How to Tell the Difference between Kawasaki Disease and MIS-C

Newswise – Kawasaki disease (KD) is the leading cause of acquired heart disease in children in developed countries, yet it has long defied easy understanding, with distinct features and multiple triggers and an unknown cause.

During the COVID-19 pandemic, Kawasaki disease case numbers declined, but another disease emerged: childhood multisystem inflammatory syndrome, or MIS-C, which shares many symptoms with KD but with a single pathogen, SARS -CoV-2 virus, which causes COVID-19.

In a new study published September 20, 2022 in Lancet Digital Healtha national team of scientists led by researchers from the University of California San Diego School of Medicine developed a machine learning algorithm to diagnose MIS-C and KD.

“For 40 years, the Kawasaki research community has attempted and failed to develop a diagnostic test for KD,” said study co-senior author Jane C. Burns, MD, a pediatrician at Rady Children’s Hospital in San Diego and director of the Kawasaki -Disease Research Center at the UC San Diego School of Medicine.

“But now, in just 18 months, we have created a tool for physicians that differentiates MIS-C from KD in children using simple test results and five physical exam features that any healthcare provider, clinic or hospital can perform , with an accuracy of over 90 percent.”

MIS-C, KD and COVID-19 share similar underlying molecular patterns and immune responses. A study published earlier this year by scientists at UC San Diego found that all three inflammatory diseases were on the same immune response continuum, with MIS-C being a more severe version of the response than KD.

MIS-C and KD share many symptoms, including fever, rash, and bloodshot eyes, but if left untreated, KD can also lead to coronary artery aneurysms and heart attacks. It remains unclear how MIS-C affects children long-term, but early data suggests a full recovery. The condition only develops in some children infected with SARS-CoV-2. However, in both KD and MIS-C, early diagnosis is crucial, but physicians lacked an accurate way to distinguish MIS-C from KD or other acute febrile childhood illnesses.

Also Read :  Yale Researchers Demonstrate XPB1 Reduces Severity of Polycystic Kidney Disease

The new study used data from 1,517 patients diagnosed with MIS-C, KD or other febrile illnesses at Rady Children’s between January 1, 2009 and June 7, 2021, with additional patient data from Connecticut Children’s Medical Center in Hartford, CT (16 patients) and Los Angeles Children’s Hospital (50 patients).

A novel deep-learning algorithm called KIDMATCH, developed by the study’s first author, Jonathan Y. Lam, a graduate student in the lab of Shamim Nemati, PhD, associate professor of medicine at the UC San Diego School of Medicine, was used for comparison of MIS uses -C and KD based on patient age, the five classic signs of clinical KD, and 17 laboratory measurements.

“Deep learning algorithms have proven their power in industrial applications such as speech recognition or machine translation and are good at identifying multiplicative risk factors. For example: the interaction between immunosuppression and hypothermia in the presence of infection, which may indicate risk,” Nemati said.

Nemati also pointed out the benefit of overcoming the problem of biased data sets when developing machine learning.

“One of the main sources of bias is the lack of diversity in the training data set, causing a model to perform better on some patient populations than others. Building a diverse training population that uses national datasets, as was done for this project, helps mitigate model bias.

Also Read :  Descriptive study of foodborne disease using disease monitoring data in Zhejiang Province, China, 2016–2020 | BMC Public Health

“To further counteract bias, the machine learning experts inserted a bound around the algorithm that allows the model to determine whether it has sufficient prior knowledge of similar cases to reliably determine whether a patient has an MIS-C risk exists. If the algorithm finds that the data is missing, it marks the case as an indeterminate result. These flags reduced false positives by 75 percent for similar machine learning models. This reduction in false alarms can significantly reduce the resource drain or time spent on an incorrect diagnosis.”

The algorithm’s conclusions were validated externally on patient cohorts from Boston Children’s Hospital, Children’s National Hospital in Washington, DC, and the CHARMS Study Group Consortium from 14 hospitals across the United States.

UC San Diego was one of eight institutions in the country funded by the Eunice Kennedy Shriver National Institute for Child Health and Human Development to develop approaches to identify children at high risk of MIS-C. Funded by a commercialization grant from RADxTech, the university is now partnering with a start-up company called Healcisio Inc., founded by Nemati and colleagues, to seek emergency use authorization from the U.S. Food and Drug Administration.

“The hope here, of course, is that KIDMATCH can help frontline clinicians differentiate between MIS-C, Kawasaki disease, and other febrile conditions so they can initiate appropriate treatment sooner and prevent serious complications,” said the co- Senior author of the Nemati study.

KD occurs with varying prevalence in different parts of the world. In the United States, it is estimated that between 4,000 and 5,000 cases are diagnosed each year, with an incidence rate of 15 to 20 cases per 100,000 children under the age of five. Experts generally believe that the disease is caused by an aerosol that could contain parts of a virus, bacteria or fungi, but there is also a hereditary aspect. Younger siblings of a KD patient have a 10-fold increased risk of KD due to a shared genetic predisposition. When children grow up with Kawasaki disease, their children are at greater risk of developing KD. MIS-C is a serious but rare condition that often requires hospitalization. It occurs in one in about 3,000 to 4,000 children and adolescents who have SARS-CoV-2 infection. Most children with MIS-C have no reported underlying medical conditions, although many are obese.

Also Read :  Can you take Paxlovid and heart disease medications at the same time?

Co-authors include: Chisato Shimizu, Adriana H. Tremoulet, Emelia Bainto, Samantha C. Roberts, Nipha Sivilay, Michael A. Gardiner, and John T. Kanegaye, all from UC San Diego and Rady Children’s Hospital-San Diego ; Alexander H. Hogan and Juan C. Salazar, Connecticut Children’s Medical Center and University of Connecticut School of Medicine; Sindhu Mohandas and Jacqueline R. Szmuszkovicz, Los Angeles Children’s Hospital; Simran Mahanta, Audrey Dionne, and Jane W. Newburger, Boston Children’s Hospital; Emily Ansusinha and Roberta L. DeBiasi, Shiying Hao, Xuefeng B. Ling, National Children’s Hospital; Harvey J. Cohen, Stanford University School of Medicine; the Kawasaki Disease Research Group for Pediatric Emergency Medicine; and the CHARMS study group.

Funding for this research came in part from the Eunice Kennedy Shriver National Institute of Child Health and Human Development, the National Heart, Lung and Blood Institute, the US Patient-Centered Outcomes Research Institute, and the US National Library of Medicine.

Full study:


Source link