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.

Epidemiological and Clinical Features of Kawasaki Disease During the COVID-19 Pandemic in the United States.

Importance: Public health measures implemented during the COVID-19 pandemic had widespread effects on population behaviors, transmission of infectious diseases, and exposures to environmental pollutants. This provided an opportunity to study how these factors potentially influenced the incidence of Kawasaki disease (KD), a self-limited pediatric vasculitis of unknown etiology. Objectives: To examine the change in KD incidence across the United States and evaluate whether public health measures affected the prevalence of KD. Design, Setting, and Participants: This multicenter cohort study included consecutive, unselected patients with KD who were diagnosed between January 1, 2018, and December 31, 2020 (multicenter cohort with 28 pediatric centers), and a detailed analysis of patients with KD who were diagnosed between January 1, 2002, and November 15, 2021 (Rady Children's Hospital San Diego [RCHSD]). Main Outcomes and Measures: For the multicenter cohort, the date of fever onset for each patient with KD was collected. For RCHSD, detailed demographic and clinical data as well as publicly available, anonymized mobile phone data and median household income by census block group were collected. The study hypothesis was that public health measures undertaken during the pandemic would reduce exposure to the airborne trigger(s) of KD and that communities with high shelter-in-place compliance would experience the greatest decrease in KD incidence. Results: A total of 2461 KD cases were included in the multicenter study (2018: 894; 2019: 905; 2020: 646), and 1461 cases (median [IQR] age, 2.8 years [1.4-4.9 years]; 900 [61.6%] males; 220 [15.1%] Asian, 512 [35.0%] Hispanic, and 338 [23.1%] White children) from RCHSD between 2002 and 2021 were also included. The 28.2% decline in KD cases nationally during 2020 (646 cases) compared with 2018 (894 cases) and 2019 (905 cases) was uneven across the United States. For RCHSD, there was a disproportionate decline in KD cases in 2020 to 2021 compared with the mean (SD) number of cases in earlier years for children aged 1 to 5 years (22 vs 44.9 [9.9]; P = .02), male children (21 vs 47.6 [10.0]; P = .01), and Asian children (4 vs 11.8 [4.4]; P = .046). Mobility data did not suggest that shelter-in-place measures were associated with the number of KD cases. Clinical features including strawberry tongue, enlarged cervical lymph node, and subacute periungual desquamation were decreased during 2020 compared with the baseline period (strawberry tongue: 39% vs 63%; P = .04; enlarged lymph node: 21% vs 32%; P = .09; periungual desquamation: 47% vs 58%; P = .16). School closures, masking mandates, decreased ambient pollution, and decreased circulation of respiratory viruses all overlapped to different extents with the period of decreased KD cases. KD in San Diego rebounded in the spring of 2021, coincident with lifting of mask mandates. Conclusions and Relevance: In this study of epidemiological and clinical features of KD during the COVID-19 pandemic in the United States, KD cases fell and remained low during the period of masking and school closure. Mobility data indicated that differential intensity of sheltering in place was not associated with KD incidence. These findings suggest that social behavior is associated with exposure to the agent(s) that trigger KD and are consistent with a respiratory portal of entry for the agent(s).