Related Experiment Video
Updated: Oct 16, 2025
A Novel Method: Super-selective Adrenal Venous Sampling
Published on: September 15, 2017
Can AI Help Pediatricians? Diagnosing Kawasaki Disease Using DRSA
Bartosz Siewert1,2, Jerzy Błaszczyński3, Ewelina Gowin1,2
1Department of Preventive Health, Poznan University of Medical Science, 60-781 Poznan, Poland.
Insights
The dominance-based rough set approach (DRSA) aids in diagnosing Kawasaki disease (KD) in children. High-sensitivity rules involve symptoms like fever, rash, conjunctivitis, and lab values such as CRP and ESR.
Area of Science:
- Pediatric Infectious Diseases
- Medical Informatics
- Computational Medicine
Background:
- Kawasaki disease (KD) diagnosis can be challenging, requiring differentiation from other febrile illnesses in children.
- Accurate early diagnosis of KD is crucial to prevent cardiac complications.
Purpose of the Study:
- To develop decision-making rules for the differential diagnosis of KD, infectious mononucleosis, and S. pyogenes pharyngitis in children.
- To evaluate the utility of the dominance-based rough set approach (DRSA) in identifying KD.
Main Methods:
- Retrospective analysis of demographic and laboratory data from pediatric patients.
- Application of traditional statistical methods and the DRSA method for rule generation.
- Data sourced from a Polish hospital, identified using ICD-10 codes.
Main Results:
- The DRSA algorithm generated 45 decision rules for recognizing KD.
- High-sensitivity rules (zero false negatives) identified key indicators: conjunctivitis with CRP ≥ 40.1 mg/L, thrombocytosis with ESR ≥ 77 mm/h, fever ≥ 5 days with rash/conjunctivitis, and fever ≥ 5 days with rash and CRP ≥ 7.05 mg/L.
Conclusions:
- DRSA analysis shows promise for early KD diagnosis in children.
- The method is effective even with limited clinical or laboratory data, aiding differential diagnosis.
Abstract:
The DRSA method (dominance-based rough set approach) was used to create decision-making rules based on the results of physical examination and additional laboratory tests in the differential diagnosis of Kawasaki disease (KD), infectious mononucleosis and S. pyogenes pharyngitis in children. The study was conducted retrospectively. The search was based on the ICD-10 (International Classification of Diseases) codes of final diagnosis. Demographic and laboratory data from one Polish hospital (Poznan) were collected. Traditional statistical methods and the DRSA method were applied in data analysis. The algorithm formed 45 decision rules recognizing KD. The rules with the highest sensitivity (number of false negatives equals zero) were based on the presence of conjunctivitis and CRP (C-reactive Protein) ≥ 40.1 mg/L, thrombocytosis and ESR (Erythrocyte Sedimentation Rate) ≥ 77 mm/h; fair general condition and fever ≥ 5 days and rash; fair general condition and fever ≥ 5 days and conjunctivitis; fever ≥ 5 days and rash and CRP ≥ 7.05 mg/L. The DRSA analysis may be helpful in diagnosing KD at an early stage of the disease. It can be used even with a small amount of clinical or laboratory data.
Related Concept Videos
01:22Rheumatic Heart Disease II: Clinical Manifestations and Diagnostic Studies
01:25Assessment of apical radial pulse
The A-R pulse assessment involves simultaneous evaluation of the apical and radial pulses. When the apical and radial pulse rates vary, this assessment helps identify a pulse deficit.
Pre-Procedural Preparation
01:30Acute Coronary Syndrome III: Diagnostic Studies