EUVIMEDEUVIMED entdecken
Open Access

Distinguishing Multisystem Inflammatory Syndrome in Children From Typhus Using Artificial Intelligence: MIS-C Versus Endemic Typhus (AI-MET)

Angela Chun, Abraham Bautista-Castillo iD, Isabella Osuna iD, Kristiana Nasto, Flor M Munoz iD, Gordon E Schutze, Sridevi Devaraj, Eyal Muscal, Marietta M de Guzman, Kristen Sexson Tejtel iD, Tiphanie P Vogel iD, Ioannis A Kakadiaris

The Journal of Infectious Diseases · 15.04.2025 · 231 (4) · 931-939

DOI: 10.1093/infdis/jiaf004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Infectious Diseases, online erschienen am 07.01.2025. Verfasst von Angela Chun und 11 weiteren Autor:innen. Beteiligte Einrichtung: Division of Rheumatology, Department of Pediatrics, Baylor College of Medicine and Texas Children's Hospital, Houston, Texas, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, COVID-19, Systemic Inflammatory Response Syndrome, Typhus, Endemic Flea-Borne. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NICHD NIH HHS, NIH HHS, National Council of Science and Technology of Mexico.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The pandemic emergent disease multisystem inflammatory syndrome in children (MIS-C) following coronavirus disease-19 infection can mimic endemic typhus. We aimed to use artificial intelligence (AI) to develop a clinical decision support system that accurately distinguishes MIS-C versus endemic typhus (MET).

Methods

Demographic, clinical, and laboratory features rapidly available following presentation were extracted for 133 patients with MIS-C and 87 patients hospitalized due to typhus. An attention module assigned importance to inputs used to create the 2-phase AI-MET. Phase 1 uses 17 features to arrive at a classification manually (MET-17). If the confidence level is not surpassed, 13 additional features are added to calculate MET-30 using a recurrent neural network.

Results

While 24 of 30 features differed statistically, the values overlapped sufficiently that the features were clinically irrelevant distinguishers as individual parameters. However, AI-MET successfully classified typhus and MIS-C with 100% accuracy. A validation cohort of 111 additional patients with MIS-C was classified with 99% accuracy.

Conclusions

Artificial intelligence can successfully distinguish MIS-C from typhus using rapidly available features. This decision support system will be a valuable tool for front-line providers facing the difficulty of diagnosing a febrile child in endemic areas.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceCOVID-19Systemic Inflammatory Response SyndromeTyphus, Endemic Flea-BorneHumansChildMaleFemaleChild, PreschoolDiagnosis, DifferentialAdolescentScrub TyphusSARS-CoV-2Infant

Stichwörter der Autor:innen

artificial intelligenceendemic typhusmachine learningmultisystem inflammatory syndrome in children (MIS-C)murine typhus

Autor:innen und Institutionen

  • Division of Rheumatology, Department of Pediatrics, Baylor College of Medicine and Texas Children's Hospital, Houston, Texas, USA.
  • Computational Biomedicine Laboratory, Department of Computer Science, University of Houston, Houston, Texas, USA.
  • Baylor College of Medicine, Houston, Texas, USA.
  • Division of Infectious Diseases, Department of Pediatrics, Baylor College of Medicine and Texas Children's Hospital, Houston, Texas, USA.
  • Department of Pathology and Immunology, Baylor College of Medicine and Texas Children's Hospital, Houston, Texas, USA.
  • Division of Cardiology, Department of Pediatrics, Baylor College of Medicine and Texas Children's Hospital, Houston, Texas, USA.

ORCID-Profile: Abraham Bautista-Castillo, Isabella Osuna, Flor M Munoz, Kristen Sexson Tejtel, Tiphanie P Vogel

Förderung

  • NICHD NIH HHS
  • NIH HHS
  • National Council of Science and Technology of Mexico
  • National Institutes of Health

Zitieren

APA

Chun, A., Bautista-Castillo, A., Osuna, I., Nasto, K., Munoz, F. M., Schutze, G. E., Devaraj, S., Muscal, E., de Guzman, M. M., Sexson Tejtel, K., Vogel, T. P., & Kakadiaris, I. A. (2025). Distinguishing Multisystem Inflammatory Syndrome in Children From Typhus Using Artificial Intelligence: MIS-C Versus Endemic Typhus (AI-MET). The Journal of Infectious Diseases, 231(4), 931-939. https://doi.org/10.1093/infdis/jiaf004

Vancouver

Chun A, Bautista-Castillo A, Osuna I, Nasto K, Munoz FM, Schutze GE, et al. Distinguishing Multisystem Inflammatory Syndrome in Children From Typhus Using Artificial Intelligence: MIS-C Versus Endemic Typhus (AI-MET). The Journal of Infectious Diseases. 2025;231(4):931-939. doi:10.1093/infdis/jiaf004

BibTeX
@article{Chun2025,
  author = {Chun, Angela and Bautista-Castillo, Abraham and Osuna, Isabella and Nasto, Kristiana and Munoz, Flor M and Schutze, Gordon E and Devaraj, Sridevi and Muscal, Eyal and de Guzman, Marietta M and Sexson Tejtel, Kristen and Vogel, Tiphanie P and Kakadiaris, Ioannis A},
  title = {Distinguishing Multisystem Inflammatory Syndrome in Children From Typhus Using Artificial Intelligence: MIS-C Versus Endemic Typhus (AI-MET)},
  journal = {The Journal of Infectious Diseases},
  year = {2025},
  volume = {231},
  number = {4},
  pages = {931--939},
  doi = {10.1093/infdis/jiaf004}
}
Kostenlos starten →