVID-19 vaccines and patients with atopy.

Background: Allergic reactions have been reported with mRNA vaccines for COVID-19 prevention. Patients perceived to be at higher risk for a reaction may be referred to an allergist, although evaluation strategies may differ between allergists. Objective: Our aim was to determine outcomes of COVID-19 vaccinations in patients evaluated by an allergist using different approaches. Methods: We conducted a retrospective case series evaluation of 98 patients seen at the University of Michigan Allergy Clinic for concerns regarding COVID-19 vaccination. Of these 98 patients, 34 underwent skin testing with polyethylene glycol (PEG) 2000 with or without PEG 3350/polysorbate 80 testing. Results: Of the 34 patients on whom skin testing was performed, 16 underwent testing before vaccination and 18 underwent testing after a reported vaccine-related event. One patient had a positive skin testing result in response to PEG 3350 following a vaccination reaction and natural infection and was advised against a second dose. One patient with a significant history concerning of anaphylaxis in response to PEG had positive results of testing to identify allergy to PEG 2000, PEG 3350, and polysorbate 80 and was advised against vaccination. Of the 98 patients, 63 (64%) tolerated COVID-19 vaccination without complication after evaluation by an allergist. Conclusion: No significant differences were found between vaccination counseling with and without skin testing to excipients. Patients who presented before the first dose of vaccination were more likely to proceed with COVID-19 vaccination and tolerate vaccination without complication.

Managing food allergy in children: An evidence-based update.

What are the limits of skin-prick testing? Is prevention possible? And do most children outgrow food allergies? This review provides the evidence to guide your care.

Cutting edge: anti-tumor necrosis factor therapy in rheumatoid arthritis inhibits memory B lymphocytes via effects on lymphoid germinal centers and follicular dendritic cell networks.

Rheumatoid arthritis (RA) is mediated by a proinflammatory cytokine network with TNF at its apex. Accordingly, drugs that block TNF have demonstrated significant efficacy in the treatment of RA. A great deal of experimental evidence also strongly implicates B cells in the pathogenesis of RA. Yet, it remains unclear whether these two important players and the therapies that target them are mechanistically linked. In this study we demonstrate that RA patients on anti-TNF (etanercept) display a paucity of follicular dendritic cell networks and germinal center (GC) structures accompanied by a reduction in CD38+ GC B cells and peripheral blood memory B cell lymphopenia compared with healthy controls and RA patients on methotrexate. This study provides initial evidence in humans to support the notion that anti-TNF treatment disrupts GC reactions at least in part via effects on follicular dendritic cells.

Vaccine responses in patients with rheumatoid arthritis.

Rheumatoid arthritis (RA) is a systemic autoimmune disease that is associated with immunologic alterations in T cells and B cells. Moreover, many of the agents used in RA patients are potentially immunosuppressive. Thus, the underlying disease and treatment may both increase the susceptibility to infections and decrease vaccine responses. With the growing use of aggressive therapies for RA, including anti-tumor necrosis factor agents and newer biologic therapies such as rituximab and abatacept, an increasing concern will be that patients may not respond to conventional vaccination. Further prospective studies on response to vaccination are needed to answer this important public health question. Nevertheless, it is already clear that vaccination does induce response in many patients. Unfortunately, vaccination is underutilized in RA patients and needs to be aggressively promoted.