Artificial Intelligence and Machine Learning for Inborn Errors of Immunity: Current State & Future Promise.

Artificial intelligence (AI) and machine learning (ML) research within medicine has been exponentially increasing over the last decade, with studies showcasing the potential of AI/ML algorithms to improve clinical practice and outcomes. Ongoing research and efforts to develop AI-based models have expanded to aid in the identification of inborn errors of immunity (IEI). The utilization of larger electronic health record (EHR) datasets, coupled with advances in phenotyping precision and enhancements in ML techniques, has the potential to significantly improve the early recognition of IEI, thereby increasing access to equitable care. In this review, we provide a comprehensive examination of AI/ML for IEI, covering the spectrum from data preprocessing for AI/ML analysis to current applications within immunology, and address the challenges associated with implementing clinical decision support systems (CDSS) to refine the diagnosis and management of IEI.

Applying Market Basket Analysis to Determine Complex Coassociations Among Food Allergens in Children With Food Protein-Induced Enterocolitis Syndrome (FPIES).

Background: Food protein-induced enterocolitis syndrome (FPIES) is a non-IgE-mediated food allergy, characterized by delayed onset of repetitive vomiting occurring 1 to 4 h following ingestion of a food allergen. Managing FPIES requires strict avoidance of the food trigger. The concern with FPIES is determining the risk of another FPIES food trigger reaction due to potential coassociations with other foods or food groups. An effective statistical approach for analyzing FPIES-related data is essential to identify common coallergens and their associations. Methods: This study employed Market Basket Analysis, a data-mining technique, to examine correlations and patterns among allergens in FPIES patients at a Houston, Texas, pediatric tertiary center. A retrospective analysis of electronic medical records from January 2018 to March 2022 for allergist diagnosed FPIES patients was conducted. The analysis utilized R software, specifically the "arules" and "arulesViz" packages, implementing the Apriori algorithm with set minimum support and confidence thresholds. Results: The study included 210 FPIES cases over 4 years, with 112 patients reacting to one food trigger and 98 to more than one trigger. In the latter group, the 5 predominant triggers were cow's milk (45.9%), rice (31.6%), oats (30.6%), soy (22.4%), and avocado (19.4%). Market Basket Analysis identified significant associations between food categories, particularly between soy and dairy, egg and dairy, oat and dairy, rice and dairy, and avocado and dairy. Conclusion: Market Basket Analysis proved effective in identifying patterns and associations in FPIES data. These insights are crucial for healthcare providers in formulating dietary recommendations for FPIES patients. This approach potentially enhances guidance on food introductions and avoidances, thereby improving management and the quality of life for those affected by FPIES.

A systematic review and expert Delphi Consensus recommendation on the use of vaccines in patients receiving dupilumab: A position paper of the American College of Allergy, Asthma and Immunology.

BACKGROUND: Dupilumab is a monoclonal antibody that targets the interleukin (IL)-4 receptor alpha subunit, thus blocking the effects of IL-4 and IL-13, and has shown efficacy in treating various conditions including asthma, atopic dermatitis, eosinophilic esophagitis, and others. Because of its immune modulatory effects, clinical trials that studied dupilumab did not allow patients to receive live vaccines during the clinical trials because of an abundance of caution, and thus package inserts recommend that patients who are being treated with dupilumab should avoid live vaccines. Because dupilumab is now approved for use in patients from 6 months of age for the treatment of atopic dermatitis, this reported contraindication is now posing a clinical dilemma for patients and clinicians. OBJECTIVE: To perform a systematic review of literature on the safety and efficacy of vaccinations in patients who are receiving dupilumab and to provide expert guidance on the use of vaccines in patients who are receiving dupilumab. METHODS: A systematic review of the literature was performed, and an expert Delphi Panel was assembled. RESULTS: The available literature on patients who received vaccinations while using dupilumab overall suggests that live vaccines are safe and that the vaccine efficacy, in general, is not affected by dupilumab. The expert Delphi panel agreed that the use of vaccines in patients receiving dupilumab was likely safe and effective. CONCLUSION: Vaccines (including live vaccines) can be administered to patients receiving dupilumab in a shared decision-making capacity.

Improving Clinical Practice Through Patient Registries in Allergy and Immunology.

Patient registries are a mechanism for collecting data on allergic and immunologic diseases that provide important information on epidemiology and outcomes that can ultimately improve patient care. Key criteria for establishing effective registries include the use of a clearly defined purpose, identifying the target population and ensuring consistent data collection. Registries in allergic diseases include those for diseases such as inborn errors of immunity (IEI), food allergy, asthma and anaphylaxis, pharmacological interventions in vulnerable populations, and adverse effects of pharmacologic interventions including hypersensitivity reactions to drugs and vaccines. Important insights gained from patient registries in our field include contributions in phenotype and outcomes in IEI, the risk for adverse reactions in food-allergic patients in multiple settings, the benefits and risk of biologic medications for asthma during pregnancy, vaccine safety, and the categorization and genetic determination of risk for severe cutaneous adverse reactions to medications. Impediments to the development of clinically meaningful patient registries include the lack of funding resources for registry establishment and the quality, quantity, and consistency of available data. Despite these drawbacks, high-quality and successful registries are invaluable in informing clinical practice and improving outcomes in patients with allergic and immunological diseases.

A Second Slice of FPIES: A Single-Center Reappraisal of Pediatric FPIES.

BACKGROUND: Food protein-induced enterocolitis syndrome (FPIES) is being increasingly recognized as a non-IgE-mediated food allergy; however, it remains unclear if and how the presentation, diagnosis, and management of this disease has changed in recent years. OBJECTIVE: To reappraise the FPIES cohort at a large US pediatric tertiary referral center. METHODS: We performed a retrospective chart review of pediatric patients with FPIES (International Classification of Diseases, Tenth Revision code K52.21) diagnosed in our allergy/immunology clinics between 2018 and 2022. RESULTS: There were 210 children diagnosed with FPIES. Most were White (73.8%), non-Hispanic (71.4%), and male (54.3%) with private insurance (77.6%). Cow's milk was the most common food trigger (35.2%), with the earliest median age of onset of 5 months. The atypical FPIES rate was 13.8%. FPIES was accurately diagnosed in 54.3% at the first medical contact. The oral food challenge pass rate was 73.5%. The rate of trigger resolution at 36 months was 77%. CONCLUSIONS: By comparing trends from a previous and current FPIES cohort, we were able to assess the potential impact of various guidelines and practice changes on the diagnosis and management of FPIES at our center. Milk and oat surpassed rice as the most common FPIES triggers; peanut and egg emerged as new FPIES triggers; there was a shorter time to diagnosis and an increased rate of atypical FPIES. Our findings reflect earlier recognition of FPIES and prompt allergy/immunology referral from community physicians, implementation of recent medical society guidelines for infant feeding practices, and growing clinical expertise of allergists at our center.

Identifying Region-Specific Allergy Sensitization Clusters to Optimize Diagnosis and Reduce Costs.

OBJECTIVE: To delineate quantitatively the allergen sensitization patterns in a large pediatric cohort and inform the selection of a region-specific panel of allergen tests for timely and cost-effective in vitro atopy screening. STUDY DESIGN: IgE levels for specific allergens from patients in the Texas Children's Health System were analyzed retrospectively. Statistical and network analyses were conducted to reveal sensitization patterns. RESULTS: Network analysis of 114 distinct allergens among 12 065 patients identified 2 main groups of allergens: environmental and food. Approximately 67.5% of patients were sensitized to environmental allergens, 47.2% to food allergens, and 7.3% to at least 1 allergen from both groups. We identified a novel panel of 13 allergens that could detect sensitization in 95% of patients, whereas panels of 7 allergens within each category effectively identified sensitization in 95% of patients with specific sensitivities. This data-driven approach is estimated to reduce overall testing costs by 52%. In agreement with literature, we observed correlations among allergens within specific categories, such as pollen, shellfish, nuts, and dairy allergens. CONCLUSIONS: This study provides insights into allergen sensitization patterns informing an algorithmic testing approach tailored for primary care settings. The use of a region and population-specific test panel can efficiently identify atopy, leading to more targeted testing. This strategy has the potential to refine laboratory testing, reduce costs, and improve the appropriateness of referrals to allergy specialists, ultimately enhancing diagnostic accuracy and resource allocation.

Natural language processing of clinical notes enables early inborn error of immunity risk ascertainment.

Background: There are now approximately 450 discrete inborn errors of immunity (IEI) described; however, diagnostic rates remain suboptimal. Use of structured health record data has proven useful for patient detection but may be augmented by natural language processing (NLP). Here we present a machine learning model that can distinguish patients from controls significantly in advance of ultimate diagnosis date. Objective: We sought to create an NLP machine learning algorithm that could identify IEI patients early during the disease course and shorten the diagnostic odyssey. Methods: Our approach involved extracting a large corpus of IEI patient clinical-note text from a major referral center's electronic health record (EHR) system and a matched control corpus for comparison. We built text classifiers with simple machine learning methods and trained them on progressively longer time epochs before date of diagnosis. Results: The top performing NLP algorithm effectively distinguished cases from controls robustly 36 months before ultimate clinical diagnosis (area under precision recall curve > 0.95). Corpus analysis demonstrated that statistically enriched, IEI-relevant terms were evident 24+ months before diagnosis, validating that clinical notes can provide a signal for early prediction of IEI. Conclusion: Mining EHR notes with NLP holds promise for improving early IEI patient detection.

Delayed presentation of food protein-induced enterocolitis syndrome (FPIES) to okra in a toddler.

BACKGROUND: Food protein-induced enterocolitis syndrome (FPIES) is a non-immunoglobulin E (IgE) -mediated food allergy predominantly observed in infants and characterized by the delayed onset of vomiting following ingestion of a trigger food. An increase in research and clinical consideration of FPIES has led to the discovery of unique deviations from the standard FPIES triggers and presentations. CASE PRESENTATION: A 34-month-old female patient with a history of consuming okra daily presented to medical attention after developing classic FPIES symptoms to okra beginning at 14-months of age. CONCLUSIONS: Recently, awareness about the varied nature of FPIES clinical presentation has come to light. This case is the first to describe FPIES to the fruit okra that developed over a 12-month time span after previously tolerating the food. This case serves to emphasize the importance of understanding the range of FPIES symptoms to improve recognition and expedite best practice recommendations.

Validating inborn error of immunity prevalence and risk with nationally representative electronic health record data.

BACKGROUND: The 10 Warning Signs of Primary Immunodeficiency were created 30 years ago to advance recognition of inborn errors of immunity (IEI). However, no population-level assessment of their utility applied to electronic health record (EHR) data has been conducted. OBJECTIVE: We sought to quantify the value of having ≥2 warning signs (WS) toward diagnosing IEI using a highly representative real-world US cohort. A secondary goal was estimating the US prevalence of IEI. METHODS: In this cohort study, we accessed normalized and de-identified EHR data on 152 million US patients. An IEI cohort (n = 41,080), in which patients were defined by having at least 1 verifiable IEI diagnosis placed ≥2 times in their record, was compared with a matched set of controls (n = 250,262). WS were encoded along with relevant diagnoses, relative weights were calculated, and the proportion of IEI cases versus controls with ≥2 WS was compared. RESULTS: The proportion of IEI cases with ≥2 WS significantly differed from controls (0.33 vs 0.031; P < .0005, χ2 test). We also estimated a US IEI prevalence of 6 per 10,000 individuals (41,080/73,165,655; 0.056%). WS 9 (≥2 deep-seated infections), 7 (fungal infections), 5 (failure to thrive) and 4 (≥2 pneumonias in 1 year) were the most heavily weighted among the IEI cohort. CONCLUSIONS: This nationally representative US-based cohort study demonstrates that presence of WS and associated clinical diagnoses can facilitate identification of patients with IEI from EHR data. In addition, we estimate that 6 in 10,000, or approximately 150,000 to 200,000 individuals are affected by IEI across the United States.

Exploring gastric cancer genetics: A turning point in common variable immunodeficiency.

Background: Gastric cancer (GC) stands as a prominent cause of cancer-related mortality and ranks second among the most frequently diagnosed malignancies in individuals with common variable immunodeficiency (CVID). Objective: We sought to conduct a comprehensive, large-scale genetic analysis to explore the CVID-associated germline variant landscape within gastric adenocarcinoma samples and to seek to delineate the transcriptomic similarities between GC and CVID. Methods: We investigated the presence of CVID-associated germline variants in 1591 GC samples and assessed their impact on tumor mutational load. The progression of GC was evaluated in patients with and without these variants. Transcriptomic similarities were explored by matching differentially expressed genes in GC to healthy gastric tissue with a CVID transcriptomic signature. Results: CVID-associated germline variants were found in 60% of GC samples. Our analysis revealed a significant association between the presence of CVID-related genetic variants and higher tumor mutational load in GC (P < .0001); high GC mutational load seems to be linked to immunotherapy response and worse prognosis. Transcriptomic similarities unveiled key genes and pathways implicated in innate immune responses and tumorigenesis. We identified upregulated genes related to oncogene drivers, inflammation, tumor suppression, DNA repair, and downregulated immunomodulatory genes shared between GC and CVID. Conclusions: Our findings contribute to a deeper understanding of potential molecular modulators of GC and shed light on the intricate interplay between immunodeficiency and cancer. This study underscores the clinical relevance of CVID-related variants in influencing GC progression and opens avenues for further exploration into novel therapeutic approaches.

Racial and ethnic disparities in early mortality among patients with inborn errors of immunity.

BACKGROUND: Racial and ethnic disparities in life expectancy in the United States have been widely documented. To date, there remains a paucity of similar data in patients with inborn errors of immunity (IEIs). OBJECTIVE: Our aim was to examine racial and ethnic differences in mortality due to an IEI in the United States. METHODS: We analyzed National Center for Health Statistics national mortality data from 2003 to 2018. We quantified age-adjusted death rate and age-specific death rate as a result of an IEI for each major racial and ethnic group in the United States and examined the association of race and ethnicity with death at a younger age. RESULTS: From 2003 to 2018, IEIs were reported as the underlying or contributing cause of death in 14,970 individuals nationwide. The age-adjusted death rate was highest among Black patients (4.25 per 1,000,000 person years), compared with 2.01, 1.71, 1.50, and 0.92 per 1,000,000 person years for White, American Indian/Alaska Native, Hispanic, and Asian/Pacific Islander patients, respectively. The odds of death before age 65 years were greatest among Black patients (odds ratio [OR] = 5.15 [95% CI = 4.61-5.76]), followed by American Indian/Alaska Native patients (OR = 3.58 [95% CI = 2.30-5.82]), compared with White patients. The odds of death before age 24 years were greater among Hispanic patients than among non-Hispanic patients (OR = 3.60 [95% CI = 3.08-4.18]). CONCLUSION: Our study highlights racial and ethnic disparities in mortality due to an IEI and the urgent need to further identify and systematically remove barriers in care for historically marginalized patients with IEIs.

Utilizing Reduced Labeled Proton Clearance to Identify Preclinical Alzheimer Disease with 3D ASL MRI.

Addressing the seminal pathophysiology in Alzheimer disease (AD) is the next logical focus for effective intervention, given the initial disappointing and more recent possibly encouraging results of monoclonal antibody trials. Endothelial cell dysfunction-induced blood-brain barrier leak with associated prolonged capillary mean transit time (cMTT) and glymphatic outflow dysfunction is the most proximal events in the degeneration cascade. Sensitive and reproducible markers are required to both identify early disease and assess future treatment trial outcomes. Two participants, with mild cognitive impairment (MCI) and one with AD, were evaluated clinically prior to MRI in this small case series report. From seven 3D turbo gradient and spin echo (TGSE) pulsed arterial spin echo (PASL) MRI sequences six homologous region of interest in bitemporal, bifrontal, and biparietal lobes for each sequence were examined and plotted against time. By choosing late perfusion times during cMTT phase of perfusion linear analysis of signal decay could be utilized. A reference axial FLAIR sequence was also obtained. Slope of the linear analysis correlated to the rate of labeled proton clearance with reduced clearance occurring in AD participants compared to normal participants in our previous study. Whether similar differences in clearance rate extend to either MCI or early AD was investigated. Participants were categorized by clinical phenotype before MRI and compared to previously published phenotype cohorts: n = 18 normal/healthy, n = 6 AD, n = 3 MCI. Significant differences in labeled proton clearance rates between AD and MCI/control phenotypes within bilateral temporal lobes (left p = 0.004, right p = 0.002) and within bilateral frontal lobes AD versus controls (left p = 0.001, right p = 0.008) and AD versus MCI (left p = 0.001, right p = 0.001) were found. This noninvasive MRI technique has potential for identifying MCI transition to AD.

Stratification of Pediatric COVID-19 Cases Using Inflammatory Biomarker Profiling and Machine Learning.

While pediatric COVID-19 is rarely severe, a small fraction of children infected with SARS-CoV-2 go on to develop multisystem inflammatory syndrome (MIS-C), with substantial morbidity. An objective method with high specificity and high sensitivity to identify current or imminent MIS-C in children infected with SARS-CoV-2 is highly desirable. The aim was to learn about an interpretable novel cytokine/chemokine assay panel providing such an objective classification. This retrospective study was conducted on four groups of pediatric patients seen at multiple sites of Texas Children's Hospital, Houston, TX who consented to provide blood samples to our COVID-19 Biorepository. Standard laboratory markers of inflammation and a novel cytokine/chemokine array were measured in blood samples of all patients. Group 1 consisted of 72 COVID-19, 70 MIS-C and 63 uninfected control patients seen between May 2020 and January 2021 and predominantly infected with pre-alpha variants. Group 2 consisted of 29 COVID-19 and 43 MIS-C patients seen between January and May 2021 infected predominantly with the alpha variant. Group 3 consisted of 30 COVID-19 and 32 MIS-C patients seen between August and October 2021 infected with alpha and/or delta variants. Group 4 consisted of 20 COVID-19 and 46 MIS-C patients seen between October 2021 andJanuary 2022 infected with delta and/or omicron variants. Group 1 was used to train an L1-regularized logistic regression model which was tested using five-fold cross validation, and then separately validated against the remaining naïve groups. The area under receiver operating curve (AUROC) and F1-score were used to quantify the performance of the cytokine/chemokine assay-based classifier. Standard laboratory markers predict MIS-C with a five-fold cross-validated AUROC of 0.86 ± 0.05 and an F1 score of 0.78 ± 0.07, while the cytokine/chemokine panel predicted MIS-C with a five-fold cross-validated AUROC of 0.95 ± 0.02 and an F1 score of 0.91 ± 0.04, with only sixteen of the forty-five cytokines/chemokines sufficient to achieve this performance. Tested on Group 2 the cytokine/chemokine panel yielded AUROC = 0.98 and F1 = 0.93, on Group 3 it yielded AUROC = 0.89 and F1 = 0.89, and on Group 4 AUROC = 0.99 and F1 = 0.97. Adding standard laboratory markers to the cytokine/chemokine panel did not improve performance. A top-10 subset of these 16 cytokines achieves equivalent performance on the validation data sets. Our findings demonstrate that a sixteen-cytokine/chemokine panel as well as the top ten subset provides a highly sensitive, and specific method to identify MIS-C in patients infected with SARS-CoV-2 of all the major variants identified to date.

What Came First: Malnutrition or Severe Disease?

A 20-year-old female with depression presented to the emergency department with chronic weight loss, weakness, fatigue, hair loss, rash, palpitations, and 2 weeks of cough. Initial history revealed that she had disordered eating habits with dietary restriction, experienced a 50-pound unintentional weight loss over 2 years despite reported adherence to nutritional supplementation, and had a normal gastrointestinal workup. On examination, she was markedly cachectic with a BMI of 10.3kg/m2 and hypotensive (84/69 mmHg). Her cardiovascular examination revealed a regular rate and rhythm without a murmur. Her breath sounds were diminished in the upper lobes bilaterally. A skin examination showed diffuse hair loss, skin breakdown, and peeling with a tender, erythematous, papular rash over the bilateral ankles, and nonpitting edema. A chest radiograph showed a right upper lobe opacity and lucent lesions in the left proximal humerus. A focused assessment with sonography for trauma examination showed a large pericardial effusion. Chest computed tomography revealed a right upper lobe opacity with an associated cavitation. Though she began improving with rifampin, isoniazid, pyrazinamide, ethambutol, levofloxacin, azithromycin, and nutritional rehabilitation, her clinical course was complicated by an acute worsening nearly 1 month into her hospitalization with persistent high fevers, worsening cough, development of a murmur, and worsening consolidation on chest computed tomography. Adolescent Medicine, Infectious Diseases, Gastroenterology, and Allergy and Immunology were consulted to guide the diagnostic evaluation and management of this patient's complex clinical course.

A Nasal Inflammatory Cytokine Signature Is Associated with Early Graft-versus-Host Disease of the Lung after Allogeneic Hematopoietic Cell Transplantation: Proof of Concept.

Respiratory inflammation in bronchiolitis obliterans syndrome (BOS) after hematopoietic cell transplantation (HCT) is poorly understood. Clinical criteria for early-stage BOS (stage 0p) often capture HCT recipients without BOS. Measuring respiratory tract inflammation may help identify BOS, particularly early BOS. We conducted a prospective observational study in HCT recipients with new-onset BOS (n = 14), BOS stage 0p (n = 10), and recipients without lung impairment with (n = 3) or without (n = 8) chronic graft-versus-host disease and measured nasal inflammation using nasosorption at enrollment and then every 3 mo for 1 y. We divided BOS stage 0p into impairment that did not return to baseline values (preBOS, n = 6), or transient impairment (n = 4). We tested eluted nasal mucosal lining fluid from nasosorption matrices for inflammatory chemokines and cytokines using multiplex magnetic bead immunoassays. We analyzed between-group differences using the Kruskal-Wallis method, adjusting for multiple comparisons. We found increased nasal inflammation in preBOS and therefore directly compared patients with preBOS to those with transient impairment, as this would be of greatest diagnostic relevance. After adjusting for multiple corrections, we found significant increases in growth factors (FGF2, TGF-α, GM-CSF, VEGF), macrophage activation (CCL4, TNF-α, IL-6), neutrophil activation (CXCL2, IL-8), T cell activation (CD40 ligand, IL-2, IL-12p70, IL-15), type 2 inflammation (eotaxin, IL-4, IL-13), type 17 inflammation (IL-17A), dendritic maturation (FLT3 ligand, IL-7), and counterregulatory molecules (PD-L1, IL-1 receptor antagonist, IL-10) in preBOS patients compared to transient impairment. These differences waned over time. In conclusion, a transient multifaceted nasal inflammatory response is associated with preBOS. Our findings require validation in larger longitudinal cohorts.

Stratification of Pediatric COVID-19 cases by inflammatory biomarker profiling and machine learning.

An objective method to identify imminent or current Multi-Inflammatory Syndrome in Children (MIS-C) infected with SARS-CoV-2 is highly desirable. The aims was to define an algorithmically interpreted novel cytokine/chemokine assay panel providing such an objective classification. This study was conducted on 4 groups of patients seen at multiple sites of Texas Children's Hospital, Houston, TX who consented to provide blood samples to our COVID-19 Biorepository. Standard laboratory markers of inflammation and a novel cytokine/chemokine array were measured in blood samples of all patients. Group 1 consisted of 72 COVID-19, 66 MIS-C and 63 uninfected control patients seen between May 2020 and January 2021 and predominantly infected with pre-alpha variants. Group 2 consisted of 29 COVID-19 and 43 MIS-C patients seen between January-May 2021 infected predominantly with the alpha variant. Group 3 consisted of 30 COVID-19 and 32 MIS-C patients seen between August-October 2021 infected with alpha and/or delta variants. Group 4 consisted of 20 COVID-19 and 46 MIS-C patients seen between October 2021-January 2022 infected with delta and/or omicron variants. Group 1 was used to train a L1-regularized logistic regression model which was validated using 5-fold cross validation, and then separately validated against the remaining naïve groups. The area under receiver operating curve (AUROC) and F1-score were used to quantify the performance of the algorithmically interpreted cytokine/chemokine assay panel. Standard laboratory markers predict MIS-C with a 5-fold cross-validated AUROC of 0.86 ± 0.05 and an F1 score of 0.78 ± 0.07, while the cytokine/chemokine panel predicted MIS-C with a 5-fold cross-validated AUROC of 0.95 ± 0.02 and an F1 score of 0.91 ± 0.04, with only sixteen of the forty-five cytokines/chemokines sufficient to achieve this performance. Tested on Group 2 the cytokine/chemokine panel yielded AUROC =0.98, F1=0.93, on Group 3 it yielded AUROC=0.89, F1 = 0.89, and on Group 4 AUROC= 0.99, F1= 0.97). Adding standard laboratory markers to the cytokine/chemokine panel did not improve performance. A top-10 subset of these 16 cytokines achieves equivalent performance on the validation data sets. Our findings demonstrate that a sixteen-cytokine/chemokine panel as well as the top ten subset provides a sensitive, specific method to identify MIS-C in patients infected with SARS-CoV-2 of all the major variants identified to date.

Cord blood transplantation for nonmalignant disorders: early functional immunity and high survival.

There is no consensus on the best donor for children with nonmalignant disorders and immune deficiencies in the absence of a matched related donor (MRD). We evaluated the 2-year overall survival (OS) after umbilical cord blood transplantation (UCBT) in patients with nonmalignant disorders from 2009 to 2020 enrolled in a prospective clinical trial using either 5/6 or 6/6 UCB as the cell source. Patients receive a fully ablative busulfan, cyclophosphamide, and fludarabine without serotherapy. Fifty-five children were enrolled, median age 5 months (range, 1-111 months); primary immune deficiency (45), metabolic (5), hemophagocytic lymphohistiocytosis (1), and hematologic disorders (4). Twenty-six patients had persistent infections before transplant. Nineteen of them (34%) were 6/6 matched, and 36 (66%) were 5/6 human leukocyte antigen-matched. The OS at 2 years was 91% (95% cumulative incidence, 79-96), with a median follow-up of 4.3 years. The median time to neutrophil and platelet recovery were 17 days (range, 5-39 days) and 37 days (range, 20-92 days), respectively. All but one evaluable patient achieved full donor chimerism. The cumulative incidence of acute GVHD grades 2-4 on day 100 was 16% (n = 9). All patients with viral infections at the time of transplant cleared the infection at a median time of 54 days (range, 44-91 days). All evaluable patients underwent correction of their immune or metabolic defects. We conclude that in the absence of MRD, UCBT following myeloablative conditioning without serotherapy is an excellent curative option in young children with nonmalignant disorders. This trial has been registered at www.clinicaltrials.gov as NCT00950846.

A validated artificial intelligence-based pipeline for population-wide primary immunodeficiency screening.

BACKGROUND: Identification of patients with underlying inborn errors of immunity and inherent susceptibility to infection remains challenging. The ensuing protracted diagnostic odyssey for such patients often results in greater morbidity and suboptimal outcomes, underscoring a need to develop systematic methods for improving diagnostic rates. OBJECTIVE: The principal aim of this study is to build and validate a generalizable analytical pipeline for population-wide detection of infection susceptibility and risk of primary immunodeficiency. METHODS: This prospective, longitudinal cohort study coupled weighted rules with a machine learning classifier for risk stratification. Claims data were analyzed from a diverse population (n = 427,110) iteratively over 30 months. Cohort outcomes were enumerated for new diagnoses, hospitalizations, and acute care visits. This study followed TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) standards. RESULTS: Cohort members initially identified as high risk were proportionally more likely to receive a diagnosis of primary immunodeficiency compared to those at low-medium risk or those without claims of interest respectively (9% vs 1.5% vs 0.2%; P < .001, chi-square test). Subsequent machine learning stratification enabled an annualized individual snapshot of complexity for triaging referrals. This study's top-performing machine learning model for visit-level prediction used a single dense layer neural network architecture (area under the receiver-operator characteristic curve = 0.98; F1 score = 0.98). CONCLUSIONS: A 2-step analytical pipeline can facilitate identification of individuals with primary immunodeficiency and accurately quantify clinical risk.

Immunosuppression in Patients With Primary Immunodeficiency-Walking the Line.

Individuals with primary immunodeficiency (PIDD) experience not only infectious complications but also immune dysregulation leading to autoimmunity, inflammation, and lymphoproliferative manifestations. Management of these complications often requires treatment with additional immunosuppressive medications, which pose an additional risk of infectious complications. Immunosuppression in individuals with PIDD therefore requires careful assessment and consideration of risks and benefits. Medications should be closely monitored, and strategies for risk mitigation of adverse events considered, such as exposure reduction, appropriate vaccination, use of antibiotics/antivirals, and optimization of immunoglobulin replacement therapy. In a subset of individuals who are not tolerating immune modulation or experiencing disease progression despite appropriate interventions, hematopoietic stem-cell transplantation is a management option.