PMID- 36797460
OWN - NLM
STAT- MEDLINE
DCOM- 20240229
LR  - 20240302
IS  - 1530-0447 (Electronic)
IS  - 0031-3998 (Print)
IS  - 0031-3998 (Linking)
VI  - 95
IP  - 3
DP  - 2024 Feb
TI  - Intravenous immunoglobulin resistance in Kawasaki disease patients: prediction 
      using clinical data.
PG  - 692-697
LID - 10.1038/s41390-023-02519-z [doi]
AB  - BACKGROUND: About 10-20% of Kawasaki disease (KD) patients are resistant to the 
      initial infusion of intravenous immunoglobin (IVIG). The aim of this study was to 
      assess whether IVIG resistance in KD patients could be predicted using standard 
      clinical and laboratory features. METHODS: Data were from two cohorts: a Korean 
      cohort of 7101 KD patients from 2015 to 2017 and a cohort of 649 KD patients from 
      San Diego enrolled from 1998 to 2021. Features included laboratory values, the 
      worst Z-score from the initial echocardiogram or during hospitalization, and the 
      five clinical KD signs at presentation. RESULTS: Five machine learning models 
      achieved a maximum median AUC of 0.711 [IQR: 0.706-0.72] in the Korean cohort and 
      0.696 [IQR: 0.609-0.722] in the San Diego cohort during stratified 10-fold 
      cross-validation using significant laboratory features identified from univariate 
      analysis. Adding the Z-score, KD clinical signs, or both did not considerably 
      improve the median AUC in either cohort. CONCLUSIONS: Using commonly measured 
      clinical laboratory data alone or in conjunction with echocardiographic findings 
      and clinical features is not sufficient to predict IVIG resistance. Further 
      attempts to predict IVIG resistance will need to incorporate additional data such 
      as transcriptomics, proteomics, and genetics to achieve meaningful predictive 
      utility. IMPACT: We demonstrated that laboratory, echocardiographic, and clinical 
      findings cannot predict intravenous immunoglobin (IVIG) resistance to a 
      clinically meaningful extent using machine learning in a homogenous Asian or 
      ethnically diverse population of patients with Kawasaki disease (KD). Visualizing 
      these features using uniform manifold approximation and projection (UMAP) is an 
      important step to evaluate predictive utility in a qualitative manner. Further 
      attempts to predict IVIG resistance in KD patients will need to incorporate novel 
      biomarkers or other specialized features such as genetic differences or 
      transcriptomics to be clinically useful.
CI  - (c) 2023. The Author(s).
FAU - Lam, Jonathan Y
AU  - Lam JY
AD  - Department of Biomedical Informatics, University of California San Diego, La 
      Jolla, CA, USA. j7lam@ucsd.edu.
FAU - Song, Min-Seob
AU  - Song MS
AD  - Department of Pediatrics, Haeundae Paik Hospital, Inje University, Busan, South 
      Korea.
FAU - Kim, Gi-Beom
AU  - Kim GB
AD  - Department of Pediatrics, Seoul National University Children's Hospital, Seoul 
      National University College of Medicine, Seoul, South Korea.
FAU - Shimizu, Chisato
AU  - Shimizu C
AD  - Department of Pediatrics, Rady Children's Hospital and University of California 
      San Diego, San Diego, CA, USA.
FAU - Bainto, Emelia
AU  - Bainto E
AD  - Department of Pediatrics, Rady Children's Hospital and University of California 
      San Diego, San Diego, CA, USA.
FAU - Tremoulet, Adriana H
AU  - Tremoulet AH
AD  - Department of Pediatrics, Rady Children's Hospital and University of California 
      San Diego, San Diego, CA, USA.
FAU - Nemati, Shamim
AU  - Nemati S
AD  - Department of Biomedical Informatics, University of California San Diego, La 
      Jolla, CA, USA.
FAU - Burns, Jane C
AU  - Burns JC
AD  - Department of Pediatrics, Rady Children's Hospital and University of California 
      San Diego, San Diego, CA, USA.
LA  - eng
GR  - R01 LM013998/LM/NLM NIH HHS/United States
GR  - T15 LM011271/LM/NLM NIH HHS/United States
PT  - Journal Article
DEP - 20230216
PL  - United States
TA  - Pediatr Res
JT  - Pediatric research
JID - 0100714
RN  - 0 (Biomarkers)
RN  - 0 (Immunoglobulins, Intravenous)
SB  - IM
MH  - Humans
MH  - Infant
MH  - Biomarkers
MH  - Drug Resistance
MH  - *Immunoglobulins, Intravenous/therapeutic use
MH  - *Mucocutaneous Lymph Node Syndrome/diagnosis/drug therapy
MH  - Retrospective Studies
MH  - East Asian People
PMC - PMC9934506
COIS- The authors declare no competing interests.
EDAT- 2023/02/17 06:00
MHDA- 2024/02/29 06:42
PMCR- 2023/02/16
CRDT- 2023/02/16 23:26
PHST- 2022/07/12 00:00 [received]
PHST- 2023/01/25 00:00 [accepted]
PHST- 2023/01/18 00:00 [revised]
PHST- 2024/02/29 06:42 [medline]
PHST- 2023/02/17 06:00 [pubmed]
PHST- 2023/02/16 23:26 [entrez]
PHST- 2023/02/16 00:00 [pmc-release]
AID - 10.1038/s41390-023-02519-z [pii]
AID - 2519 [pii]
AID - 10.1038/s41390-023-02519-z [doi]
PST - ppublish
SO  - Pediatr Res. 2024 Feb;95(3):692-697. doi: 10.1038/s41390-023-02519-z. Epub 2023 
      Feb 16.