EUVIMEDEUVIMED entdecken
Multizentrische Studie

Prediction of inhibitor development in previously untreated and minimally treated children with severe and moderately severe hemophilia A using a machine-learning network

Letícia Lemos Jardim, Tiago A Schieber, Marcio Portugal Santana, Mônica Hermida Cerqueira, Claudia Santos Lorenzato, Vivian Karla Brognoli Franco, Luciana Werneck Zuccherato, Brendon Ayala da Silva Santos, Daniel Gonçalves Chaves, Martín Gomez Ravetti, Suely Meireles Rezende

Journal of Thrombosis and Haemostasis · 2024

DOI: 10.1016/j.jtha.2024.05.017 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of Thrombosis and Haemostasis, 2024. Verfasst von Letícia Lemos Jardim und 10 weiteren Autor:innen. Beteiligte Einrichtung: Instituto René Rachou (Fiocruz Minas), Belo Horizonte, Minas Gerais, Brazil; Department of Clinical Epidemiology, Leiden University Medical Centre, L…. Hauptthemen laut MEDLINE: Factor VIII, Hemophilia A, Machine Learning, Severity of Illness Index. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 75 Literaturangaben. Gefördert von: Minas Gerais State Foundation of Support to the Research, Coordination of Higher Education Personnel Improvement, Conselho Nacional de Desenvolvimento Científico e Tecnológico.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Prediction of inhibitor development in patients with hemophilia A (HA) remains a challenge. OBJECTIVES: To construct a predictive model for inhibitor development in HA using a network of clinical variables and biomarkers based on the individual similarity network. METHODS: Previously untreated and minimally treated children with severe/moderately severe HA, participants of the HEMFIL Cohort Study, were followed up until reaching 75 exposure days (EDs) without inhibitor (INH-) or upon inhibitor development (INH+). Clinical data and biological samples were collected before the start of factor (F)VIII replacement (T0). A predictive model (HemfilNET) was built to compare the networks and potential global topological differences between INH- and INH+ at T0, considering the network robustness. For validation, the "leave-one-out" cross-validation technique was employed. Accuracy, precision, recall, and F1-score were used as evaluation metrics for the machine-learning model. RESULTS: We included 95 children with HA (CHA), of whom 31 (33%) developed inhibitors. The algorithm, featuring 37 variables, identified distinct patterns of networks at T0 for INH+ and INH-. The accuracy of the model was 74.2% for CHA INH+ and 98.4% for INH-. By focusing the analysis on CHA with high-risk F8 mutations for inhibitor development, the accuracy in identifying CHA INH+ increased to 82.1%. CONCLUSION: Our machine-learning algorithm demonstrated an overall accuracy of 90.5% for predicting inhibitor development in CHA, which further improved when restricting the analysis to CHA with a high-risk F8 genotype. However, our model requires validation in other cohorts. Yet, missing data for some variables hindered more precise predictions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Factor VIIIHemophilia AMachine LearningSeverity of Illness IndexHumansInfantMaleBiomarkersBlood Coagulation Factor InhibitorsPredictive Value of TestsReproducibility of ResultsRisk AssessmentRisk FactorsTime FactorsTreatment Outcome

Stichwörter der Autor:innen

factor VIIIhemophilia Ainhibitormachine-learningpreviously untreated children

Substanzen

BiomarkersBlood Coagulation Factor InhibitorsF8 protein, humanFactor VIII

Autor:innen und Institutionen

  • Instituto René Rachou (Fiocruz Minas), Belo Horizonte, Minas Gerais, Brazil; Department of Clinical Epidemiology, Leiden University Medical Centre, Leiden, the Netherlands.
  • Faculdade de Ciências Econômicas, School of Economics, Universidade Federal de Minas Gerais, Brazil.
  • Fundação Hemominas, Belo Horizonte, Minas Gerais, Brazil.
  • Instituto de Hematologia Arthur de Siqueira Cavalcanti, Rio de Janeiro, Brazil.
  • Centro de Hematologia e Hemoterapia do Paraná, Curitiba, Brazil.
  • Centro de Hematologia e Hemoterapia de Santa Catarina, Florianópolis, Brazil.

Förderung

  • Minas Gerais State Foundation of Support to the Research
  • Coordination of Higher Education Personnel Improvement
  • Conselho Nacional de Desenvolvimento Científico e Tecnológico
  • National Health Foundation
  • Ministério da Saúde

Zitieren

APA

Jardim, L. L., Schieber, T. A., Santana, M. P., Cerqueira, M. H., Lorenzato, C. S., Franco, V. K. B., Zuccherato, L. W., da Silva Santos, B. A., Chaves, D. G., Ravetti, M. G., & Rezende, S. M. (2024). Prediction of inhibitor development in previously untreated and minimally treated children with severe and moderately severe hemophilia A using a machine-learning network. Journal of Thrombosis and Haemostasis. https://doi.org/10.1016/j.jtha.2024.05.017

Vancouver

Jardim LL, Schieber TA, Santana MP, Cerqueira MH, Lorenzato CS, Franco VKB, et al. Prediction of inhibitor development in previously untreated and minimally treated children with severe and moderately severe hemophilia A using a machine-learning network. Journal of Thrombosis and Haemostasis. 2024. doi:10.1016/j.jtha.2024.05.017

BibTeX
@article{Jardim2024,
  author = {Jardim, Letícia Lemos and Schieber, Tiago A and Santana, Marcio Portugal and Cerqueira, Mônica Hermida and Lorenzato, Claudia Santos and Franco, Vivian Karla Brognoli and Zuccherato, Luciana Werneck and da Silva Santos, Brendon Ayala and Chaves, Daniel Gonçalves and Ravetti, Martín Gomez and Rezende, Suely Meireles},
  title = {Prediction of inhibitor development in previously untreated and minimally treated children with severe and moderately severe hemophilia A using a machine-learning network},
  journal = {Journal of Thrombosis and Haemostasis},
  year = {2024},
  doi = {10.1016/j.jtha.2024.05.017}
}
Kostenlos starten →