Plasma Cell-free RNA Signatures of Inflammatory Syndromes in Children.

Inflammatory syndromes, including those caused by infection, are a major cause of hospital admissions among children and are often misdiagnosed because of a lack of advanced molecular diagnostic tools. In this study, we explored the utility of circulating cell-free RNA (cfRNA) in plasma as an analyte for the differential diagnosis and characterization of pediatric inflammatory syndromes. We profiled cfRNA in 370 plasma samples from pediatric patients with a range of inflammatory conditions, including Kawasaki disease (KD), Multisystem Inflammatory Syndrome in Children (MIS-C), viral infections and bacterial infections. We developed machine learning models based on these cfRNA profiles, which effectively differentiated KD from MIS-C - two conditions presenting with overlapping symptoms - with high performance (Test Area Under the Curve (AUC) = 0.97). We further extended this methodology into a multiclass machine learning framework that achieved 81% accuracy in distinguishing among KD, MIS-C, viral, and bacterial infections. We further demonstrated that cfRNA profiles can be used to quantify injury to specific tissues and organs, including the liver, heart, endothelium, nervous system, and the upper respiratory tract. Overall, this study identified cfRNA as a versatile analyte for the differential diagnosis and characterization of a wide range of pediatric inflammatory syndromes.

A Deep Learning Framework for Image-Based Screening of Kawasaki Disease.

Kawasaki disease (KD) is a leading cause of acquired heart disease in children and is characterized by the presence of a combination of five clinical signs assessed during the physical examination. Timely treatment of intravenous immunoglobin is needed to prevent coronary artery aneurysm formation, but KD is usually diagnosed when pediatric patients are evaluated by a clinician in the emergency department days after onset. One or more of the five clinical signs usually manifests in pediatric patients prior to ED admission, presenting an opportunity for earlier intervention if families receive guidance to seek medical care as soon as clinical signs are observed along with a fever for at least five days. We present a deep learning framework for a novel screening tool to calculate the relative risk of KD by analyzing images of the five clinical signs. The framework consists of convolutional neural networks to separately calculate the risk for each clinical sign, and a new algorithm to determine what clinical sign is in an image. We achieved a mean accuracy of 90% during 10-fold cross-validation and 88% during external validation for the new algorithm. These results demonstrate the algorithms in the proposed screening tool can be utilized by families to determine if their child should be evaluated by a clinician based on the number of clinical signs consistent with KD.Clinical Relevance- This screening framework has the potential for earlier clinical evaluation and detection of KD to reduce the risk of coronary artery complications.

Impact of SARS-CoV-2 Infection on the Association Between Laboratory Tests and Severe Outcomes Among Hospitalized Children.

Background: To assist clinicians with identifying children at risk of severe outcomes, we assessed the association between laboratory findings and severe outcomes among severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-infected children and determined if SARS-CoV-2 test result status modified the associations. Methods: We conducted a cross-sectional analysis of participants tested for SARS-CoV-2 infection in 41 pediatric emergency departments in 10 countries. Participants were hospitalized, had laboratory testing performed, and completed 14-day follow-up. The primary objective was to assess the associations between laboratory findings and severe outcomes. The secondary objective was to determine if the SARS-CoV-2 test result modified the associations. Results: We included 1817 participants; 522 (28.7%) SARS-CoV-2 test-positive and 1295 (71.3%) test-negative. Seventy-five (14.4%) test-positive and 174 (13.4%) test-negative children experienced severe outcomes. In regression analysis, we found that among SARS-CoV-2-positive children, procalcitonin ≥0.5 ng/mL (adjusted odds ratio [aOR], 9.14; 95% CI, 2.90-28.80), ferritin >500 ng/mL (aOR, 7.95; 95% CI, 1.89-33.44), D-dimer ≥1500 ng/mL (aOR, 4.57; 95% CI, 1.12-18.68), serum glucose ≥120 mg/dL (aOR, 2.01; 95% CI, 1.06-3.81), lymphocyte count <1.0 × 109/L (aOR, 3.21; 95% CI, 1.34-7.69), and platelet count <150 × 109/L (aOR, 2.82; 95% CI, 1.31-6.07) were associated with severe outcomes. Evaluation of the interaction term revealed that a positive SARS-CoV-2 result increased the associations with severe outcomes for elevated procalcitonin, C-reactive protein (CRP), D-dimer, and for reduced lymphocyte and platelet counts. Conclusions: Specific laboratory parameters are associated with severe outcomes in SARS-CoV-2-infected children, and elevated serum procalcitonin, CRP, and D-dimer and low absolute lymphocyte and platelet counts were more strongly associated with severe outcomes in children testing positive compared with those testing negative.

A machine-learning algorithm for diagnosis of multisystem inflammatory syndrome in children and Kawasaki disease in the USA: a retrospective model development and validation study.

BACKGROUND: Multisystem inflammatory syndrome in children (MIS-C) is a novel disease that was identified during the COVID-19 pandemic and is characterised by systemic inflammation following SARS-CoV-2 infection. Early detection of MIS-C is a challenge given its clinical similarities to Kawasaki disease and other acute febrile childhood illnesses. We aimed to develop and validate an artificial intelligence algorithm that can distinguish among MIS-C, Kawasaki disease, and other similar febrile illnesses and aid in the diagnosis of patients in the emergency department and acute care setting. METHODS: In this retrospective model development and validation study, we developed a deep-learning algorithm called KIDMATCH (Kawasaki Disease vs Multisystem Inflammatory Syndrome in Children) using patient age, the five classic clinical Kawasaki disease signs, and 17 laboratory measurements. All features were prospectively collected at the time of initial evaluation from patients diagnosed with Kawasaki disease or other febrile illness between Jan 1, 2009, and Dec 31, 2019, at Rady Children's Hospital in San Diego (CA, USA). For patients with MIS-C, the same data were collected from patients between May 7, 2020, and July 20, 2021, at Rady Children's Hospital, Connecticut Children's Medical Center in Hartford (CT, USA), and Children's Hospital Los Angeles (CA, USA). We trained a two-stage model consisting of feedforward neural networks to distinguish between patients with MIS-C and those without and then those with Kawasaki disease and other febrile illnesses. After internally validating the algorithm using stratified tenfold cross-validation, we incorporated a conformal prediction framework to tag patients with erroneous data or distribution shifts. We finally externally validated KIDMATCH on patients with MIS-C enrolled between April 22, 2020, and July 21, 2021, from Boston Children's Hospital (MA, USA), Children's National Hospital (Washington, DC, USA), and the CHARMS Study Group consortium of 14 US hospitals. FINDINGS: 1517 patients diagnosed at Rady Children's Hospital between Jan 1, 2009, and June 7, 2021, with MIS-C (n=69), Kawasaki disease (n=775), or other febrile illnesses (n=673) were identified for internal validation, with an additional 16 patients with MIS-C included from Connecticut Children's Medical Center and 50 from Children's Hospital Los Angeles between May 7, 2020, and July 20, 2021. KIDMATCH achieved a median area under the receiver operating characteristic curve during internal validation of 98·8% (IQR 98·0-99·3) in the first stage and 96·0% (95·6-97·2) in the second stage. We externally validated KIDMATCH on 175 patients with MIS-C from Boston Children's Hospital (n=50), Children's National Hospital (n=42), and the CHARMS Study Group consortium of 14 US hospitals (n=83). External validation of KIDMATCH on patients with MIS-C correctly classified 76 of 81 patients (94% accuracy, two rejected by conformal prediction) from 14 hospitals in the CHARMS Study Group consortium, 47 of 49 patients (96% accuracy, one rejected by conformal prediction) from Boston Children's Hospital, and 36 of 40 patients (90% accuracy, two rejected by conformal prediction) from Children's National Hospital. INTERPRETATION: KIDMATCH has the potential to aid front-line clinicians to distinguish between MIS-C, Kawasaki disease, and other similar febrile illnesses to allow prompt treatment and prevent severe complications. FUNDING: US Eunice Kennedy Shriver National Institute of Child Health and Human Development, US National Heart, Lung, and Blood Institute, US Patient-Centered Outcomes Research Institute, US National Library of Medicine, the McCance Foundation, and the Gordon and Marilyn Macklin Foundation.

Post-COVID-19 Conditions Among Children 90 Days After SARS-CoV-2 Infection.

Importance: Little is known about the risk factors for, and the risk of, developing post-COVID-19 conditions (PCCs) among children. Objectives: To estimate the proportion of SARS-CoV-2-positive children with PCCs 90 days after a positive test result, to compare this proportion with SARS-CoV-2-negative children, and to assess factors associated with PCCs. Design, Setting, and Participants: This prospective cohort study, conducted in 36 emergency departments (EDs) in 8 countries between March 7, 2020, and January 20, 2021, included 1884 SARS-CoV-2-positive children who completed 90-day follow-up; 1686 of these children were frequency matched by hospitalization status, country, and recruitment date with 1701 SARS-CoV-2-negative controls. Exposure: SARS-CoV-2 detected via nucleic acid testing. Main Outcomes and Measures: Post-COVID-19 conditions, defined as any persistent, new, or recurrent health problems reported in the 90-day follow-up survey. Results: Of 8642 enrolled children, 2368 (27.4%) were SARS-CoV-2 positive, among whom 2365 (99.9%) had index ED visit disposition data available; among the 1884 children (79.7%) who completed follow-up, the median age was 3 years (IQR, 0-10 years) and 994 (52.8%) were boys. A total of 110 SARS-CoV-2-positive children (5.8%; 95% CI, 4.8%-7.0%) reported PCCs, including 44 of 447 children (9.8%; 95% CI, 7.4%-13.0%) hospitalized during the acute illness and 66 of 1437 children (4.6%; 95% CI, 3.6%-5.8%) not hospitalized during the acute illness (difference, 5.3%; 95% CI, 2.5%-8.5%). Among SARS-CoV-2-positive children, the most common symptom was fatigue or weakness (21 [1.1%]). Characteristics associated with reporting at least 1 PCC at 90 days included being hospitalized 48 hours or more compared with no hospitalization (adjusted odds ratio [aOR], 2.67 [95% CI, 1.63-4.38]); having 4 or more symptoms reported at the index ED visit compared with 1 to 3 symptoms (4-6 symptoms: aOR, 2.35 [95% CI, 1.28-4.31]; ≥7 symptoms: aOR, 4.59 [95% CI, 2.50-8.44]); and being 14 years of age or older compared with younger than 1 year (aOR, 2.67 [95% CI, 1.43-4.99]). SARS-CoV-2-positive children were more likely to report PCCs at 90 days compared with those who tested negative, both among those who were not hospitalized (55 of 1295 [4.2%; 95% CI, 3.2%-5.5%] vs 35 of 1321 [2.7%; 95% CI, 1.9%-3.7%]; difference, 1.6% [95% CI, 0.2%-3.0%]) and those who were hospitalized (40 of 391 [10.2%; 95% CI, 7.4%-13.7%] vs 19 of 380 [5.0%; 95% CI, 3.0%-7.7%]; difference, 5.2% [95% CI, 1.5%-9.1%]). In addition, SARS-CoV-2 positivity was associated with reporting PCCs 90 days after the index ED visit (aOR, 1.63 [95% CI, 1.14-2.35]), specifically systemic health problems (eg, fatigue, weakness, fever; aOR, 2.44 [95% CI, 1.19-5.00]). Conclusions and Relevance: In this cohort study, SARS-CoV-2 infection was associated with reporting PCCs at 90 days in children. Guidance and follow-up are particularly necessary for hospitalized children who have numerous acute symptoms and are older.

Multicenter Validation of a Machine Learning Algorithm for Diagnosing Pediatric Patients with Multisystem Inflammatory Syndrome and Kawasaki Disease.

BACKGROUND: Multisystem inflammatory syndrome in children (MIS-C) is a novel disease identified during the COVID-19 pandemic characterized by systemic inflammation following SARS-CoV-2 infection. Delays in diagnosing MIS-C may lead to more severe disease with cardiac dysfunction or death. Most pediatric patients recover fully with anti-inflammatory treatments, but early detection of MIS-C remains a challenge given its clinical similarities to Kawasaki disease (KD) and other acute childhood illnesses. METHODS: We developed KIDMATCH ( K awasak I D isease vs M ultisystem Infl A mma T ory syndrome in CH ildren), a deep learning algorithm for screening patients for MIS-C, KD, or other febrile illness, using age, the five classical clinical KD signs, and 17 laboratory measurements prospectively collected within 24 hours of admission to the emergency department from 1448 patients diagnosed with KD or other febrile illness between January 1, 2009 and December 31, 2019 at Rady Children's Hospital. For MIS-C patients, the same data was collected from 131 patients between May 14, 2020 to June 18, 2021 at Rady Children's Hospital, Connecticut Children's Hospital, and Children's Hospital Los Angeles. We trained a two-stage model consisting of feedforward neural networks to distinguish between MIS-C and non MIS-C patients and then KD and other febrile illness. After internally validating the algorithm using 10-fold cross validation, we incorporated a conformal prediction framework to tag patients with erroneous data or distribution shifts, enhancing the model generalizability and confidence by flagging unfamiliar cases as indeterminate instead of making spurious predictions. We externally validated KIDMATCH on 175 MIS-C patients from 16 hospitals across the United States. FINDINGS: KIDMATCH achieved a high median area under the curve in the 10-fold cross validation of 0.988 [IQR: 0.98-0.993] in the first stage and 0.96 [IQR: 0.956-0.972] in the second stage using thresholds set at 95% sensitivity to detect positive MIS-C and KD cases respectively during training. External validation of KIDMATCH on MIS-C patients correctly classified 76/83 (2 rejected) patients from the CHARMS consortium, 47/50 (1 rejected) patients from Boston Children's Hospital, and 36/42 (2 rejected) patients from Children's National Hospital. INTERPRETATION: KIDMATCH has the potential to aid frontline clinicians with distinguishing between MIS-C, KD, and similar febrile illnesses in a timely manner to allow prompt treatment and prevent severe complications. FUNDING: Eunice Kennedy Shriver National Institute of Child Health and Human Development, National Heart, Lung, and Blood Institute, Patient-Centered Outcomes Research Institute, National Library of Medicine.

Outcomes of SARS-CoV-2-Positive Youths Tested in Emergency Departments: The Global PERN-COVID-19 Study.

Importance: Severe outcomes among youths with SARS-CoV-2 infections are poorly characterized. Objective: To estimate the proportion of children with severe outcomes within 14 days of testing positive for SARS-CoV-2 in an emergency department (ED). Design, Setting, and Participants: This prospective cohort study with 14-day follow-up enrolled participants between March 2020 and June 2021. Participants were youths aged younger than 18 years who were tested for SARS-CoV-2 infection at one of 41 EDs across 10 countries including Argentina, Australia, Canada, Costa Rica, Italy, New Zealand, Paraguay, Singapore, Spain, and the United States. Statistical analysis was performed from September to October 2021. Exposures: Acute SARS-CoV-2 infection was determined by nucleic acid (eg, polymerase chain reaction) testing. Main Outcomes and Measures: Severe outcomes, a composite measure defined as intensive interventions during hospitalization (eg, inotropic support, positive pressure ventilation), diagnoses indicating severe organ impairment, or death. Results: Among 3222 enrolled youths who tested positive for SARS-CoV-2 infection, 3221 (>99.9%) had index visit outcome data available, 2007 (62.3%) were from the United States, 1694 (52.6%) were male, and 484 (15.0%) had a self-reported chronic illness; the median (IQR) age was 3 (0-10) years. After 14 days of follow-up, 735 children (22.8% [95% CI, 21.4%-24.3%]) were hospitalized, 107 (3.3% [95% CI, 2.7%-4.0%]) had severe outcomes, and 4 children (0.12% [95% CI, 0.03%-0.32%]) died. Characteristics associated with severe outcomes included being aged 5 to 18 years (age 5 to <10 years vs <1 year: odds ratio [OR], 1.60 [95% CI, 1.09-2.34]; age 10 to <18 years vs <1 year: OR, 2.39 [95% CI 1.38-4.14]), having a self-reported chronic illness (OR, 2.34 [95% CI, 1.59-3.44]), prior episode of pneumonia (OR, 3.15 [95% CI, 1.83-5.42]), symptoms starting 4 to 7 days prior to seeking ED care (vs starting 0-3 days before seeking care: OR, 2.22 [95% CI, 1.29-3.82]), and country (eg, Canada vs US: OR, 0.11 [95% CI, 0.05-0.23]; Costa Rica vs US: OR, 1.76 [95% CI, 1.05-2.96]; Spain vs US: OR, 0.51 [95% CI, 0.27-0.98]). Among a subgroup of 2510 participants discharged home from the ED after initial testing and who had complete follow-up, 50 (2.0%; 95% CI, 1.5%-2.6%) were eventually hospitalized and 12 (0.5%; 95% CI, 0.3%-0.8%) had severe outcomes. Compared with hospitalized SARS-CoV-2-negative youths, the risk of severe outcomes was higher among hospitalized SARS-CoV-2-positive youths (risk difference, 3.9%; 95% CI, 1.1%-6.9%). Conclusions and Relevance: In this study, approximately 3% of SARS-CoV-2-positive youths tested in EDs experienced severe outcomes within 2 weeks of their ED visit. Among children discharged home from the ED, the risk was much lower. Risk factors such as age, underlying chronic illness, and symptom duration may be useful to consider when making clinical care decisions.

Evaluation of a Pediatric Early Warning Score as a Predictor of Occult Invasive Bacterial Infection in the Pediatric Emergency Department.

OBJECTIVES: The aims of the study were to evaluate the diagnostic performance of Pediatric Early Warning Score (PEWS) to predict occult invasive bacterial infection (IBI) in well-appearing pediatric emergency department (PED) patients without known risk factors for bacterial infection and to compare PEWS to heart rate (HR) and Emergency Severity Index (ESI). METHODS: We performed a retrospective case-control analysis of febrile PED patients aged 60 days to 18 years over a 2-year period. Subjects were excluded if they were ill appearing, admitted to an intensive care unit, or had a known high-risk condition. Cases of occult IBI were included if they had a noncontaminant positive culture other than an isolated positive urine culture. Two febrile control subjects were identified for each case. Odds ratios and receiver operating characteristic curves were evaluated to determine performance characteristics of PEWS at triage and disposition, age-adjusted HR at triage and disposition, and ESI at triage. RESULTS: Compared with 178 controls, 89 cases had higher disposition PEWS, higher disposition HR, lower ESI, and higher rate of hospital admission. Disposition PEWS ≥3 (odds ratio, 2.57; 95% confidence interval, 1.08-6.18), disposition HR > 99th percentile, and ESI demonstrated increased odds of occult IBI. Area under the receiver operating characteristic curve for disposition PEWS (0.56) was similar to triage PEWS (0.54), triage HR (0.54), disposition HR (0.58), and ESI (0.65). CONCLUSIONS: Subjects with PEWS ≥3 at PED disposition have increased odds of occult IBI; however, PEWS has poor discriminative ability at all cutoffs. We cannot recommend PEWS used in isolation to predict occult IBI.

Interrater Reliability of the Pediatric Asthma Score.

OBJECTIVES: The aim of this study was to determine the interrater reliability (IRR) of the Pediatric Asthma Score (PAS) and to evaluate the discriminative performance of this score to predict the need for hospital admission among children with acute asthma. METHODS: A secondary analysis of prospective data was performed to compare triage nurse and study personnel PAS scores among children aged 6 to 18 years presenting to the emergency department with acute asthma. The IRR was determined by calculation of weighted Cohen κ with differences evaluated by Wilcoxon ranked pairs. Receiver operating characteristic curves were created to evaluate the predictive ability of PAS to determine the need for hospital admission. RESULTS: One hundred one subjects were evaluated by both study personnel and a triage nurse with PAS score recorded. The IRR of the total PAS score was determined to be moderate (κ = 0.57) and acceptable, although lower than previously reported. Individual components of the PAS score demonstrated fair to substantial agreement. Receiver operating characteristic analysis demonstrated total PAS at emergency department triage to have poor test characteristics in predicting the need for hospital admission, whether PAS was determined by study personnel, triage nurse, or an average score (area under the curve, 0.62-0.65). CONCLUSIONS: In this study, total PAS score demonstrated a moderate and acceptable level of IRR with a poor discriminative ability to determine the need for hospital admission at the time of ED triage.

Implementation of KIDMATCH: A Clinical Decision Support Tool for Diagnosing Pediatric Patients with Multisystem Inflammatory Syndrome and Kawasaki Disease.

Multisystem inflammatory syndrome in children (MIS-C) is a novel disease identified during the COVID-19 pandemic that may lead to cardiac dysfunction or death in pediatric patients. Early detection of MIS-C remains a challenge given the lack of a diagnostic test and its clinical similarities to Kawasaki disease (KD) and other acute childhood illnesses. We developed and validated the KawasakI Disease vs Multisystem InflAmmaTory syndrome in CHildren (KIDMATCH) clinical decision support tool for screening patients for MIS-C, KD, or other febrile illnesses. Here we describe the implementation and iterative refinement of KIDMATCH with provider feedback as a web calculator in the clinical workflow within Rady Children's Hospital. Our findings demonstrate KIDMATCH and its underlying artificial intelligence model have clinical utility in aiding clinicians at the time of initial evaluation within the hospital setting to distinguish patients who have MIS-C, KD, or other febrile illnesses.

Factors Motivating Traditional Healer versus Biomedical Facility Use for Treatment of Pediatric Febrile Illness: Results from a Qualitative Study in Southwestern Uganda.

Febrile illnesses, such as malaria and pneumonia, are among the most common causes of mortality in children younger than 5 years in Uganda outside of the neonatal period. Their impact could be mitigated through earlier diagnosis and treatment at biomedical facilities; however, it is estimated that a large percentage of Ugandans (70-80%) seek traditional healers for their first line of medical care. This study sought to characterize individual and structural influences on health care-seeking behaviors for febrile children. Minimally structured, qualitative interviews were conducted for 34 caregivers of children presenting to biomedical and traditional healer sites, respectively. We identified six themes that shape the pathway of care for febrile children: 1) peer recommendations, 2) trust in biomedicine, 3) trust in traditional medicine, 4) mistrust in providers and therapies, 5) economic resources and access to health care, and 6) perceptions of child health. Biomedical providers are preferred by those who value laboratory testing and formal medical training, whereas traditional healer preference is heavily influenced by convenience, peer recommendations, and firm beliefs in traditional causes of illness. However, most caregivers concurrently use both biomedical and traditional therapies for their child during the same illness cycle. The biomedical system is often considered as a backup when traditional healing "fails." Initiatives seeking to encourage earlier presentation to biomedical facilities must consider the individual and structural forces that motivate seeking traditional healers. Educational programs and cooperation with traditional healers may increase biomedical referrals and decrease time to appropriate care and treatment for vulnerable/susceptible children.