Interpretable machine-learning prognosis of mycetoma from routine clinical data
Transactions of The Royal Society of Tropical Medicine and Hygiene · 2026
DOI: 10.1093/trstmh/trag061 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of The Royal Society of Tropical Medicine and Hygiene, 2026. Verfasst von Maha H Yousif und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Mathematics, University of Khartoum, Khartoum 11111, Sudan. Hauptthemen laut MEDLINE: Mycetoma, Machine Learning. Die Arbeit nennt 71 Literaturangaben. Gefördert von: MRC.
Abstract (Originalsprache)
Background
Mycetoma is a chronic tropical infection with limited tools for predicting treatment outcomes.
Methods
Routinely collected demographic, clinical, imaging, etiological, treatment, and follow-up data from 1,084 patients at the Mycetoma Research Centre were used to evaluate supervised machine learning models for outcome prediction. Binary and three-class tasks (cured, recurrence, disability) were assessed using stratified five-fold cross-validation with preprocessing, imputation, scaling, and class balancing. Logistic regression, support vector machine, and random forest models were compared.
Results
Treatment mode, treatment duration, disease duration at presentation, adherence, lesion size, and imaging findings were the most important predictors. In eumycetoma, random forest achieved the best binary performance (accuracy 0.760 ± 0.036; ROC-AUC 0.835 ± 0.036). In actinomycetoma, random forest achieved accuracy of 0.719 ± 0.115 and ROC-AUC of 0.779 ± 0.138. For the three-class task, random forest performed best in eumycetoma (accuracy 0.612 ± 0.033; macro-AUC 0.777 ± 0.029), while logistic regression performed best in actinomycetoma (accuracy 0.735 ± 0.097; macro-AUC 0.713 ± 0.092).
Conclusions
Standard clinical and imaging variables can support machine learning-based risk stratification in mycetoma, potentially improving early management and follow-up. External validation and clinical utility assessment are still required.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Applied Mathematics, University of Khartoum, Khartoum 11111, Sudan.
- Department of Mathematical Science, Delaware State University, Dover, DE 19901, United States.
- Department of Mathematics, Georgia State University, Atlanta, GA, United States.
- Mycetoma Research Centre, University of Khartoum, Khartoum 11111, Sudan.
- Faculty of Pharmacy, National University-Sudan, Khartoum 11111, Sudan.
ORCID-Profile: Ali Awadallah Saeed
Förderung
- MRC
Zitieren
APA
Yousif, M. H., Alsammani, A., Abdalla, M. H., Bashier, E. B. M., Mohammed, M. A. Y., Saeed, A. A., & Fahal, A. H. (2026). Interpretable machine-learning prognosis of mycetoma from routine clinical data. Transactions of The Royal Society of Tropical Medicine and Hygiene. https://doi.org/10.1093/trstmh/trag061
Vancouver
Yousif MH, Alsammani A, Abdalla MH, Bashier EBM, Mohammed MAY, Saeed AA, et al. Interpretable machine-learning prognosis of mycetoma from routine clinical data. Transactions of The Royal Society of Tropical Medicine and Hygiene. 2026. doi:10.1093/trstmh/trag061
BibTeX
@article{Yousif2026,
author = {Yousif, Maha H and Alsammani, Abdallah and Abdalla, Mohsin H and Bashier, Eihab B M and Mohammed, Mohammed A Y and Saeed, Ali Awadallah and Fahal, Ahmed H},
title = {Interpretable machine-learning prognosis of mycetoma from routine clinical data},
journal = {Transactions of The Royal Society of Tropical Medicine and Hygiene},
year = {2026},
doi = {10.1093/trstmh/trag061}
}
EUVIMED