EUVIMEDEUVIMED entdecken
Multizentrische Studie

MALrisk: a machine-learning–based tool to predict imported malaria in returned travellers with fever

Leire Balerdi-Sarasola iD, Pedro Fleitas iD, Emmanuel Bottieau, Blaise Genton, Paula Petrone iD, Jose Muñoz, Daniel Camprubí-Ferrer iD

Journal of Travel Medicine · 10.12.2024 · 31 (8)

DOI: 10.1093/jtm/taae054 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of Travel Medicine, online erschienen am 05.04.2024. Verfasst von Leire Balerdi-Sarasola und 6 weiteren Autor:innen. Beteiligte Einrichtung: ISGlobal, Hospital Clínic, Universitat de Barcelona, Barcelona, Spain. Hauptthemen laut MEDLINE: Machine Learning, Travel, Fever. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: Spanish Ministry of Science and Innovation and State Research Agency, CIBER-Consorcio Centro de Investigación Biomédica en Red, Generalitat de Catalunya through the CERCA Program and AGAUR program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Early diagnosis is key to reducing the morbi-mortality associated with P. falciparum malaria among international travellers. However, access to microbiological tests can be challenging for some healthcare settings. Artificial Intelligence could improve the management of febrile travellers.

Methods

Data from a multicentric prospective study of febrile travellers were obtained to build a machine-learning model to predict malaria cases among travellers presenting with fever. Demographic characteristics, clinical and laboratory variables were leveraged as features. Eleven machine-learning classification models were evaluated by 50-fold cross-validation in a Training set. Then, the model with the best performance, defined by the Area Under the Curve (AUC), was chosen for parameter optimization and evaluation in the Test set. Finally, a reduced model was elaborated with those features that contributed most to the model.

Results

Out of 11 machine-learning models, XGBoost presented the best performance (mean AUC of 0.98 and a mean F1 score of 0.78). A reduced model (MALrisk) was developed using only six features: Africa as a travel destination, platelet count, rash, respiratory symptoms, hyperbilirubinemia and chemoprophylaxis intake. MALrisk predicted malaria cases with 100% (95%CI 96–100) sensitivity and 72% (95%CI 68–75) specificity.

Conclusions

The MALrisk can aid in the timely identification of malaria in non-endemic settings, allowing the initiation of empiric antimalarials and reinforcing the need for urgent transfer in healthcare facilities with no access to malaria diagnostic tests. This resource could be easily scalable to a digital application and could reduce the morbidity associated with late diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningTravelFeverHumansProspective StudiesMaleFemaleAdultMalaria, FalciparumCommunicable Diseases, ImportedMiddle AgedMalariaAntimalarials

Stichwörter der Autor:innen

Malariamachine-learningtravellers

Substanzen

Antimalarials

Autor:innen und Institutionen

  • ISGlobal, Hospital Clínic, Universitat de Barcelona, Barcelona, Spain.
  • Department of Clinical Sciences, Institute of Tropical Medicine, Antwerp, Belgium.
  • Center for Primary Care and Public Health, University of Lausanne, Lausanne, Switzerland.

ORCID-Profile: Leire Balerdi-Sarasola, Pedro Fleitas, Paula Petrone, Daniel Camprubí-Ferrer

Förderung

  • Spanish Ministry of Science and Innovation and State Research Agency
  • CIBER-Consorcio Centro de Investigación Biomédica en Red
  • Generalitat de Catalunya through the CERCA Program and AGAUR program

Zitieren

APA

Balerdi-Sarasola, L., Fleitas, P., Bottieau, E., Genton, B., Petrone, P., Muñoz, J., & Camprubí-Ferrer, D. (2024). MALrisk: a machine-learning–based tool to predict imported malaria in returned travellers with fever. Journal of Travel Medicine, 31(8). https://doi.org/10.1093/jtm/taae054

Vancouver

Balerdi-Sarasola L, Fleitas P, Bottieau E, Genton B, Petrone P, Muñoz J, et al. MALrisk: a machine-learning–based tool to predict imported malaria in returned travellers with fever. Journal of Travel Medicine. 2024;31(8). doi:10.1093/jtm/taae054

BibTeX
@article{BalerdiSarasola2024,
  author = {Balerdi-Sarasola, Leire and Fleitas, Pedro and Bottieau, Emmanuel and Genton, Blaise and Petrone, Paula and Muñoz, Jose and Camprubí-Ferrer, Daniel},
  title = {MALrisk: a machine-learning–based tool to predict imported malaria in returned travellers with fever},
  journal = {Journal of Travel Medicine},
  year = {2024},
  volume = {31},
  number = {8},
  doi = {10.1093/jtm/taae054}
}
Kostenlos starten →