Kawasaki Disease (KD) 2020


Kawasaki disease (KD) is relatively uncommon, mostly affecting children under the age of 5 years but can occur in older children. It is not known what causes KD and there is currently no diagnostic test, leaving doctors to diagnose the disease based on clinical criteria (such as presence of fever, rash, swollen lymph nodes and red eyes). The most serious complication of KD is damage to the coronary arteries, potentially requiring long-term management.

A need therefore exists for methods for diagnosis, prognosis, and/or monitoring of Kawasaki disease, and associated outcomes, including permanent coronary artery and heart damage in children.

Seattle Children’s Hospital identified Prevencio as having expertise in developing highly accurate, AI-driven, multiple protein, algorithmically scored blood tests. We developed a partnership and collaborated to develop a highly accurate multiple protein panel for the diagnosis of Kawasaki Disease.

Pediatric Academic Societies Scientific Sessions 2021

An Artificial Intelligence-derived Proteomic Panel to Diagnose Kawasaki Disease (KD)


  • Prospective blood samples were collected from children presenting to the emergency room with symptoms of fever ≥ 38.1 0 C to develop a diagnostic blood test for KD.

  • The final panel identified had three biomarkers: NT-proBNP, C-reactive protein (CRP) and thyroxine binding globulin.

  • The model had an AUC of 0.92 (95% C.I.:0.88, 0.96) for accurate diagnosis of KD.

  • This proteomic panel can provide rapid laboratory confirmation of KD diagnosis, thus decreasing time to diagnose and treat patients positive for KD.

Study Overview

Kawasaki Disease (KD) diagnosis is currently based mainly on American Heart Association (AHA) algorithms. No specific or sensitive blood test or panel exists to confirm the diagnosis, thus remaining challenging for clinicians.

To develop a proteomic panel to diagnose Kawasaki Disease using Artificial Intelligence (AI).

A multiple biomarker panel approach would provide accurate, biologically based diagnostic information to identify Kawasaki Disease.

A machine learning method was used to select protein panels accurate for KD diagnosis. Then a diagnostic model was trained on the 150 patient samples using LASSO with logistic regression. This model was evaluated using in-sample validation.

Key Findings


  • The final panel identified had three biomarkers: NT-proBNP, C-reactive protein (CRP) and thyroxine binding globulin.

  • With the three-level risk score, diagnoses of low-risk patients (0-4) had a NPV of 96%, and high-risk patients (6-10) had a PPV of 83%.

  • Using a protein-based approach and machine learning, we developed and internally validated a

multiple blood protein panel with high accuracy for predicting the presence of KD.



  • The proteomic panel can be performed on existing laboratory platforms for rapid laboratory

confirmation of KD diagnosis.

  • In the physician office, this blood panel can be easily done to rapidly triage the patient to the ED

if the test is positive.


  • A multi-proteomic panel was developed with high accuracy for predicting the presence of KD.

Scroll Down for PAS 2021 Poster